Fix find_in_batches with customized primary_key

activerecord/CHANGELOG.md

@@ -1,5 +1,20 @@
 ## Rails 4.0.0 (unreleased) ##
 
+*   Fix `find_in_batches` when primary_key is set other than id.
+    You can now use this method with the primary key which is not integer-based.
+
+    Example:
+
+        class Post < ActiveRecord::Base
+          self.primary_key = :title
+        end
+
+        Post.find_in_batches(:start => 'My First Post') do |batch|
+          batch.each { |post| post.author.greeting }
+        end
+
+    *Toshiyuki Kawanishi*
+
 *   You can now override the generated accessor methods for stored attributes
     and reuse the original behavior with `read_store_attribute` and `write_store_attribute`,
     which are counterparts to `read_attribute` and `write_attribute`.

activerecord/lib/active_record/relation/batches.rb

@@ -36,12 +36,12 @@ def find_each(options = {})
     # 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).
+    # option on that worker). You can also use non-integer-based primary keys
+    # if start point is set.
     #
     # 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
+    # ascending on the primary key (e.g. "id ASC") to make the batch ordering
+    # work. You can't set the limit either, that's used to control
     # the batch sizes.
     #
     #   Person.where("age > 21").find_in_batches do |group|
@@ -62,15 +62,16 @@ def find_in_batches(options = {})
         ActiveRecord::Base.logger.warn("Scoped order and limit are ignored, it's forced to be batch order and batch size")
       end
 
-      start = options.delete(:start).to_i
+      start = options.delete(:start)
+      start ||= 0
       batch_size = options.delete(:batch_size) || 1000
 
       relation = relation.reorder(batch_order).limit(batch_size)
       records = relation.where(table[primary_key].gteq(start)).to_a
 
       while records.any?
         records_size = records.size
-        primary_key_offset = records.last.id
+        primary_key_offset = records.last.send(primary_key)
 
         yield records
 

activerecord/test/cases/batches_test.rb

@@ -124,4 +124,15 @@ def test_find_in_batches_should_not_ignore_the_default_scope_if_it_is_other_then
     assert_equal special_posts_ids, posts.map(&:id)
   end
 
+  def test_find_in_batches_should_use_any_column_as_primary_key
+    title_order_posts = Post.order('title asc')
+    start_title = title_order_posts.first.title
+
+    posts = []
+    PostWithTitlePrimaryKey.find_in_batches(:batch_size => 1, :start => start_title) do |batch|
+      posts.concat(batch)
+    end
+
+    assert_equal title_order_posts.map(&:id), posts.map(&:id)
+  end
 end

activerecord/test/models/post.rb

@@ -186,3 +186,8 @@ class SpecialPostWithDefaultScope < ActiveRecord::Base
   self.table_name = 'posts'
   default_scope { where(:id => [1, 5,6]) }
 end
+
+class PostWithTitlePrimaryKey < ActiveRecord::Base
+  self.table_name = 'posts'
+  self.primary_key = :title
+end