django1/docs/topics/db/queries.txt

==============
Making queries
==============

.. currentmodule:: django.db.models

Once you've created your :doc:`data models </topics/db/models>`, Django
automatically gives you a database-abstraction API that lets you create,
retrieve, update and delete objects. This document explains how to use this
API. Refer to the :doc:`data model reference </ref/models/index>` for full
details of all the various model lookup options.

Throughout this guide (and in the reference), we'll refer to the following
models, which comprise a Weblog application:

.. _queryset-model-example:

.. code-block:: python

    from django.db import models

    class Blog(models.Model):
        name = models.CharField(max_length=100)
        tagline = models.TextField()

        def __str__(self):
            return self.name

    class Author(models.Model):
        name = models.CharField(max_length=200)
        email = models.EmailField()

        def __str__(self):
            return self.name

    class Entry(models.Model):
        blog = models.ForeignKey(Blog, on_delete=models.CASCADE)
        headline = models.CharField(max_length=255)
        body_text = models.TextField()
        pub_date = models.DateField()
        mod_date = models.DateField()
        authors = models.ManyToManyField(Author)
        number_of_comments = models.IntegerField()
        number_of_pingbacks = models.IntegerField()
        rating = models.IntegerField()

        def __str__(self):
            return self.headline

Creating objects
================

To represent database-table data in Python objects, Django uses an intuitive
system: A model class represents a database table, and an instance of that
class represents a particular record in the database table.

To create an object, instantiate it using keyword arguments to the model class,
then call :meth:`~django.db.models.Model.save` to save it to the database.

Assuming models live in a file ``mysite/blog/models.py``, here's an example::

    >>> from blog.models import Blog
    >>> b = Blog(name='Beatles Blog', tagline='All the latest Beatles news.')
    >>> b.save()

This performs an ``INSERT`` SQL statement behind the scenes. Django doesn't hit
the database until you explicitly call :meth:`~django.db.models.Model.save`.

The :meth:`~django.db.models.Model.save` method has no return value.

.. seealso::

    :meth:`~django.db.models.Model.save` takes a number of advanced options not
    described here. See the documentation for
    :meth:`~django.db.models.Model.save` for complete details.

    To create and save an object in a single step, use the
    :meth:`~django.db.models.query.QuerySet.create()` method.

Saving changes to objects
=========================

To save changes to an object that's already in the database, use
:meth:`~django.db.models.Model.save`.

Given a ``Blog`` instance ``b5`` that has already been saved to the database,
this example changes its name and updates its record in the database::

    >>> b5.name = 'New name'
    >>> b5.save()

This performs an ``UPDATE`` SQL statement behind the scenes. Django doesn't hit
the database until you explicitly call :meth:`~django.db.models.Model.save`.

Saving ``ForeignKey`` and ``ManyToManyField`` fields
----------------------------------------------------

Updating a :class:`~django.db.models.ForeignKey` field works exactly the same
way as saving a normal field -- assign an object of the right type to the field
in question. This example updates the ``blog`` attribute of an ``Entry``
instance ``entry``, assuming appropriate instances of ``Entry`` and ``Blog``
are already saved to the database (so we can retrieve them below)::

    >>> from blog.models import Blog, Entry
    >>> entry = Entry.objects.get(pk=1)
    >>> cheese_blog = Blog.objects.get(name="Cheddar Talk")
    >>> entry.blog = cheese_blog
    >>> entry.save()

Updating a :class:`~django.db.models.ManyToManyField` works a little
differently -- use the
:meth:`~django.db.models.fields.related.RelatedManager.add` method on the field
to add a record to the relation. This example adds the ``Author`` instance
``joe`` to the ``entry`` object::

    >>> from blog.models import Author
    >>> joe = Author.objects.create(name="Joe")
    >>> entry.authors.add(joe)

To add multiple records to a :class:`~django.db.models.ManyToManyField` in one
go, include multiple arguments in the call to
:meth:`~django.db.models.fields.related.RelatedManager.add`, like this::

    >>> john = Author.objects.create(name="John")
    >>> paul = Author.objects.create(name="Paul")
    >>> george = Author.objects.create(name="George")
    >>> ringo = Author.objects.create(name="Ringo")
    >>> entry.authors.add(john, paul, george, ringo)

Django will complain if you try to assign or add an object of the wrong type.

.. _retrieving-objects:

Retrieving objects
==================

To retrieve objects from your database, construct a
:class:`~django.db.models.query.QuerySet` via a
:class:`~django.db.models.Manager` on your model class.

A :class:`~django.db.models.query.QuerySet` represents a collection of objects
from your database. It can have zero, one or many *filters*. Filters narrow
down the query results based on the given parameters. In SQL terms, a
:class:`~django.db.models.query.QuerySet` equates to a ``SELECT`` statement,
and a filter is a limiting clause such as ``WHERE`` or ``LIMIT``.

You get a :class:`~django.db.models.query.QuerySet` by using your model's
:class:`~django.db.models.Manager`. Each model has at least one
:class:`~django.db.models.Manager`, and it's called
:attr:`~django.db.models.Model.objects` by default. Access it directly via the
model class, like so::

    >>> Blog.objects
    <django.db.models.manager.Manager object at ...>
    >>> b = Blog(name='Foo', tagline='Bar')
    >>> b.objects
    Traceback:
        ...
    AttributeError: "Manager isn't accessible via Blog instances."

.. note::

    ``Managers`` are accessible only via model classes, rather than from model
    instances, to enforce a separation between "table-level" operations and
    "record-level" operations.

The :class:`~django.db.models.Manager` is the main source of ``QuerySets`` for
a model. For example, ``Blog.objects.all()`` returns a
:class:`~django.db.models.query.QuerySet` that contains all ``Blog`` objects in
the database.

Retrieving all objects
----------------------

The simplest way to retrieve objects from a table is to get all of them. To do
this, use the :meth:`~django.db.models.query.QuerySet.all` method on a
:class:`~django.db.models.Manager`::

    >>> all_entries = Entry.objects.all()

The :meth:`~django.db.models.query.QuerySet.all` method returns a
:class:`~django.db.models.query.QuerySet` of all the objects in the database.

Retrieving specific objects with filters
----------------------------------------

The :class:`~django.db.models.query.QuerySet` returned by
:meth:`~django.db.models.query.QuerySet.all` describes all objects in the
database table. Usually, though, you'll need to select only a subset of the
complete set of objects.

To create such a subset, you refine the initial
:class:`~django.db.models.query.QuerySet`, adding filter conditions. The two
most common ways to refine a :class:`~django.db.models.query.QuerySet` are:

``filter(**kwargs)``
    Returns a new :class:`~django.db.models.query.QuerySet` containing objects
    that match the given lookup parameters.

``exclude(**kwargs)``
    Returns a new :class:`~django.db.models.query.QuerySet` containing objects
    that do *not* match the given lookup parameters.

The lookup parameters (``**kwargs`` in the above function definitions) should
be in the format described in `Field lookups`_ below.

For example, to get a :class:`~django.db.models.query.QuerySet` of blog entries
from the year 2006, use :meth:`~django.db.models.query.QuerySet.filter` like
so::

    Entry.objects.filter(pub_date__year=2006)

With the default manager class, it is the same as::

    Entry.objects.all().filter(pub_date__year=2006)

.. _chaining-filters:

Chaining filters
~~~~~~~~~~~~~~~~

The result of refining a :class:`~django.db.models.query.QuerySet` is itself a
:class:`~django.db.models.query.QuerySet`, so it's possible to chain
refinements together. For example::

    >>> Entry.objects.filter(
    ...     headline__startswith='What'
    ... ).exclude(
    ...     pub_date__gte=datetime.date.today()
    ... ).filter(
    ...     pub_date__gte=datetime.date(2005, 1, 30)
    ... )

This takes the initial :class:`~django.db.models.query.QuerySet` of all entries
in the database, adds a filter, then an exclusion, then another filter. The
final result is a :class:`~django.db.models.query.QuerySet` containing all
entries with a headline that starts with "What", that were published between
January 30, 2005, and the current day.

.. _filtered-querysets-are-unique:

Filtered ``QuerySet``\s are unique
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Each time you refine a :class:`~django.db.models.query.QuerySet`, you get a
brand-new :class:`~django.db.models.query.QuerySet` that is in no way bound to
the previous :class:`~django.db.models.query.QuerySet`. Each refinement creates
a separate and distinct :class:`~django.db.models.query.QuerySet` that can be
stored, used and reused.

Example::

    >>> q1 = Entry.objects.filter(headline__startswith="What")
    >>> q2 = q1.exclude(pub_date__gte=datetime.date.today())
    >>> q3 = q1.filter(pub_date__gte=datetime.date.today())

These three ``QuerySets`` are separate. The first is a base
:class:`~django.db.models.query.QuerySet` containing all entries that contain a
headline starting with "What". The second is a subset of the first, with an
additional criteria that excludes records whose ``pub_date`` is today or in the
future. The third is a subset of the first, with an additional criteria that
selects only the records whose ``pub_date`` is today or in the future. The
initial :class:`~django.db.models.query.QuerySet` (``q1``) is unaffected by the
refinement process.

.. _querysets-are-lazy:

``QuerySet``\s are lazy
~~~~~~~~~~~~~~~~~~~~~~~

``QuerySets`` are lazy -- the act of creating a
:class:`~django.db.models.query.QuerySet` doesn't involve any database
activity. You can stack filters together all day long, and Django won't
actually run the query until the :class:`~django.db.models.query.QuerySet` is
*evaluated*. Take a look at this example::

    >>> q = Entry.objects.filter(headline__startswith="What")
    >>> q = q.filter(pub_date__lte=datetime.date.today())
    >>> q = q.exclude(body_text__icontains="food")
    >>> print(q)

Though this looks like three database hits, in fact it hits the database only
once, at the last line (``print(q)``). In general, the results of a
:class:`~django.db.models.query.QuerySet` aren't fetched from the database
until you "ask" for them. When you do, the
:class:`~django.db.models.query.QuerySet` is *evaluated* by accessing the
database. For more details on exactly when evaluation takes place, see
:ref:`when-querysets-are-evaluated`.

.. _retrieving-single-object-with-get:

Retrieving a single object with ``get()``
-----------------------------------------

:meth:`~django.db.models.query.QuerySet.filter` will always give you a
:class:`~django.db.models.query.QuerySet`, even if only a single object matches
the query - in this case, it will be a
:class:`~django.db.models.query.QuerySet` containing a single element.

If you know there is only one object that matches your query, you can use the
:meth:`~django.db.models.query.QuerySet.get` method on a
:class:`~django.db.models.Manager` which returns the object directly::

    >>> one_entry = Entry.objects.get(pk=1)

You can use any query expression with
:meth:`~django.db.models.query.QuerySet.get`, just like with
:meth:`~django.db.models.query.QuerySet.filter` - again, see `Field lookups`_
below.

Note that there is a difference between using
:meth:`~django.db.models.query.QuerySet.get`, and using
:meth:`~django.db.models.query.QuerySet.filter` with a slice of ``[0]``. If
there are no results that match the query,
:meth:`~django.db.models.query.QuerySet.get` will raise a ``DoesNotExist``
exception. This exception is an attribute of the model class that the query is
being performed on - so in the code above, if there is no ``Entry`` object with
a primary key of 1, Django will raise ``Entry.DoesNotExist``.

Similarly, Django will complain if more than one item matches the
:meth:`~django.db.models.query.QuerySet.get` query. In this case, it will raise
:exc:`~django.core.exceptions.MultipleObjectsReturned`, which again is an
attribute of the model class itself.


Other ``QuerySet`` methods
--------------------------

Most of the time you'll use :meth:`~django.db.models.query.QuerySet.all`,
:meth:`~django.db.models.query.QuerySet.get`,
:meth:`~django.db.models.query.QuerySet.filter` and
:meth:`~django.db.models.query.QuerySet.exclude` when you need to look up
objects from the database. However, that's far from all there is; see the
:ref:`QuerySet API Reference <queryset-api>` for a complete list of all the
various :class:`~django.db.models.query.QuerySet` methods.

.. _limiting-querysets:

Limiting ``QuerySet``\s
-----------------------

Use a subset of Python's array-slicing syntax to limit your
:class:`~django.db.models.query.QuerySet` to a certain number of results. This
is the equivalent of SQL's ``LIMIT`` and ``OFFSET`` clauses.

For example, this returns the first 5 objects (``LIMIT 5``)::

    >>> Entry.objects.all()[:5]

This returns the sixth through tenth objects (``OFFSET 5 LIMIT 5``)::

    >>> Entry.objects.all()[5:10]

Negative indexing (i.e. ``Entry.objects.all()[-1]``) is not supported.

Generally, slicing a :class:`~django.db.models.query.QuerySet` returns a new
:class:`~django.db.models.query.QuerySet` -- it doesn't evaluate the query. An
exception is if you use the "step" parameter of Python slice syntax. For
example, this would actually execute the query in order to return a list of
every *second* object of the first 10::

    >>> Entry.objects.all()[:10:2]

Further filtering or ordering of a sliced queryset is prohibited due to the
ambiguous nature of how that might work.

To retrieve a *single* object rather than a list
(e.g. ``SELECT foo FROM bar LIMIT 1``), use an index instead of a slice. For
example, this returns the first ``Entry`` in the database, after ordering
entries alphabetically by headline::

    >>> Entry.objects.order_by('headline')[0]

This is roughly equivalent to::

    >>> Entry.objects.order_by('headline')[0:1].get()

Note, however, that the first of these will raise ``IndexError`` while the
second will raise ``DoesNotExist`` if no objects match the given criteria. See
:meth:`~django.db.models.query.QuerySet.get` for more details.

.. _field-lookups-intro:

Field lookups
-------------

Field lookups are how you specify the meat of an SQL ``WHERE`` clause. They're
specified as keyword arguments to the :class:`~django.db.models.query.QuerySet`
methods :meth:`~django.db.models.query.QuerySet.filter`,
:meth:`~django.db.models.query.QuerySet.exclude` and
:meth:`~django.db.models.query.QuerySet.get`.

Basic lookups keyword arguments take the form ``field__lookuptype=value``.
(That's a double-underscore). For example::

    >>> Entry.objects.filter(pub_date__lte='2006-01-01')

translates (roughly) into the following SQL:

.. code-block:: sql

    SELECT * FROM blog_entry WHERE pub_date <= '2006-01-01';

.. admonition:: How this is possible

   Python has the ability to define functions that accept arbitrary name-value
   arguments whose names and values are evaluated at runtime. For more
   information, see :ref:`tut-keywordargs` in the official Python tutorial.

The field specified in a lookup has to be the name of a model field. There's
one exception though, in case of a :class:`~django.db.models.ForeignKey` you
can specify the field name suffixed with ``_id``. In this case, the value
parameter is expected to contain the raw value of the foreign model's primary
key. For example:

    >>> Entry.objects.filter(blog_id=4)

If you pass an invalid keyword argument, a lookup function will raise
``TypeError``.

The database API supports about two dozen lookup types; a complete reference
can be found in the :ref:`field lookup reference <field-lookups>`. To give you
a taste of what's available, here's some of the more common lookups you'll
probably use:

:lookup:`exact`
    An "exact" match. For example::

        >>> Entry.objects.get(headline__exact="Cat bites dog")

    Would generate SQL along these lines:

    .. code-block:: sql

        SELECT ... WHERE headline = 'Cat bites dog';

    If you don't provide a lookup type -- that is, if your keyword argument
    doesn't contain a double underscore -- the lookup type is assumed to be
    ``exact``.

    For example, the following two statements are equivalent::

        >>> Blog.objects.get(id__exact=14)  # Explicit form
        >>> Blog.objects.get(id=14)         # __exact is implied

    This is for convenience, because ``exact`` lookups are the common case.

:lookup:`iexact`
    A case-insensitive match. So, the query::

        >>> Blog.objects.get(name__iexact="beatles blog")

    Would match a ``Blog`` titled ``"Beatles Blog"``, ``"beatles blog"``, or
    even ``"BeAtlES blOG"``.

:lookup:`contains`
    Case-sensitive containment test. For example::

        Entry.objects.get(headline__contains='Lennon')

    Roughly translates to this SQL:

    .. code-block:: sql

        SELECT ... WHERE headline LIKE '%Lennon%';

    Note this will match the headline ``'Today Lennon honored'`` but not
    ``'today lennon honored'``.

    There's also a case-insensitive version, :lookup:`icontains`.

:lookup:`startswith`, :lookup:`endswith`
    Starts-with and ends-with search, respectively. There are also
    case-insensitive versions called :lookup:`istartswith` and
    :lookup:`iendswith`.

Again, this only scratches the surface. A complete reference can be found in the
:ref:`field lookup reference <field-lookups>`.

.. _lookups-that-span-relationships:

Lookups that span relationships
-------------------------------

Django offers a powerful and intuitive way to "follow" relationships in
lookups, taking care of the SQL ``JOIN``\s for you automatically, behind the
scenes. To span a relationship, use the field name of related fields
across models, separated by double underscores, until you get to the field you
want.

This example retrieves all ``Entry`` objects with a ``Blog`` whose ``name``
is ``'Beatles Blog'``::

    >>> Entry.objects.filter(blog__name='Beatles Blog')

This spanning can be as deep as you'd like.

It works backwards, too. Whilst it :attr:`can be customized
<.ForeignKey.related_query_name>`, by default you refer to a "reverse"
relationship in a lookup using the lowercase name of the model.

This example retrieves all ``Blog`` objects which have at least one ``Entry``
whose ``headline`` contains ``'Lennon'``::

    >>> Blog.objects.filter(entry__headline__contains='Lennon')

If you are filtering across multiple relationships and one of the intermediate
models doesn't have a value that meets the filter condition, Django will treat
it as if there is an empty (all values are ``NULL``), but valid, object there.
All this means is that no error will be raised. For example, in this filter::

    Blog.objects.filter(entry__authors__name='Lennon')

(if there was a related ``Author`` model), if there was no ``author``
associated with an entry, it would be treated as if there was also no ``name``
attached, rather than raising an error because of the missing ``author``.
Usually this is exactly what you want to have happen. The only case where it
might be confusing is if you are using :lookup:`isnull`. Thus::

    Blog.objects.filter(entry__authors__name__isnull=True)

will return ``Blog`` objects that have an empty ``name`` on the ``author`` and
also those which have an empty ``author`` on the ``entry``. If you don't want
those latter objects, you could write::

    Blog.objects.filter(entry__authors__isnull=False, entry__authors__name__isnull=True)

Spanning multi-valued relationships
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

When you are filtering an object based on a
:class:`~django.db.models.ManyToManyField` or a reverse
:class:`~django.db.models.ForeignKey`, there are two different sorts of filter
you may be interested in. Consider the ``Blog``/``Entry`` relationship
(``Blog`` to ``Entry`` is a one-to-many relation). We might be interested in
finding blogs that have an entry which has both *"Lennon"* in the headline and
was published in 2008. Or we might want to find blogs that have an entry with
*"Lennon"* in the headline as well as an entry that was published
in 2008. Since there are multiple entries associated with a single ``Blog``,
both of these queries are possible and make sense in some situations.

The same type of situation arises with a
:class:`~django.db.models.ManyToManyField`. For example, if an ``Entry`` has a
:class:`~django.db.models.ManyToManyField` called ``tags``, we might want to
find entries linked to tags called *"music"* and *"bands"* or we might want an
entry that contains a tag with a name of *"music"* and a status of *"public"*.

To handle both of these situations, Django has a consistent way of processing
:meth:`~django.db.models.query.QuerySet.filter` calls. Everything inside a
single :meth:`~django.db.models.query.QuerySet.filter` call is applied
simultaneously to filter out items matching all those requirements. Successive
:meth:`~django.db.models.query.QuerySet.filter` calls further restrict the set
of objects, but for multi-valued relations, they apply to any object linked to
the primary model, not necessarily those objects that were selected by an
earlier :meth:`~django.db.models.query.QuerySet.filter` call.

That may sound a bit confusing, so hopefully an example will clarify. To
select all blogs that contain entries with both *"Lennon"* in the headline
and that were published in 2008 (the same entry satisfying both conditions),
we would write::

    Blog.objects.filter(entry__headline__contains='Lennon', entry__pub_date__year=2008)

To select all blogs that contain an entry with *"Lennon"* in the headline
**as well as** an entry that was published in 2008, we would write::

    Blog.objects.filter(entry__headline__contains='Lennon').filter(entry__pub_date__year=2008)

Suppose there is only one blog that had both entries containing *"Lennon"* and
entries from 2008, but that none of the entries from 2008 contained *"Lennon"*.
The first query would not return any blogs, but the second query would return
that one blog.

In the second example, the first filter restricts the queryset to all those
blogs linked to entries with *"Lennon"* in the headline. The second filter
restricts the set of blogs *further* to those that are also linked to entries
that were published in 2008. The entries selected by the second filter may or
may not be the same as the entries in the first filter. We are filtering the
``Blog`` items with each filter statement, not the ``Entry`` items.

.. note::

    The behavior of :meth:`~django.db.models.query.QuerySet.filter` for queries
    that span multi-value relationships, as described above, is not implemented
    equivalently for :meth:`~django.db.models.query.QuerySet.exclude`. Instead,
    the conditions in a single :meth:`~django.db.models.query.QuerySet.exclude`
    call will not necessarily refer to the same item.

    For example, the following query would exclude blogs that contain *both*
    entries with *"Lennon"* in the headline *and* entries published in 2008::

        Blog.objects.exclude(
            entry__headline__contains='Lennon',
            entry__pub_date__year=2008,
        )

    However, unlike the behavior when using
    :meth:`~django.db.models.query.QuerySet.filter`, this will not limit blogs
    based on entries that satisfy both conditions. In order to do that, i.e.
    to select all blogs that do not contain entries published with *"Lennon"*
    that were published in 2008, you need to make two queries::

        Blog.objects.exclude(
            entry__in=Entry.objects.filter(
                headline__contains='Lennon',
                pub_date__year=2008,
            ),
        )

.. _using-f-expressions-in-filters:

Filters can reference fields on the model
-----------------------------------------

In the examples given so far, we have constructed filters that compare
the value of a model field with a constant. But what if you want to compare
the value of a model field with another field on the same model?

Django provides :class:`F expressions <django.db.models.F>` to allow such
comparisons. Instances of ``F()`` act as a reference to a model field within a
query. These references can then be used in query filters to compare the values
of two different fields on the same model instance.

For example, to find a list of all blog entries that have had more comments
than pingbacks, we construct an ``F()`` object to reference the pingback count,
and use that ``F()`` object in the query::

    >>> from django.db.models import F
    >>> Entry.objects.filter(number_of_comments__gt=F('number_of_pingbacks'))

Django supports the use of addition, subtraction, multiplication,
division, modulo, and power arithmetic with ``F()`` objects, both with constants
and with other ``F()`` objects. To find all the blog entries with more than
*twice* as many comments as pingbacks, we modify the query::

    >>> Entry.objects.filter(number_of_comments__gt=F('number_of_pingbacks') * 2)

To find all the entries where the rating of the entry is less than the
sum of the pingback count and comment count, we would issue the
query::

    >>> Entry.objects.filter(rating__lt=F('number_of_comments') + F('number_of_pingbacks'))

You can also use the double underscore notation to span relationships in
an ``F()`` object. An ``F()`` object with a double underscore will introduce
any joins needed to access the related object. For example, to retrieve all
the entries where the author's name is the same as the blog name, we could
issue the query::

    >>> Entry.objects.filter(authors__name=F('blog__name'))

For date and date/time fields, you can add or subtract a
:class:`~datetime.timedelta` object. The following would return all entries
that were modified more than 3 days after they were published::

    >>> from datetime import timedelta
    >>> Entry.objects.filter(mod_date__gt=F('pub_date') + timedelta(days=3))

The ``F()`` objects support bitwise operations by ``.bitand()``, ``.bitor()``,
``.bitxor()``, ``.bitrightshift()``, and ``.bitleftshift()``. For example::

    >>> F('somefield').bitand(16)

.. admonition:: Oracle

    Oracle doesn't support bitwise XOR operation.

.. versionchanged:: 3.1

    Support for ``.bitxor()`` was added.

The ``pk`` lookup shortcut
--------------------------

For convenience, Django provides a ``pk`` lookup shortcut, which stands for
"primary key".

In the example ``Blog`` model, the primary key is the ``id`` field, so these
three statements are equivalent::

    >>> Blog.objects.get(id__exact=14) # Explicit form
    >>> Blog.objects.get(id=14) # __exact is implied
    >>> Blog.objects.get(pk=14) # pk implies id__exact

The use of ``pk`` isn't limited to ``__exact`` queries -- any query term
can be combined with ``pk`` to perform a query on the primary key of a model::

    # Get blogs entries with id 1, 4 and 7
    >>> Blog.objects.filter(pk__in=[1,4,7])

    # Get all blog entries with id > 14
    >>> Blog.objects.filter(pk__gt=14)

``pk`` lookups also work across joins. For example, these three statements are
equivalent::

    >>> Entry.objects.filter(blog__id__exact=3) # Explicit form
    >>> Entry.objects.filter(blog__id=3)        # __exact is implied
    >>> Entry.objects.filter(blog__pk=3)        # __pk implies __id__exact

Escaping percent signs and underscores in ``LIKE`` statements
-------------------------------------------------------------

The field lookups that equate to ``LIKE`` SQL statements (``iexact``,
``contains``, ``icontains``, ``startswith``, ``istartswith``, ``endswith``
and ``iendswith``) will automatically escape the two special characters used in
``LIKE`` statements -- the percent sign and the underscore. (In a ``LIKE``
statement, the percent sign signifies a multiple-character wildcard and the
underscore signifies a single-character wildcard.)

This means things should work intuitively, so the abstraction doesn't leak.
For example, to retrieve all the entries that contain a percent sign, use the
percent sign as any other character::

    >>> Entry.objects.filter(headline__contains='%')

Django takes care of the quoting for you; the resulting SQL will look something
like this:

.. code-block:: sql

    SELECT ... WHERE headline LIKE '%\%%';

Same goes for underscores. Both percentage signs and underscores are handled
for you transparently.

.. _caching-and-querysets:

Caching and ``QuerySet``\s
--------------------------

Each :class:`~django.db.models.query.QuerySet` contains a cache to minimize
database access. Understanding how it works will allow you to write the most
efficient code.

In a newly created :class:`~django.db.models.query.QuerySet`, the cache is
empty. The first time a :class:`~django.db.models.query.QuerySet` is evaluated
-- and, hence, a database query happens -- Django saves the query results in
the :class:`~django.db.models.query.QuerySet`’s cache and returns the results
that have been explicitly requested (e.g., the next element, if the
:class:`~django.db.models.query.QuerySet` is being iterated over). Subsequent
evaluations of the :class:`~django.db.models.query.QuerySet` reuse the cached
results.

Keep this caching behavior in mind, because it may bite you if you don't use
your :class:`~django.db.models.query.QuerySet`\s correctly. For example, the
following will create two :class:`~django.db.models.query.QuerySet`\s, evaluate
them, and throw them away::

    >>> print([e.headline for e in Entry.objects.all()])
    >>> print([e.pub_date for e in Entry.objects.all()])

That means the same database query will be executed twice, effectively doubling
your database load. Also, there's a possibility the two lists may not include
the same database records, because an ``Entry`` may have been added or deleted
in the split second between the two requests.

To avoid this problem, save the :class:`~django.db.models.query.QuerySet` and
reuse it::

    >>> queryset = Entry.objects.all()
    >>> print([p.headline for p in queryset]) # Evaluate the query set.
    >>> print([p.pub_date for p in queryset]) # Re-use the cache from the evaluation.

When ``QuerySet``\s are not cached
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Querysets do not always cache their results.  When evaluating only *part* of
the queryset, the cache is checked, but if it is not populated then the items
returned by the subsequent query are not cached. Specifically, this means that
:ref:`limiting the queryset <limiting-querysets>` using an array slice or an
index will not populate the cache.

For example, repeatedly getting a certain index in a queryset object will query
the database each time::

    >>> queryset = Entry.objects.all()
    >>> print(queryset[5]) # Queries the database
    >>> print(queryset[5]) # Queries the database again

However, if the entire queryset has already been evaluated, the cache will be
checked instead::

    >>> queryset = Entry.objects.all()
    >>> [entry for entry in queryset] # Queries the database
    >>> print(queryset[5]) # Uses cache
    >>> print(queryset[5]) # Uses cache

Here are some examples of other actions that will result in the entire queryset
being evaluated and therefore populate the cache::

    >>> [entry for entry in queryset]
    >>> bool(queryset)
    >>> entry in queryset
    >>> list(queryset)

.. note::

    Simply printing the queryset will not populate the cache. This is because
    the call to ``__repr__()`` only returns a slice of the entire queryset.

.. _querying-jsonfield:

Querying ``JSONField``
======================

Lookups implementation is different in :class:`~django.db.models.JSONField`,
mainly due to the existence of key transformations. To demonstrate, we will use
the following example model::

    from django.db import models

    class Dog(models.Model):
        name = models.CharField(max_length=200)
        data = models.JSONField(null=True)

        def __str__(self):
            return self.name

Storing and querying for ``None``
---------------------------------

As with other fields, storing ``None`` as the field's value will store it as
SQL ``NULL``. While not recommended, it is possible to store JSON scalar
``null`` instead of SQL ``NULL`` by using :class:`Value('null')
<django.db.models.Value>`.

Whichever of the values is stored, when retrieved from the database, the Python
representation of the JSON scalar ``null`` is the same as SQL ``NULL``, i.e.
``None``. Therefore, it can be hard to distinguish between them.

This only applies to ``None`` as the top-level value of the field. If ``None``
is inside a :py:class:`list` or :py:class:`dict`, it will always be interpreted
as JSON ``null``.

When querying, ``None`` value will always be interpreted as JSON ``null``. To
query for SQL ``NULL``, use :lookup:`isnull`::

    >>> Dog.objects.create(name='Max', data=None)  # SQL NULL.
    <Dog: Max>
    >>> Dog.objects.create(name='Archie', data=Value('null'))  # JSON null.
    <Dog: Archie>
    >>> Dog.objects.filter(data=None)
    <QuerySet [<Dog: Archie>]>
    >>> Dog.objects.filter(data=Value('null'))
    <QuerySet [<Dog: Archie>]>
    >>> Dog.objects.filter(data__isnull=True)
    <QuerySet [<Dog: Max>]>
    >>> Dog.objects.filter(data__isnull=False)
    <QuerySet [<Dog: Archie>]>

Unless you are sure you wish to work with SQL ``NULL`` values, consider setting
``null=False`` and providing a suitable default for empty values, such as
``default=dict``.

.. note::

    Storing JSON scalar ``null`` does not violate :attr:`null=False
    <django.db.models.Field.null>`.

.. fieldlookup:: jsonfield.key

Key, index, and path transforms
-------------------------------

To query based on a given dictionary key, use that key as the lookup name::

    >>> Dog.objects.create(name='Rufus', data={
    ...     'breed': 'labrador',
    ...     'owner': {
    ...         'name': 'Bob',
    ...         'other_pets': [{
    ...             'name': 'Fishy',
    ...         }],
    ...     },
    ... })
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'breed': 'collie', 'owner': None})
    <Dog: Meg>
    >>> Dog.objects.filter(data__breed='collie')
    <QuerySet [<Dog: Meg>]>

Multiple keys can be chained together to form a path lookup::

    >>> Dog.objects.filter(data__owner__name='Bob')
    <QuerySet [<Dog: Rufus>]>

If the key is an integer, it will be interpreted as an index transform in an
array::

    >>> Dog.objects.filter(data__owner__other_pets__0__name='Fishy')
    <QuerySet [<Dog: Rufus>]>

If the key you wish to query by clashes with the name of another lookup, use
the :lookup:`contains <jsonfield.contains>` lookup instead.

To query for missing keys, use the ``isnull`` lookup::

    >>> Dog.objects.create(name='Shep', data={'breed': 'collie'})
    <Dog: Shep>
    >>> Dog.objects.filter(data__owner__isnull=True)
    <QuerySet [<Dog: Shep>]>

.. note::

    The lookup examples given above implicitly use the :lookup:`exact` lookup.
    Key, index, and path transforms can also be chained with:
    :lookup:`contains`, :lookup:`icontains`, :lookup:`endswith`,
    :lookup:`iendswith`, :lookup:`iexact`, :lookup:`regex`, :lookup:`iregex`,
    :lookup:`startswith`, :lookup:`istartswith`, :lookup:`lt`, :lookup:`lte`,
    :lookup:`gt`, and :lookup:`gte` lookups.

.. warning::

    Since any string could be a key in a JSON object, any lookup other than
    those listed below will be interpreted as a key lookup. No errors are
    raised. Be extra careful for typing mistakes, and always check your queries
    work as you intend.

.. admonition:: MariaDB and Oracle users

    Using :meth:`~django.db.models.query.QuerySet.order_by` on key, index, or
    path transforms will sort the objects using the string representation of
    the values. This is because MariaDB and Oracle Database do not provide a
    function that converts JSON values into their equivalent SQL values.

.. admonition:: Oracle users

    On Oracle Database, using ``None`` as the lookup value in an
    :meth:`~django.db.models.query.QuerySet.exclude` query will return objects
    that do not have ``null`` as the value at the given path, including objects
    that do not have the path. On other database backends, the query will
    return objects that have the path and the value is not ``null``.

.. admonition:: PostgreSQL users

    On PostgreSQL, if only one key or index is used, the SQL operator ``->`` is
    used. If multiple operators are used then the ``#>`` operator is used.

Containment and key operations
------------------------------

.. fieldlookup:: jsonfield.contains

``contains``
~~~~~~~~~~~~

The :lookup:`contains` lookup is overridden on ``JSONField``. The returned
objects are those where the given ``dict`` of key-value pairs are all
contained in the top-level of the field. For example::

    >>> Dog.objects.create(name='Rufus', data={'breed': 'labrador', 'owner': 'Bob'})
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'breed': 'collie', 'owner': 'Bob'})
    <Dog: Meg>
    >>> Dog.objects.create(name='Fred', data={})
    <Dog: Fred>
    >>> Dog.objects.filter(data__contains={'owner': 'Bob'})
    <QuerySet [<Dog: Rufus>, <Dog: Meg>]>
    >>> Dog.objects.filter(data__contains={'breed': 'collie'})
    <QuerySet [<Dog: Meg>]>

.. fieldlookup:: jsonfield.contained_by

``contained_by``
~~~~~~~~~~~~~~~~

This is the inverse of the :lookup:`contains <jsonfield.contains>` lookup - the
objects returned will be those where the key-value pairs on the object are a
subset of those in the value passed. For example::

    >>> Dog.objects.create(name='Rufus', data={'breed': 'labrador', 'owner': 'Bob'})
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'breed': 'collie', 'owner': 'Bob'})
    <Dog: Meg>
    >>> Dog.objects.create(name='Fred', data={})
    <Dog: Fred>
    >>> Dog.objects.filter(data__contained_by={'breed': 'collie', 'owner': 'Bob'})
    <QuerySet [<Dog: Meg>, <Dog: Fred>]>
    >>> Dog.objects.filter(data__contained_by={'breed': 'collie'})
    <QuerySet [<Dog: Fred>]>

.. admonition:: Oracle

    ``contained_by`` is not supported on Oracle.

.. fieldlookup:: jsonfield.has_key

``has_key``
~~~~~~~~~~~

Returns objects where the given key is in the top-level of the data. For
example::

    >>> Dog.objects.create(name='Rufus', data={'breed': 'labrador'})
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'breed': 'collie', 'owner': 'Bob'})
    <Dog: Meg>
    >>> Dog.objects.filter(data__has_key='owner')
    <QuerySet [<Dog: Meg>]>

.. fieldlookup:: jsonfield.has_any_keys

``has_keys``
~~~~~~~~~~~~

Returns objects where all of the given keys are in the top-level of the data.
For example::

    >>> Dog.objects.create(name='Rufus', data={'breed': 'labrador'})
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'breed': 'collie', 'owner': 'Bob'})
    <Dog: Meg>
    >>> Dog.objects.filter(data__has_keys=['breed', 'owner'])
    <QuerySet [<Dog: Meg>]>

.. fieldlookup:: jsonfield.has_keys

``has_any_keys``
~~~~~~~~~~~~~~~~

Returns objects where any of the given keys are in the top-level of the data.
For example::

    >>> Dog.objects.create(name='Rufus', data={'breed': 'labrador'})
    <Dog: Rufus>
    >>> Dog.objects.create(name='Meg', data={'owner': 'Bob'})
    <Dog: Meg>
    >>> Dog.objects.filter(data__has_any_keys=['owner', 'breed'])
    <QuerySet [<Dog: Rufus>, <Dog: Meg>]>

.. _complex-lookups-with-q:

Complex lookups with ``Q`` objects
==================================

Keyword argument queries -- in :meth:`~django.db.models.query.QuerySet.filter`,
etc. -- are "AND"ed together. If you need to execute more complex queries (for
example, queries with ``OR`` statements), you can use :class:`Q objects <django.db.models.Q>`.

A :class:`Q object <django.db.models.Q>` (``django.db.models.Q``) is an object
used to encapsulate a collection of keyword arguments. These keyword arguments
are specified as in "Field lookups" above.

For example, this ``Q`` object encapsulates a single ``LIKE`` query::

    from django.db.models import Q
    Q(question__startswith='What')

``Q`` objects can be combined using the ``&`` and ``|`` operators. When an
operator is used on two ``Q`` objects, it yields a new ``Q`` object.

For example, this statement yields a single ``Q`` object that represents the
"OR" of two ``"question__startswith"`` queries::

    Q(question__startswith='Who') | Q(question__startswith='What')

This is equivalent to the following SQL ``WHERE`` clause::

    WHERE question LIKE 'Who%' OR question LIKE 'What%'

You can compose statements of arbitrary complexity by combining ``Q`` objects
with the ``&`` and ``|`` operators and use parenthetical grouping. Also, ``Q``
objects can be negated using the ``~`` operator, allowing for combined lookups
that combine both a normal query and a negated (``NOT``) query::

    Q(question__startswith='Who') | ~Q(pub_date__year=2005)

Each lookup function that takes keyword-arguments
(e.g. :meth:`~django.db.models.query.QuerySet.filter`,
:meth:`~django.db.models.query.QuerySet.exclude`,
:meth:`~django.db.models.query.QuerySet.get`) can also be passed one or more
``Q`` objects as positional (not-named) arguments. If you provide multiple
``Q`` object arguments to a lookup function, the arguments will be "AND"ed
together. For example::

    Poll.objects.get(
        Q(question__startswith='Who'),
        Q(pub_date=date(2005, 5, 2)) | Q(pub_date=date(2005, 5, 6))
    )

... roughly translates into the SQL:

.. code-block:: sql

    SELECT * from polls WHERE question LIKE 'Who%'
        AND (pub_date = '2005-05-02' OR pub_date = '2005-05-06')

Lookup functions can mix the use of ``Q`` objects and keyword arguments. All
arguments provided to a lookup function (be they keyword arguments or ``Q``
objects) are "AND"ed together. However, if a ``Q`` object is provided, it must
precede the definition of any keyword arguments. For example::

    Poll.objects.get(
        Q(pub_date=date(2005, 5, 2)) | Q(pub_date=date(2005, 5, 6)),
        question__startswith='Who',
    )

... would be a valid query, equivalent to the previous example; but::

    # INVALID QUERY
    Poll.objects.get(
        question__startswith='Who',
        Q(pub_date=date(2005, 5, 2)) | Q(pub_date=date(2005, 5, 6))
    )

... would not be valid.

.. seealso::

    The :source:`OR lookups examples <tests/or_lookups/tests.py>` in Django's
    unit tests show some possible uses of ``Q``.

Comparing objects
=================

To compare two model instances, use the standard Python comparison operator,
the double equals sign: ``==``. Behind the scenes, that compares the primary
key values of two models.

Using the ``Entry`` example above, the following two statements are equivalent::

    >>> some_entry == other_entry
    >>> some_entry.id == other_entry.id

If a model's primary key isn't called ``id``, no problem. Comparisons will
always use the primary key, whatever it's called. For example, if a model's
primary key field is called ``name``, these two statements are equivalent::

    >>> some_obj == other_obj
    >>> some_obj.name == other_obj.name

.. _topics-db-queries-delete:

Deleting objects
================

The delete method, conveniently, is named
:meth:`~django.db.models.Model.delete`. This method immediately deletes the
object and returns the number of objects deleted and a dictionary with
the number of deletions per object type. Example::

    >>> e.delete()
    (1, {'weblog.Entry': 1})

You can also delete objects in bulk. Every
:class:`~django.db.models.query.QuerySet` has a
:meth:`~django.db.models.query.QuerySet.delete` method, which deletes all
members of that :class:`~django.db.models.query.QuerySet`.

For example, this deletes all ``Entry`` objects with a ``pub_date`` year of
2005::

    >>> Entry.objects.filter(pub_date__year=2005).delete()
    (5, {'webapp.Entry': 5})

Keep in mind that this will, whenever possible, be executed purely in SQL, and
so the ``delete()`` methods of individual object instances will not necessarily
be called during the process. If you've provided a custom ``delete()`` method
on a model class and want to ensure that it is called, you will need to
"manually" delete instances of that model (e.g., by iterating over a
:class:`~django.db.models.query.QuerySet` and calling ``delete()`` on each
object individually) rather than using the bulk
:meth:`~django.db.models.query.QuerySet.delete` method of a
:class:`~django.db.models.query.QuerySet`.

When Django deletes an object, by default it emulates the behavior of the SQL
constraint ``ON DELETE CASCADE`` -- in other words, any objects which had
foreign keys pointing at the object to be deleted will be deleted along with
it. For example::

    b = Blog.objects.get(pk=1)
    # This will delete the Blog and all of its Entry objects.
    b.delete()

This cascade behavior is customizable via the
:attr:`~django.db.models.ForeignKey.on_delete` argument to the
:class:`~django.db.models.ForeignKey`.

Note that :meth:`~django.db.models.query.QuerySet.delete` is the only
:class:`~django.db.models.query.QuerySet` method that is not exposed on a
:class:`~django.db.models.Manager` itself. This is a safety mechanism to
prevent you from accidentally requesting ``Entry.objects.delete()``, and
deleting *all* the entries. If you *do* want to delete all the objects, then
you have to explicitly request a complete query set::

    Entry.objects.all().delete()

.. _topics-db-queries-copy:

Copying model instances
=======================

Although there is no built-in method for copying model instances, it is
possible to easily create new instance with all fields' values copied. In the
simplest case, you can set ``pk`` to ``None``. Using our blog example::

    blog = Blog(name='My blog', tagline='Blogging is easy')
    blog.save() # blog.pk == 1

    blog.pk = None
    blog.save() # blog.pk == 2

Things get more complicated if you use inheritance. Consider a subclass of
``Blog``::

    class ThemeBlog(Blog):
        theme = models.CharField(max_length=200)

    django_blog = ThemeBlog(name='Django', tagline='Django is easy', theme='python')
    django_blog.save() # django_blog.pk == 3

Due to how inheritance works, you have to set both ``pk`` and ``id`` to None::

    django_blog.pk = None
    django_blog.id = None
    django_blog.save() # django_blog.pk == 4

This process doesn't copy relations that aren't part of the model's database
table. For example, ``Entry`` has a ``ManyToManyField`` to ``Author``. After
duplicating an entry, you must set the many-to-many relations for the new
entry::

    entry = Entry.objects.all()[0] # some previous entry
    old_authors = entry.authors.all()
    entry.pk = None
    entry.save()
    entry.authors.set(old_authors)

For a ``OneToOneField``, you must duplicate the related object and assign it
to the new object's field to avoid violating the one-to-one unique constraint.
For example, assuming ``entry`` is already duplicated as above::

    detail = EntryDetail.objects.all()[0]
    detail.pk = None
    detail.entry = entry
    detail.save()

.. _topics-db-queries-update:

Updating multiple objects at once
=================================

Sometimes you want to set a field to a particular value for all the objects in
a :class:`~django.db.models.query.QuerySet`. You can do this with the
:meth:`~django.db.models.query.QuerySet.update` method. For example::

    # Update all the headlines with pub_date in 2007.
    Entry.objects.filter(pub_date__year=2007).update(headline='Everything is the same')

You can only set non-relation fields and :class:`~django.db.models.ForeignKey`
fields using this method. To update a non-relation field, provide the new value
as a constant. To update :class:`~django.db.models.ForeignKey` fields, set the
new value to be the new model instance you want to point to. For example::

    >>> b = Blog.objects.get(pk=1)

    # Change every Entry so that it belongs to this Blog.
    >>> Entry.objects.all().update(blog=b)

The ``update()`` method is applied instantly and returns the number of rows
matched by the query (which may not be equal to the number of rows updated if
some rows already have the new value). The only restriction on the
:class:`~django.db.models.query.QuerySet` being updated is that it can only
access one database table: the model's main table. You can filter based on
related fields, but you can only update columns in the model's main
table. Example::

    >>> b = Blog.objects.get(pk=1)

    # Update all the headlines belonging to this Blog.
    >>> Entry.objects.select_related().filter(blog=b).update(headline='Everything is the same')

Be aware that the ``update()`` method is converted directly to an SQL
statement. It is a bulk operation for direct updates. It doesn't run any
:meth:`~django.db.models.Model.save` methods on your models, or emit the
``pre_save`` or ``post_save`` signals (which are a consequence of calling
:meth:`~django.db.models.Model.save`), or honor the
:attr:`~django.db.models.DateField.auto_now` field option.
If you want to save every item in a :class:`~django.db.models.query.QuerySet`
and make sure that the :meth:`~django.db.models.Model.save` method is called on
each instance, you don't need any special function to handle that. Loop over
them and call :meth:`~django.db.models.Model.save`::

    for item in my_queryset:
        item.save()

Calls to update can also use :class:`F expressions <django.db.models.F>` to
update one field based on the value of another field in the model. This is
especially useful for incrementing counters based upon their current value. For
example, to increment the pingback count for every entry in the blog::

    >>> Entry.objects.all().update(number_of_pingbacks=F('number_of_pingbacks') + 1)

However, unlike ``F()`` objects in filter and exclude clauses, you can't
introduce joins when you use ``F()`` objects in an update -- you can only
reference fields local to the model being updated. If you attempt to introduce
a join with an ``F()`` object, a ``FieldError`` will be raised::

    # This will raise a FieldError
    >>> Entry.objects.update(headline=F('blog__name'))

.. _topics-db-queries-related:

Related objects
===============

When you define a relationship in a model (i.e., a
:class:`~django.db.models.ForeignKey`,
:class:`~django.db.models.OneToOneField`, or
:class:`~django.db.models.ManyToManyField`), instances of that model will have
a convenient API to access the related object(s).

Using the models at the top of this page, for example, an ``Entry`` object ``e``
can get its associated ``Blog`` object by accessing the ``blog`` attribute:
``e.blog``.

(Behind the scenes, this functionality is implemented by Python descriptors_.
This shouldn't really matter to you, but we point it out here for the curious.)

Django also creates API accessors for the "other" side of the relationship --
the link from the related model to the model that defines the relationship.
For example, a ``Blog`` object ``b`` has access to a list of all related
``Entry`` objects via the ``entry_set`` attribute: ``b.entry_set.all()``.

All examples in this section use the sample ``Blog``, ``Author`` and ``Entry``
models defined at the top of this page.

.. _descriptors: https://docs.python.org/howto/descriptor.html

One-to-many relationships
-------------------------

Forward
~~~~~~~

If a model has a :class:`~django.db.models.ForeignKey`, instances of that model
will have access to the related (foreign) object via an attribute of the model.

Example::

    >>> e = Entry.objects.get(id=2)
    >>> e.blog # Returns the related Blog object.

You can get and set via a foreign-key attribute. As you may expect, changes to
the foreign key aren't saved to the database until you call
:meth:`~django.db.models.Model.save`. Example::

    >>> e = Entry.objects.get(id=2)
    >>> e.blog = some_blog
    >>> e.save()

If a :class:`~django.db.models.ForeignKey` field has ``null=True`` set (i.e.,
it allows ``NULL`` values), you can assign ``None`` to remove the relation.
Example::

    >>> e = Entry.objects.get(id=2)
    >>> e.blog = None
    >>> e.save() # "UPDATE blog_entry SET blog_id = NULL ...;"

Forward access to one-to-many relationships is cached the first time the
related object is accessed. Subsequent accesses to the foreign key on the same
object instance are cached. Example::

    >>> e = Entry.objects.get(id=2)
    >>> print(e.blog)  # Hits the database to retrieve the associated Blog.
    >>> print(e.blog)  # Doesn't hit the database; uses cached version.

Note that the :meth:`~django.db.models.query.QuerySet.select_related`
:class:`~django.db.models.query.QuerySet` method recursively prepopulates the
cache of all one-to-many relationships ahead of time. Example::

    >>> e = Entry.objects.select_related().get(id=2)
    >>> print(e.blog)  # Doesn't hit the database; uses cached version.
    >>> print(e.blog)  # Doesn't hit the database; uses cached version.

.. _backwards-related-objects:

Following relationships "backward"
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

If a model has a :class:`~django.db.models.ForeignKey`, instances of the
foreign-key model will have access to a :class:`~django.db.models.Manager` that
returns all instances of the first model. By default, this
:class:`~django.db.models.Manager` is named ``FOO_set``, where ``FOO`` is the
source model name, lowercased. This :class:`~django.db.models.Manager` returns
``QuerySets``, which can be filtered and manipulated as described in the
"Retrieving objects" section above.

Example::

    >>> b = Blog.objects.get(id=1)
    >>> b.entry_set.all() # Returns all Entry objects related to Blog.

    # b.entry_set is a Manager that returns QuerySets.
    >>> b.entry_set.filter(headline__contains='Lennon')
    >>> b.entry_set.count()

You can override the ``FOO_set`` name by setting the
:attr:`~django.db.models.ForeignKey.related_name` parameter in the
:class:`~django.db.models.ForeignKey` definition. For example, if the ``Entry``
model was altered to ``blog = ForeignKey(Blog, on_delete=models.CASCADE,
related_name='entries')``, the above example code would look like this::

    >>> b = Blog.objects.get(id=1)
    >>> b.entries.all() # Returns all Entry objects related to Blog.

    # b.entries is a Manager that returns QuerySets.
    >>> b.entries.filter(headline__contains='Lennon')
    >>> b.entries.count()

.. _using-custom-reverse-manager:

Using a custom reverse manager
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

By default the :class:`~django.db.models.fields.related.RelatedManager` used
for reverse relations is a subclass of the :ref:`default manager <manager-names>`
for that model. If you would like to specify a different manager for a given
query you can use the following syntax::

    from django.db import models

    class Entry(models.Model):
        #...
        objects = models.Manager()  # Default Manager
        entries = EntryManager()    # Custom Manager

    b = Blog.objects.get(id=1)
    b.entry_set(manager='entries').all()

If ``EntryManager`` performed default filtering in its ``get_queryset()``
method, that filtering would apply to the ``all()`` call.

Specifying a custom reverse manager also enables you to call its custom
methods::

    b.entry_set(manager='entries').is_published()

Additional methods to handle related objects
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In addition to the :class:`~django.db.models.query.QuerySet` methods defined in
"Retrieving objects" above, the :class:`~django.db.models.ForeignKey`
:class:`~django.db.models.Manager` has additional methods used to handle the
set of related objects. A synopsis of each is below, and complete details can
be found in the :doc:`related objects reference </ref/models/relations>`.

``add(obj1, obj2, ...)``
    Adds the specified model objects to the related object set.

``create(**kwargs)``
    Creates a new object, saves it and puts it in the related object set.
    Returns the newly created object.

``remove(obj1, obj2, ...)``
    Removes the specified model objects from the related object set.

``clear()``
    Removes all objects from the related object set.

``set(objs)``
    Replace the set of related objects.

To assign the members of a related set, use the ``set()`` method with an
iterable of object instances. For example, if ``e1`` and ``e2`` are ``Entry``
instances::

    b = Blog.objects.get(id=1)
    b.entry_set.set([e1, e2])

If the ``clear()`` method is available, any pre-existing objects will be
removed from the ``entry_set`` before all objects in the iterable (in this
case, a list) are added to the set. If the ``clear()`` method is *not*
available, all objects in the iterable will be added without removing any
existing elements.

Each "reverse" operation described in this section has an immediate effect on
the database. Every addition, creation and deletion is immediately and
automatically saved to the database.

.. _m2m-reverse-relationships:

Many-to-many relationships
--------------------------

Both ends of a many-to-many relationship get automatic API access to the other
end. The API works similar to a "backward" one-to-many relationship, above.

One difference is in the attribute naming: The model that defines the
:class:`~django.db.models.ManyToManyField` uses the attribute name of that
field itself, whereas the "reverse" model uses the lowercased model name of the
original model, plus ``'_set'`` (just like reverse one-to-many relationships).

An example makes this easier to understand::

    e = Entry.objects.get(id=3)
    e.authors.all() # Returns all Author objects for this Entry.
    e.authors.count()
    e.authors.filter(name__contains='John')

    a = Author.objects.get(id=5)
    a.entry_set.all() # Returns all Entry objects for this Author.

Like :class:`~django.db.models.ForeignKey`,
:class:`~django.db.models.ManyToManyField` can specify
:attr:`~django.db.models.ManyToManyField.related_name`. In the above example,
if the :class:`~django.db.models.ManyToManyField` in ``Entry`` had specified
``related_name='entries'``, then each ``Author`` instance would have an
``entries`` attribute instead of ``entry_set``.

Another difference from one-to-many relationships is that in addition to model
instances,  the ``add()``, ``set()``, and ``remove()`` methods on many-to-many
relationships accept primary key values. For example, if ``e1`` and ``e2`` are
``Entry`` instances, then these ``set()`` calls work identically::

    a = Author.objects.get(id=5)
    a.entry_set.set([e1, e2])
    a.entry_set.set([e1.pk, e2.pk])

One-to-one relationships
------------------------

One-to-one relationships are very similar to many-to-one relationships. If you
define a :class:`~django.db.models.OneToOneField` on your model, instances of
that model will have access to the related object via an attribute of the
model.

For example::

    class EntryDetail(models.Model):
        entry = models.OneToOneField(Entry, on_delete=models.CASCADE)
        details = models.TextField()

    ed = EntryDetail.objects.get(id=2)
    ed.entry # Returns the related Entry object.

The difference comes in "reverse" queries. The related model in a one-to-one
relationship also has access to a :class:`~django.db.models.Manager` object, but
that :class:`~django.db.models.Manager` represents a single object, rather than
a collection of objects::

    e = Entry.objects.get(id=2)
    e.entrydetail # returns the related EntryDetail object

If no object has been assigned to this relationship, Django will raise
a ``DoesNotExist`` exception.

Instances can be assigned to the reverse relationship in the same way as
you would assign the forward relationship::

    e.entrydetail = ed

How are the backward relationships possible?
--------------------------------------------

Other object-relational mappers require you to define relationships on both
sides. The Django developers believe this is a violation of the DRY (Don't
Repeat Yourself) principle, so Django only requires you to define the
relationship on one end.

But how is this possible, given that a model class doesn't know which other
model classes are related to it until those other model classes are loaded?

The answer lies in the :data:`app registry <django.apps.apps>`. When Django
starts, it imports each application listed in :setting:`INSTALLED_APPS`, and
then the ``models`` module inside each application. Whenever a new model class
is created, Django adds backward-relationships to any related models. If the
related models haven't been imported yet, Django keeps tracks of the
relationships and adds them when the related models eventually are imported.

For this reason, it's particularly important that all the models you're using
be defined in applications listed in :setting:`INSTALLED_APPS`. Otherwise,
backwards relations may not work properly.

Queries over related objects
----------------------------

Queries involving related objects follow the same rules as queries involving
normal value fields. When specifying the value for a query to match, you may
use either an object instance itself, or the primary key value for the object.

For example, if you have a Blog object ``b`` with ``id=5``, the following
three queries would be identical::

    Entry.objects.filter(blog=b) # Query using object instance
    Entry.objects.filter(blog=b.id) # Query using id from instance
    Entry.objects.filter(blog=5) # Query using id directly

Falling back to raw SQL
=======================

If you find yourself needing to write an SQL query that is too complex for
Django's database-mapper to handle, you can fall back on writing SQL by hand.
Django has a couple of options for writing raw SQL queries; see
:doc:`/topics/db/sql`.

Finally, it's important to note that the Django database layer is merely an
interface to your database. You can access your database via other tools,
programming languages or database frameworks; there's nothing Django-specific
about your database.