diff -r 5ff1fc726848 -r c6bca38c1cbf parts/django/docs/topics/db/queries.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/parts/django/docs/topics/db/queries.txt Sat Jan 08 11:20:57 2011 +0530 @@ -0,0 +1,1110 @@ +============== +Making queries +============== + +.. currentmodule:: django.db.models + +Once you've created your :doc:`data 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 ` 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 + + class Blog(models.Model): + name = models.CharField(max_length=100) + tagline = models.TextField() + + def __unicode__(self): + return self.name + + class Author(models.Model): + name = models.CharField(max_length=50) + email = models.EmailField() + + def __unicode__(self): + return self.name + + class Entry(models.Model): + blog = models.ForeignKey(Blog) + headline = models.CharField(max_length=255) + body_text = models.TextField() + pub_date = models.DateTimeField() + authors = models.ManyToManyField(Author) + n_comments = models.IntegerField() + n_pingbacks = models.IntegerField() + rating = models.IntegerField() + + def __unicode__(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 ``save()`` to save it to the database. + +You import the model class from wherever it lives on the Python path, as you +may expect. (We point this out here because previous Django versions required +funky model importing.) + +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 ``save()``. + +The ``save()`` method has no return value. + +.. seealso:: + + ``save()`` takes a number of advanced options not described here. + See the documentation for ``save()`` for complete details. + + To create an object and save it all in one step see the ```create()``` + method. + +Saving changes to objects +========================= + +To save changes to an object that's already in the database, use ``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 ``save()``. + +Saving ``ForeignKey`` and ``ManyToManyField`` fields +---------------------------------------------------- + +Updating a ``ForeignKey`` field works exactly the same way as saving a normal +field; simply assign an object of the right type to the field in question. +This example updates the ``blog`` attribute of an ``Entry`` instance ``entry``:: + + >>> from blog.models import Entry + >>> entry = Entry.objects.get(pk=1) + >>> cheese_blog = Blog.objects.get(name="Cheddar Talk") + >>> entry.blog = cheese_blog + >>> entry.save() + +Updating a ``ManyToManyField`` works a little differently; use the ``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) + +Django will complain if you try to assign or add an object of the wrong type. + +Retrieving objects +================== + +To retrieve objects from your database, you construct a ``QuerySet`` via a +``Manager`` on your model class. + +A ``QuerySet`` represents a collection of objects from your database. It can +have zero, one or many *filters* -- criteria that narrow down the collection +based on given parameters. In SQL terms, a ``QuerySet`` equates to a ``SELECT`` +statement, and a filter is a limiting clause such as ``WHERE`` or ``LIMIT``. + +You get a ``QuerySet`` by using your model's ``Manager``. Each model has at +least one ``Manager``, and it's called ``objects`` by default. Access it +directly via the model class, like so:: + + >>> Blog.objects + + >>> 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 ``Manager`` is the main source of ``QuerySets`` for a model. It acts as a +"root" ``QuerySet`` that describes all objects in the model's database table. +For example, ``Blog.objects`` is the initial ``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 ``all()`` method on a ``Manager``:: + + >>> all_entries = Entry.objects.all() + +The ``all()`` method returns a ``QuerySet`` of all the objects in the database. + +(If ``Entry.objects`` is a ``QuerySet``, why can't we just do ``Entry.objects``? +That's because ``Entry.objects``, the root ``QuerySet``, is a special case +that cannot be evaluated. The ``all()`` method returns a ``QuerySet`` that +*can* be evaluated.) + + +Retrieving specific objects with filters +---------------------------------------- + +The root ``QuerySet`` provided by the ``Manager`` 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 ``QuerySet``, adding filter +conditions. The two most common ways to refine a ``QuerySet`` are: + + ``filter(**kwargs)`` + Returns a new ``QuerySet`` containing objects that match the given + lookup parameters. + + ``exclude(**kwargs)`` + Returns a new ``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 ``QuerySet`` of blog entries from the year 2006, use +``filter()`` like so:: + + Entry.objects.filter(pub_date__year=2006) + +We don't have to add an ``all()`` -- ``Entry.objects.all().filter(...)``. That +would still work, but you only need ``all()`` when you want all objects from the +root ``QuerySet``. + +.. _chaining-filters: + +Chaining filters +~~~~~~~~~~~~~~~~ + +The result of refining a ``QuerySet`` is itself a ``QuerySet``, so it's +possible to chain refinements together. For example:: + + >>> Entry.objects.filter( + ... headline__startswith='What' + ... ).exclude( + ... pub_date__gte=datetime.now() + ... ).filter( + ... pub_date__gte=datetime(2005, 1, 1) + ... ) + +This takes the initial ``QuerySet`` of all entries in the database, adds a +filter, then an exclusion, then another filter. The final result is a +``QuerySet`` containing all entries with a headline that starts with "What", +that were published between January 1, 2005, and the current day. + +.. _filtered-querysets-are-unique: + +Filtered QuerySets are unique +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Each time you refine a ``QuerySet``, you get a brand-new ``QuerySet`` that is +in no way bound to the previous ``QuerySet``. Each refinement creates a +separate and distinct ``QuerySet`` that can be stored, used and reused. + +Example:: + + >> q1 = Entry.objects.filter(headline__startswith="What") + >> q2 = q1.exclude(pub_date__gte=datetime.now()) + >> q3 = q1.filter(pub_date__gte=datetime.now()) + +These three ``QuerySets`` are separate. The first is a base ``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 greater than now. The third is a subset of the first, +with an additional criteria that selects only the records whose ``pub_date`` is +greater than now. The initial ``QuerySet`` (``q1``) is unaffected by the +refinement process. + +.. _querysets-are-lazy: + +QuerySets are lazy +~~~~~~~~~~~~~~~~~~ + +``QuerySets`` are lazy -- the act of creating a ``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 ``QuerySet`` is *evaluated*. Take a look at +this example:: + + >>> q = Entry.objects.filter(headline__startswith="What") + >>> q = q.filter(pub_date__lte=datetime.now()) + >>> 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 ``QuerySet`` +aren't fetched from the database until you "ask" for them. When you do, the +``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 +----------------------------------- + +``.filter()`` will always give you a ``QuerySet``, even if only a single +object matches the query - in this case, it will be a ``QuerySet`` containing +a single element. + +If you know there is only one object that matches your query, you can use +the ``get()`` method on a `Manager` which returns the object directly:: + + >>> one_entry = Entry.objects.get(pk=1) + +You can use any query expression with ``get()``, just like with ``filter()`` - +again, see `Field lookups`_ below. + +Note that there is a difference between using ``.get()``, and using +``.filter()`` with a slice of ``[0]``. If there are no results that match the +query, ``.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 ``get()`` +query. In this case, it will raise ``MultipleObjectsReturned``, which again is +an attribute of the model class itself. + + +Other QuerySet methods +---------------------- + +Most of the time you'll use ``all()``, ``get()``, ``filter()`` and ``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 ` for a complete +list of all the various ``QuerySet`` methods. + +.. _limiting-querysets: + +Limiting QuerySets +------------------ + +Use a subset of Python's array-slicing syntax to limit your ``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 ``QuerySet`` returns a new ``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] + +To retrieve a *single* object rather than a list +(e.g. ``SELECT foo FROM bar LIMIT 1``), use a simple 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.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 ``QuerySet`` methods ``filter()``, +``exclude()`` and ``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:: + + 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 `Keyword Arguments`_ in the official Python tutorial. + + .. _`Keyword Arguments`: http://docs.python.org/tutorial/controlflow.html#keyword-arguments + +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 `. 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="Man bites dog") + + Would generate SQL along these lines: + + .. code-block:: sql + + SELECT ... WHERE headline = 'Man 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 `. + +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, just 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__exact='Beatles Blog') + +This spanning can be as deep as you'd like. + +It works backwards, too. To refer to a "reverse" relationship, just use 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 ``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 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. versionadded:: 1.0 + +When you are filtering an object based on a ``ManyToManyField`` or a reverse +``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 ``ManyToManyField``. For example, if +an ``Entry`` has a ``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 +``filter()`` and ``exclude()`` calls. Everything inside a single ``filter()`` +call is applied simultaneously to filter out items matching all those +requirements. Successive ``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 ``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) + +In this second example, the first filter restricted the queryset to all those +blogs linked to that particular type of entry. The second filter restricted +the set of blogs *further* to those that are also linked to the second type of +entry. The entries select 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. + +All of this behavior also applies to ``exclude()``: all the conditions in a +single ``exclude()`` statement apply to a single instance (if those conditions +are talking about the same multi-valued relation). Conditions in subsequent +``filter()`` or ``exclude()`` calls that refer to the same relation may end up +filtering on different linked objects. + +.. _query-expressions: + +Filters can reference fields on the model +----------------------------------------- + +.. versionadded:: 1.1 + +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 the ``F()`` object 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 comment count, +and use that ``F()`` object in the query:: + + >>> from django.db.models import F + >>> Entry.objects.filter(n_comments__gt=F('n_pingbacks')) + +Django supports the use of addition, subtraction, multiplication, +division and modulo 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(n_comments__gt=F('n_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('n_comments') + F('n_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')) + +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, just 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 QuerySets +--------------------- + +Each ``QuerySet`` contains a cache, to minimize database access. It's important +to understand how it works, in order to write the most efficient code. + +In a newly created ``QuerySet``, the cache is empty. The first time a +``QuerySet`` is evaluated -- and, hence, a database query happens -- Django +saves the query results in the ``QuerySet``'s cache and returns the results +that have been explicitly requested (e.g., the next element, if the +``QuerySet`` is being iterated over). Subsequent evaluations of the +``QuerySet`` reuse the cached results. + +Keep this caching behavior in mind, because it may bite you if you don't use +your ``QuerySet``\s correctly. For example, the following will create two +``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, simply save the ``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. + +.. _complex-lookups-with-q: + +Complex lookups with Q objects +============================== + +Keyword argument queries -- in ``filter()``, etc. -- are "AND"ed together. If +you need to execute more complex queries (for example, queries with ``OR`` +statements), you can use ``Q`` objects. + +A ``Q`` object (``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:: + + 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. ``filter()``, +``exclude()``, ``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:: + + 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 `OR lookups examples`_ in the Django unit tests show some possible uses + of ``Q``. + + .. _OR lookups examples: http://code.djangoproject.com/browser/django/trunk/tests/modeltests/or_lookups/tests.py + +Comparing objects +================= + +To compare two model instances, just 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 ``delete()``. This method immediately +deletes the object and has no return value. Example:: + + e.delete() + +You can also delete objects in bulk. Every ``QuerySet`` has a ``delete()`` +method, which deletes all members of that ``QuerySet``. + +For example, this deletes all ``Entry`` objects with a ``pub_date`` year of +2005:: + + Entry.objects.filter(pub_date__year=2005).delete() + +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 ``QuerySet`` and calling ``delete()`` +on each object individually) rather than using the bulk ``delete()`` +method of a ``QuerySet``. + +When Django deletes an object, 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() + +Note that ``delete()`` is the only ``QuerySet`` method that is not exposed on a +``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-update: + +Updating multiple objects at once +================================= + +.. versionadded:: 1.0 + +Sometimes you want to set a field to a particular value for all the objects in +a ``QuerySet``. You can do this with the ``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 ``ForeignKey`` fields using this +method. To update a non-relation field, provide the new value as a constant. +To update ``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 +affected by the query. The only restriction on the ``QuerySet`` that is +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 +``save()`` methods on your models, or emit the ``pre_save`` or ``post_save`` +signals (which are a consequence of calling ``save()``). If you want to save +every item in a ``QuerySet`` and make sure that the ``save()`` method is +called on each instance, you don't need any special function to handle that. +Just loop over them and call ``save()``:: + + for item in my_queryset: + item.save() + +.. versionadded:: 1.1 + +Calls to update can also use :ref:`F() objects ` 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(n_pingbacks=F('n_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')) + +Related objects +=============== + +When you define a relationship in a model (i.e., a ``ForeignKey``, +``OneToOneField``, or ``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: http://users.rcn.com/python/download/Descriptor.htm + +One-to-many relationships +------------------------- + +Forward +~~~~~~~ + +If a model has a ``ForeignKey``, instances of that model will have access to +the related (foreign) object via a simple 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 ``save()``. +Example:: + + >>> e = Entry.objects.get(id=2) + >>> e.blog = some_blog + >>> e.save() + +If a ``ForeignKey`` field has ``null=True`` set (i.e., it allows ``NULL`` +values), you can assign ``None`` to it. 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 ``select_related()`` ``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 ``ForeignKey``, instances of the foreign-key model will have +access to a ``Manager`` that returns all instances of the first model. By +default, this ``Manager`` is named ``FOO_set``, where ``FOO`` is the source +model name, lowercased. This ``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 ``related_name`` +parameter in the ``ForeignKey()`` definition. For example, if the ``Entry`` +model was altered to ``blog = ForeignKey(Blog, 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() + +You cannot access a reverse ``ForeignKey`` ``Manager`` from the class; it must +be accessed from an instance:: + + >>> Blog.entry_set + Traceback: + ... + AttributeError: "Manager must be accessed via instance". + +In addition to the ``QuerySet`` methods defined in "Retrieving objects" above, +the ``ForeignKey`` ``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 `. + +``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. + +To assign the members of a related set in one fell swoop, just assign to it +from any iterable object. The iterable can contain object instances, or just +a list of primary key values. For example:: + + b = Blog.objects.get(id=1) + b.entry_set = [e1, e2] + +In this example, ``e1`` and ``e2`` can be full Entry instances, or integer +primary key values. + +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. + +Many-to-many relationships +-------------------------- + +Both ends of a many-to-many relationship get automatic API access to the other +end. The API works just as a "backward" one-to-many relationship, above. + +The only difference is in the attribute naming: The model that defines the +``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 ``ForeignKey``, ``ManyToManyField`` can specify ``related_name``. In the +above example, if the ``ManyToManyField`` in ``Entry`` had specified +``related_name='entries'``, then each ``Author`` instance would have an +``entries`` attribute instead of ``entry_set``. + +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 a simple attribute of the +model. + +For example:: + + class EntryDetail(models.Model): + entry = models.OneToOneField(Entry) + 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 :setting:`INSTALLED_APPS` setting. The first time any model is +loaded, Django iterates over every model in :setting:`INSTALLED_APPS` and creates the +backward relationships in memory as needed. Essentially, one of the functions +of :setting:`INSTALLED_APPS` is to tell Django the entire model domain. + +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.