Add support for passing the list of columns to update in upsert_all

rails#41933 added a new `on_duplicate:` option to `upsert_all`, to allow
providing custom SQL update code. This change makes `on_duplicate` admit
an array of columns too, so that `upsert_all` only updates those
columns when a conflict happens.

This allows limiting the list of updated column in a database-agnostic
way.

Author: jorgemanrubia

activerecord/CHANGELOG.md

@@ -1,3 +1,20 @@
+*   Add a new option `:update_only` to `upsert_all` to configure the list of columns to update in case of conflict.
+
+    Before, you could only customize the update SQL sentence via `:on_duplicate`. There is now a new option `:update_only` that lets you provide a list of columns to update in case of conflict:
+
+    ```ruby
+    Commodity.upsert_all(
+      [
+        { id: 2, name: "Copper", price: 4.84 },
+        { id: 4, name: "Gold", price: 1380.87 },
+        { id: 6, name: "Aluminium", price: 0.35 }
+      ],
+      update_only: [:price] # Only prices will be updated
+    )
+    ```
+
+    *Jorge Manrubia*
+
 *   Remove deprecated `ActiveRecord::Result#map!` and `ActiveRecord::Result#collect!`.
 
     *Rafael Mendonça França*

activerecord/lib/active_record/insert_all.rb

@@ -5,22 +5,19 @@
 module ActiveRecord
   class InsertAll # :nodoc:
     attr_reader :model, :connection, :inserts, :keys
-    attr_reader :on_duplicate, :returning, :unique_by, :update_sql
+    attr_reader :on_duplicate, :update_only, :returning, :unique_by, :update_sql
 
-    def initialize(model, inserts, on_duplicate:, returning: nil, unique_by: nil, record_timestamps: nil)
+    def initialize(model, inserts, on_duplicate:, update_only: nil, returning: nil, unique_by: nil, record_timestamps: nil)
       raise ArgumentError, "Empty list of attributes passed" if inserts.blank?
 
       @model, @connection, @inserts, @keys = model, model.connection, inserts, inserts.first.keys.map(&:to_s)
-      @on_duplicate, @returning, @unique_by = on_duplicate, returning, unique_by
+      @on_duplicate, @update_only, @returning, @unique_by = on_duplicate, update_only, returning, unique_by
       @record_timestamps = record_timestamps.nil? ? model.record_timestamps : record_timestamps
 
-      disallow_raw_sql!(returning)
       disallow_raw_sql!(on_duplicate)
+      disallow_raw_sql!(returning)
 
-      if Arel.arel_node?(on_duplicate)
-        @update_sql = on_duplicate
-        @on_duplicate = :update
-      end
+      configure_on_duplicate_update_logic
 
       if model.scope_attributes?
         @scope_attributes = model.scope_attributes
@@ -45,7 +42,7 @@ def execute
     end
 
     def updatable_columns
-      keys - readonly_columns - unique_by_columns
+      @updatable_columns ||= keys - readonly_columns - unique_by_columns
     end
 
     def primary_keys
@@ -91,6 +88,24 @@ def keys_including_timestamps
     private
       attr_reader :scope_attributes
 
+      def configure_on_duplicate_update_logic
+        if custom_update_sql_provided? && update_only.present?
+          raise ArgumentError, "You can't set :update_only and provide custom update SQL via :on_duplicate at the same time"
+        end
+
+        if update_only.present?
+          @updatable_columns = Array(update_only)
+          @on_duplicate = :update
+        elsif custom_update_sql_provided?
+          @update_sql = on_duplicate
+          @on_duplicate = :update
+        end
+      end
+
+      def custom_update_sql_provided?
+        @custom_update_sql_provided ||= Arel.arel_node?(on_duplicate)
+      end
+
       def find_unique_index_for(unique_by)
         if !connection.supports_insert_conflict_target?
           return if unique_by.nil?

activerecord/lib/active_record/persistence.rb

@@ -235,6 +235,10 @@ def upsert(attributes, on_duplicate: :update, returning: nil, unique_by: nil, re
       # Returns an <tt>ActiveRecord::Result</tt> with its contents based on
       # <tt>:returning</tt> (see below).
       #
+      # By default, +upsert_all+ will update all the columns that can be updated when
+      # there is a conflict. These are all the columns except primary keys, read-only
+      # columns, and columns covered by the optional +unique_by+.
+      #
       # ==== Options
       #
       # [:returning]
@@ -268,9 +272,41 @@ def upsert(attributes, on_duplicate: :update, returning: nil, unique_by: nil, re
       # Active Record's schema_cache.
       #
       # [:on_duplicate]
-      #   Specify a custom SQL for updating rows on conflict.
+      #   Configure the SQL update sentence that will be used in case of conflict.
+      #
+      #   NOTE: If you use this option you must provide all the columns you want to update
+      #   by yourself.
+      #
+      #   Example:
+      #
+      #     Commodity.upsert_all(
+      #       [
+      #         { id: 2, name: "Copper", price: 4.84 },
+      #         { id: 4, name: "Gold", price: 1380.87 },
+      #         { id: 6, name: "Aluminium", price: 0.35 }
+      #       ],
+      #       on_duplicate: Arel.sql("price = GREATEST(commodities.price, EXCLUDED.price)")
+      #     )
+      #
+      #   See the related +:update_only+ option. Both options can't be used at the same time.
+      #
+      # [:update_only]
+      #   Provide a list of column names that will be updated in case of conflict. If not provided,
+      #   +upsert_all+ will update all the columns that can be updated. These are all the columns
+      #   except primary keys, read-only columns, and columns covered by the optional +unique_by+
+      #
+      #   Example:
+      #
+      #     Commodity.upsert_all(
+      #       [
+      #         { id: 2, name: "Copper", price: 4.84 },
+      #         { id: 4, name: "Gold", price: 1380.87 },
+      #         { id: 6, name: "Aluminium", price: 0.35 }
+      #       ],
+      #       on_duplicate: [:price] # Only prices will be updated
+      #     )
       #
-      #   NOTE: in this case you must provide all the columns you want to update by yourself.
+      #   See the related +:on_duplicate+ option. Both options can't be used at the same time.
       #
       # [:record_timestamps]
       #   By default, automatic setting of timestamp columns is controlled by
@@ -294,8 +330,8 @@ def upsert(attributes, on_duplicate: :update, returning: nil, unique_by: nil, re
       #   ], unique_by: :isbn)
       #
       #   Book.find_by(isbn: "1").title # => "Eloquent Ruby"
-      def upsert_all(attributes, on_duplicate: :update, returning: nil, unique_by: nil, record_timestamps: nil)
-        InsertAll.new(self, attributes, on_duplicate: on_duplicate, returning: returning, unique_by: unique_by, record_timestamps: record_timestamps).execute
+      def upsert_all(attributes, on_duplicate: :update, update_only: nil, returning: nil, unique_by: nil, record_timestamps: nil)
+        InsertAll.new(self, attributes, on_duplicate: on_duplicate, update_only: update_only, returning: returning, unique_by: unique_by, record_timestamps: record_timestamps).execute
       end
 
       # Given an attributes hash, +instantiate+ returns a new instance of

activerecord/test/cases/insert_all_test.rb

@@ -336,6 +336,31 @@ def test_upsert_all_does_not_update_primary_keys
     assert_equal "1974522598", book.isbn, "Should have updated the isbn"
   end
 
+  def test_passing_both_on_update_and_update_only_will_raise_an_error
+    assert_raises ArgumentError do
+      Book.upsert_all [{ id: 101, name: "Perelandra", author_id: 7, isbn: "1974522598" }], on_duplicate: "NAME=values(name)", update_only: :name
+    end
+  end
+
+  def test_upsert_all_only_updates_the_column_provided_via_update_only
+    Book.upsert_all [{ id: 101, name: "Perelandra", author_id: 7, isbn: "1974522598" }]
+    Book.upsert_all [{ id: 101, name: "Perelandra 2", author_id: 7, isbn: "111111" }], update_only: :name
+
+    book = Book.find(101)
+    assert_equal "Perelandra 2", book.name, "Should have updated the name"
+    assert_equal "1974522598", book.isbn, "Should not have updated the isbn"
+  end
+
+  def test_upsert_all_only_updates_the_list_of_columns_provided_via_update_only
+    Book.upsert_all [{ id: 101, name: "Perelandra", author_id: 7, isbn: "1974522598" }]
+    Book.upsert_all [{ id: 101, name: "Perelandra 2", author_id: 6, isbn: "111111" }], update_only: %i[ name isbn ]
+
+    book = Book.find(101)
+    assert_equal "Perelandra 2", book.name, "Should have updated the name"
+    assert_equal "111111", book.isbn, "Should have updated the isbn"
+    assert_equal 7, book.author_id, "Should not have updated the author_id"
+  end
+
   def test_upsert_all_does_not_perform_an_upsert_if_a_partial_index_doesnt_apply
     skip unless supports_insert_on_duplicate_update? && supports_insert_conflict_target? && supports_partial_index?