path: root/activerecord/lib/active_record/association_preload.rb

require 'active_support/core_ext/array/wrap'
require 'active_support/core_ext/enumerable'

module ActiveRecord
  # See ActiveRecord::AssociationPreload::ClassMethods for documentation.
  module AssociationPreload #:nodoc:
    extend ActiveSupport::Concern

    # Implements the details of eager loading of Active Record associations.
    # Application developers should not use this module directly.
    #
    # <tt>ActiveRecord::Base</tt> is extended with this module. The source code in
    # <tt>ActiveRecord::Base</tt> references methods defined in this module.
    #
    # Note that 'eager loading' and 'preloading' are actually the same thing.
    # However, there are two different eager loading strategies.
    #
    # The first one is by using table joins. This was only strategy available
    # prior to Rails 2.1. Suppose that you have an Author model with columns
    # 'name' and 'age', and a Book model with columns 'name' and 'sales'. Using
    # this strategy, Active Record would try to retrieve all data for an author
    # and all of its books via a single query:
    #
    #   SELECT * FROM authors
    #   LEFT OUTER JOIN books ON authors.id = books.id
    #   WHERE authors.name = 'Ken Akamatsu'
    #
    # However, this could result in many rows that contain redundant data. After
    # having received the first row, we already have enough data to instantiate
    # the Author object. In all subsequent rows, only the data for the joined
    # 'books' table is useful; the joined 'authors' data is just redundant, and
    # processing this redundant data takes memory and CPU time. The problem
    # quickly becomes worse and worse as the level of eager loading increases
    # (i.e. if Active Record is to eager load the associations' associations as
    # well).
    #
    # The second strategy is to use multiple database queries, one for each
    # level of association. Since Rails 2.1, this is the default strategy. In
    # situations where a table join is necessary (e.g. when the +:conditions+
    # option references an association's column), it will fallback to the table
    # join strategy.
    #
    # See also ActiveRecord::Associations::ClassMethods, which explains eager
    # loading in a more high-level (application developer-friendly) manner.
    module ClassMethods
      protected

      # Eager loads the named associations for the given Active Record record(s).
      #
      # In this description, 'association name' shall refer to the name passed
      # to an association creation method. For example, a model that specifies
      # <tt>belongs_to :author</tt>, <tt>has_many :buyers</tt> has association
      # names +:author+ and +:buyers+.
      #
      # == Parameters
      # +records+ is an array of ActiveRecord::Base. This array needs not be flat,
      # i.e. +records+ itself may also contain arrays of records. In any case,
      # +preload_associations+ will preload the all associations records by
      # flattening +records+.
      #
      # +associations+ specifies one or more associations that you want to
      # preload. It may be:
      # - a Symbol or a String which specifies a single association name. For
      #   example, specifying +:books+ allows this method to preload all books
      #   for an Author.
      # - an Array which specifies multiple association names. This array
      #   is processed recursively. For example, specifying <tt>[:avatar, :books]</tt>
      #   allows this method to preload an author's avatar as well as all of his
      #   books.
      # - a Hash which specifies multiple association names, as well as
      #   association names for the to-be-preloaded association objects. For
      #   example, specifying <tt>{ :author => :avatar }</tt> will preload a
      #   book's author, as well as that author's avatar.
      #
      # +:associations+ has the same format as the +:include+ option for
      # <tt>ActiveRecord::Base.find</tt>. So +associations+ could look like this:
      #
      #   :books
      #   [ :books, :author ]
      #   { :author => :avatar }
      #   [ :books, { :author => :avatar } ]
      #
      # +preload_options+ contains options that will be passed to ActiveRecord::Base#find
      # (which is called under the hood for preloading records). But it is passed
      # only one level deep in the +associations+ argument, i.e. it's not passed
      # to the child associations when +associations+ is a Hash.
      def preload_associations(records, associations, preload_options={})
        records = Array.wrap(records).compact.uniq
        return if records.empty?
        case associations
        when Array then associations.each {|association| preload_associations(records, association, preload_options)}
        when Symbol, String then preload_one_association(records, associations.to_sym, preload_options)
        when Hash then
          associations.each do |parent, child|
            raise "parent must be an association name" unless parent.is_a?(String) || parent.is_a?(Symbol)
            preload_associations(records, parent, preload_options)
            reflection = reflections[parent]
            parents = records.sum { |record| Array.wrap(record.send(reflection.name)) }
            unless parents.empty?
              parents.first.class.preload_associations(parents, child)
            end
          end
        end
      end

      private

      # Preloads a specific named association for the given records. This is
      # called by +preload_associations+ as its base case.
      def preload_one_association(records, association, preload_options={})
        class_to_reflection = {}
        # Not all records have the same class, so group then preload
        # group on the reflection itself so that if various subclass share the same association then
        # we do not split them unnecessarily
        records.group_by { |record| class_to_reflection[record.class] ||= record.class.reflections[association]}.each do |reflection, _records|
          raise ConfigurationError, "Association named '#{ association }' was not found; perhaps you misspelled it?" unless reflection

          # 'reflection.macro' can return 'belongs_to', 'has_many', etc. Thus,
          # the following could call 'preload_belongs_to_association',
          # 'preload_has_many_association', etc.
          send("preload_#{reflection.macro}_association", _records, reflection, preload_options)
        end
      end

      def add_preloaded_records_to_collection(parent_records, reflection_name, associated_record)
        parent_records.each do |parent_record|
          association = parent_record.association(reflection_name)
          association.loaded!
          association.target.concat(Array.wrap(associated_record))
          association.set_inverse_instance(associated_record)
        end
      end

      def add_preloaded_record_to_collection(parent_records, reflection_name, associated_record)
        parent_records.each do |parent_record|
          parent_record.association(reflection_name).target = associated_record
        end
      end

      def set_association_collection_records(id_to_parent_map, reflection_name, associated_records, key)
        associated_records.each do |associated_record|
          parent_records = id_to_parent_map[associated_record[key].to_s]
          add_preloaded_records_to_collection(parent_records, reflection_name, associated_record)
        end
      end

      def set_association_single_records(id_to_record_map, reflection_name, associated_records, key)
        seen_keys = {}
        associated_records.each do |associated_record|
          seen_key = associated_record[key].to_s

          #this is a has_one or belongs_to: there should only be one record.
          #Unfortunately we can't (in portable way) ask the database for
          #'all records where foo_id in (x,y,z), but please
          # only one row per distinct foo_id' so this where we enforce that
          next if seen_keys.key? seen_key

          seen_keys[seen_key] = true
          mapped_records = id_to_record_map[seen_key]
          mapped_records.each do |mapped_record|
            association_proxy = mapped_record.association(reflection_name)
            association_proxy.target = associated_record
            association_proxy.send(:set_inverse_instance, associated_record)
          end
        end

        id_to_record_map.each do |id, records|
          next if seen_keys.include?(id)
          add_preloaded_record_to_collection(records, reflection_name, nil)
        end
      end

      # Given a collection of Active Record objects, constructs a Hash which maps
      # the objects' IDs to the relevant objects. Returns a 2-tuple
      # <tt>(id_to_record_map, ids)</tt> where +id_to_record_map+ is the Hash,
      # and +ids+ is an Array of record IDs.
      def construct_id_map(records, primary_key=nil)
        records.group_by do |record|
          primary_key ||= record.class.primary_key
          record[primary_key].to_s
        end
      end

      def preload_has_and_belongs_to_many_association(records, reflection, preload_options={})

        left = reflection.klass.arel_table

        id_to_record_map = construct_id_map(records)

        records.each { |record| record.association(reflection.name).loaded! }
        options = reflection.options

        right = Arel::Table.new(options[:join_table]).alias('t0')

        join_condition = left[reflection.klass.primary_key].eq(
          right[reflection.association_foreign_key])

        join = left.create_join(right, left.create_on(join_condition))
        select = [
          # FIXME: options[:select] is always nil in the tests.  Do we really
          # need it?
          options[:select] || left[Arel.star],
          right[reflection.foreign_key].as(
            Arel.sql('the_parent_record_id'))
        ]

        associated_records_proxy = reflection.klass.unscoped.
            includes(options[:include]).
            order(options[:order])

        associated_records_proxy.joins_values = [join]
        associated_records_proxy.select_values = select

        custom_conditions = append_conditions(reflection, preload_options)

        klass = associated_records_proxy.klass

        associated_records(id_to_record_map.keys) { |some_ids|
          method     = in_or_equal(some_ids)
          conditions = right.create_and(
            [right[reflection.foreign_key].send(*method)] +
            custom_conditions)

          relation = associated_records_proxy.where(conditions)
          klass.connection.select_all(relation.arel.to_sql, 'SQL', relation.bind_values)
        }.map! { |row|
          parent_records = id_to_record_map[row['the_parent_record_id'].to_s]
          associated_record = klass.instantiate row
          add_preloaded_records_to_collection(
            parent_records, reflection.name, associated_record)
          associated_record
        }
      end

      def preload_has_one_association(records, reflection, preload_options={})
        return if records.first.association(reflection.name).loaded?
        id_to_record_map = construct_id_map(records, reflection.options[:primary_key])
        options = reflection.options

        add_preloaded_record_to_collection(records, reflection.name, nil)

        if options[:through]
          through_records = preload_through_records(records, reflection, options[:through])

          unless through_records.empty?
            through_reflection = reflections[options[:through]]
            through_primary_key = through_reflection.foreign_key
            source = reflection.source_reflection.name
            through_records.first.class.preload_associations(through_records, source)
            if through_reflection.macro == :belongs_to
              id_to_record_map    = construct_id_map(records, through_primary_key)
              through_primary_key = through_reflection.klass.primary_key
            end

            through_records.each do |through_record|
              add_preloaded_record_to_collection(id_to_record_map[through_record[through_primary_key].to_s],
                                                 reflection.name, through_record.send(source))
            end
          end
        else
          set_association_single_records(id_to_record_map, reflection.name, find_associated_records(id_to_record_map.keys, reflection, preload_options), reflection.foreign_key)
        end
      end

      def preload_has_many_association(records, reflection, preload_options={})
        return if records.first.send(reflection.name).loaded?
        options = reflection.options

        foreign_key = reflection.through_reflection_foreign_key
        id_to_record_map = construct_id_map(records, foreign_key || reflection.options[:primary_key])
        records.each { |record| record.association(reflection.name).loaded! }

        if options[:through]
          through_records = preload_through_records(records, reflection, options[:through])
          unless through_records.empty?
            source = reflection.source_reflection.name
            through_records.first.class.preload_associations(through_records, source, options)
            through_records.each do |through_record|
              through_record_id = through_record[reflection.through_reflection_primary_key].to_s
              add_preloaded_records_to_collection(id_to_record_map[through_record_id], reflection.name, through_record.send(source))
            end
            records.each { |record| record.send(reflection.name).target.uniq! } if options[:uniq]
          end

        else
          set_association_collection_records(id_to_record_map, reflection.name, find_associated_records(id_to_record_map.keys, reflection, preload_options),
                                             reflection.foreign_key)
        end
      end

      def preload_through_records(records, reflection, through_association)
        if reflection.options[:source_type]
          interface = reflection.source_reflection.foreign_type
          preload_options = {:conditions => ["#{connection.quote_column_name interface} = ?", reflection.options[:source_type]]}

          records.compact!
          records.first.class.preload_associations(records, through_association, preload_options)

          # Dont cache the association - we would only be caching a subset
          records.map { |record|
            proxy = record.association(through_association)

            if proxy.respond_to?(:target)
              Array.wrap(proxy.target).tap { proxy.reset }
            else # this is a has_one :through reflection
              [proxy].compact
            end
          }.flatten(1)
        else
          options = {}
          options[:include] = reflection.options[:include] || reflection.options[:source] if reflection.options[:conditions]
          options[:order] = reflection.options[:order]
          options[:conditions] = reflection.options[:conditions]
          records.first.class.preload_associations(records, through_association, options)

          records.map { |record|
            Array.wrap(record.send(through_association))
          }.flatten(1)
        end
      end

      def preload_belongs_to_association(records, reflection, preload_options={})
        return if records.first.association(reflection.name).loaded?
        options = reflection.options

        klasses_and_ids = {}

        if options[:polymorphic]
          # Construct a mapping from klass to a list of ids to load and a mapping of those ids back
          # to their parent_records
          records.each do |record|
            if klass = record.send(reflection.foreign_type)
              klass_id = record.send(reflection.foreign_key)
              if klass_id
                id_map = klasses_and_ids[klass.constantize] ||= {}
                (id_map[klass_id.to_s] ||= []) << record
              end
            end
          end
        else
          id_map = records.group_by do |record|
            key = record.send(reflection.foreign_key)
            key && key.to_s
          end
          klasses_and_ids[reflection.klass] = id_map unless id_map.empty?
        end

        klasses_and_ids.each do |klass, _id_map|
          primary_key = (reflection.options[:primary_key] || klass.primary_key).to_s
          keys        = _id_map.keys.compact

          unless keys.empty?
            table       = klass.arel_table
            method      = in_or_equal(keys)
            conditions  = table[primary_key].send(*method)

            custom_conditions = append_conditions(reflection, preload_options)
            conditions = custom_conditions.inject(conditions) do |ast, cond|
              ast.and cond
            end

            associated_records = klass.unscoped.where(conditions).apply_finder_options(options.slice(:include, :select, :joins, :order)).to_a
          else
            associated_records = []
          end

          set_association_single_records(_id_map, reflection.name, associated_records, primary_key)
        end
      end

      def find_associated_records(ids, reflection, preload_options)
        options    = reflection.options
        table      = reflection.klass.arel_table

        conditions = []

        key = reflection.foreign_key

        if interface = reflection.options[:as]
          key = "#{interface}_id"
          conditions << table["#{interface}_type"].eq(base_class.sti_name)
        end

        conditions.concat append_conditions(reflection, preload_options)

        find_options = {
          :select => preload_options[:select] || options[:select] || table[Arel.star],
          :include => preload_options[:include] || options[:include],
          :joins => options[:joins],
          :group => preload_options[:group] || options[:group],
          :order => preload_options[:order] || options[:order]
        }

        associated_records(ids) do |some_ids|
          method = in_or_equal(some_ids)
          where = table.create_and(conditions + [table[key].send(*method)])

          reflection.klass.scoped.apply_finder_options(find_options.merge(:conditions => where)).to_a
        end
      end

      def process_conditions(conditions, klass = self)
        if conditions.respond_to?(:to_proc)
          conditions = instance_eval(&conditions)
        end

        klass.send(:sanitize_sql, conditions)
      end

      def append_conditions(reflection, preload_options)
        [
          ('(' + process_conditions(reflection.options[:conditions], reflection.klass) + ')' if reflection.options[:conditions]),
          ('(' + process_conditions(preload_options[:conditions]) + ')' if preload_options[:conditions]),
        ].compact.map { |x| Arel.sql x }
      end

      def in_or_equal(ids)
        ids.length == 1 ? ['eq', ids.first] : ['in', ids]
      end

      # Some databases impose a limit on the number of ids in a list (in Oracle its 1000)
      # Make several smaller queries if necessary or make one query if the adapter supports it
      def associated_records(ids)
        in_clause_length = connection.in_clause_length || ids.size
        records = []
        ids.each_slice(in_clause_length) do |some_ids|
          records.concat yield(some_ids)
        end
        records
      end
    end
  end
end