Commit d5803bb5 authored by Luke Plant's avatar Luke Plant
Browse files

More efficient IN clauses for prefetch_related queries by use of sets to eliminate duplicates 

This simply reduces the size of the IN clause in the SQL, which can be
significant in some cases.

git-svn-id: http://code.djangoproject.com/svn/django/trunk@16944 bcc190cf-cafb-0310-a4f2-bffc1f526a37
parent 095dbe88

django/contrib/contenttypes/generic.py

+3 −3
Original line number Diff line number Diff line
@@ -65,7 +65,7 @@ class GenericForeignKey(object): 
    def get_prefetch_query_set(self, instances):

        # For efficiency, group the instances by content type and then do one

        # query per model

        fk_dict = defaultdict(list)

        fk_dict = defaultdict(set)

        # We need one instance for each group in order to get the right db:

        instance_dict = {}

        ct_attname = self.model._meta.get_field(self.ct_field).get_attname()
@@ -75,7 +75,7 @@ class GenericForeignKey(object): 
            if ct_id is not None:

                fk_val = getattr(instance, self.fk_field)

                if fk_val is not None:

                    fk_dict[ct_id].append(fk_val)

                    fk_dict[ct_id].add(fk_val)

                    instance_dict[ct_id] = instance



        ret_val = []
@@ -325,7 +325,7 @@ def create_generic_related_manager(superclass): 
            query = {

                '%s__pk' % self.content_type_field_name: self.content_type.id,

                '%s__in' % self.object_id_field_name:

                    [obj._get_pk_val() for obj in instances]

                    set(obj._get_pk_val() for obj in instances)

                }

            qs = super(GenericRelatedObjectManager, self).get_query_set().using(db).filter(**query)

            return (qs,

django/db/models/fields/related.py

+4 −4
Original line number Diff line number Diff line
@@ -237,7 +237,7 @@ class SingleRelatedObjectDescriptor(object): 
        return self.related.model._base_manager.using(db)



    def get_prefetch_query_set(self, instances):

        vals = [instance._get_pk_val() for instance in instances]

        vals = set(instance._get_pk_val() for instance in instances)

        params = {'%s__pk__in' % self.related.field.name: vals}

        return (self.get_query_set(),

                attrgetter(self.related.field.attname),
@@ -316,7 +316,7 @@ class ReverseSingleRelatedObjectDescriptor(object): 
            return QuerySet(self.field.rel.to).using(db)



    def get_prefetch_query_set(self, instances):

        vals = [getattr(instance, self.field.attname) for instance in instances]

        vals = set(getattr(instance, self.field.attname) for instance in instances)

        other_field = self.field.rel.get_related_field()

        if other_field.rel:

            params = {'%s__pk__in' % self.field.rel.field_name: vals}
@@ -463,7 +463,7 @@ class ForeignRelatedObjectsDescriptor(object): 
            def get_prefetch_query_set(self, instances):

                db = self._db or router.db_for_read(self.model)

                query = {'%s__%s__in' % (rel_field.name, attname):

                             [getattr(obj, attname) for obj in instances]}

                             set(getattr(obj, attname) for obj in instances)}

                qs = super(RelatedManager, self).get_query_set().using(db).filter(**query)

                return (qs,

                        attrgetter(rel_field.get_attname()),
@@ -546,7 +546,7 @@ def create_many_related_manager(superclass, rel): 
            from django.db import connections

            db = self._db or router.db_for_read(self.model)

            query = {'%s__pk__in' % self.query_field_name:

                         [obj._get_pk_val() for obj in instances]}

                         set(obj._get_pk_val() for obj in instances)}

            qs = super(ManyRelatedManager, self).get_query_set().using(db)._next_is_sticky().filter(**query)



            # M2M: need to annotate the query in order to get the primary model