django1/django/db/models/query.py

1913 lines
79 KiB
Python

"""
The main QuerySet implementation. This provides the public API for the ORM.
"""
import copy
import operator
import warnings
from collections import namedtuple
from functools import lru_cache
from itertools import chain
from django.conf import settings
from django.core import exceptions
from django.db import (
DJANGO_VERSION_PICKLE_KEY, IntegrityError, connections, router,
transaction,
)
from django.db.models import DateField, DateTimeField, sql
from django.db.models.constants import LOOKUP_SEP
from django.db.models.deletion import Collector
from django.db.models.expressions import Case, Expression, F, Value, When
from django.db.models.fields import AutoField
from django.db.models.functions import Cast, Trunc
from django.db.models.query_utils import FilteredRelation, InvalidQuery, Q
from django.db.models.sql.constants import CURSOR, GET_ITERATOR_CHUNK_SIZE
from django.db.utils import NotSupportedError
from django.utils import timezone
from django.utils.functional import cached_property, partition
from django.utils.version import get_version
# The maximum number of results to fetch in a get() query.
MAX_GET_RESULTS = 21
# The maximum number of items to display in a QuerySet.__repr__
REPR_OUTPUT_SIZE = 20
# Pull into this namespace for backwards compatibility.
EmptyResultSet = sql.EmptyResultSet
class BaseIterable:
def __init__(self, queryset, chunked_fetch=False, chunk_size=GET_ITERATOR_CHUNK_SIZE):
self.queryset = queryset
self.chunked_fetch = chunked_fetch
self.chunk_size = chunk_size
class ModelIterable(BaseIterable):
"""Iterable that yields a model instance for each row."""
def __iter__(self):
queryset = self.queryset
db = queryset.db
compiler = queryset.query.get_compiler(using=db)
# Execute the query. This will also fill compiler.select, klass_info,
# and annotations.
results = compiler.execute_sql(chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size)
select, klass_info, annotation_col_map = (compiler.select, compiler.klass_info,
compiler.annotation_col_map)
model_cls = klass_info['model']
select_fields = klass_info['select_fields']
model_fields_start, model_fields_end = select_fields[0], select_fields[-1] + 1
init_list = [f[0].target.attname
for f in select[model_fields_start:model_fields_end]]
related_populators = get_related_populators(klass_info, select, db)
known_related_objects = [
(field, related_objs, operator.attrgetter(*[
field.attname
if from_field == 'self' else
queryset.model._meta.get_field(from_field).attname
for from_field in field.from_fields
])) for field, related_objs in queryset._known_related_objects.items()
]
for row in compiler.results_iter(results):
obj = model_cls.from_db(db, init_list, row[model_fields_start:model_fields_end])
for rel_populator in related_populators:
rel_populator.populate(row, obj)
if annotation_col_map:
for attr_name, col_pos in annotation_col_map.items():
setattr(obj, attr_name, row[col_pos])
# Add the known related objects to the model.
for field, rel_objs, rel_getter in known_related_objects:
# Avoid overwriting objects loaded by, e.g., select_related().
if field.is_cached(obj):
continue
rel_obj_id = rel_getter(obj)
try:
rel_obj = rel_objs[rel_obj_id]
except KeyError:
pass # May happen in qs1 | qs2 scenarios.
else:
setattr(obj, field.name, rel_obj)
yield obj
class ValuesIterable(BaseIterable):
"""
Iterable returned by QuerySet.values() that yields a dict for each row.
"""
def __iter__(self):
queryset = self.queryset
query = queryset.query
compiler = query.get_compiler(queryset.db)
# extra(select=...) cols are always at the start of the row.
names = [
*query.extra_select,
*query.values_select,
*query.annotation_select,
]
indexes = range(len(names))
for row in compiler.results_iter(chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size):
yield {names[i]: row[i] for i in indexes}
class ValuesListIterable(BaseIterable):
"""
Iterable returned by QuerySet.values_list(flat=False) that yields a tuple
for each row.
"""
def __iter__(self):
queryset = self.queryset
query = queryset.query
compiler = query.get_compiler(queryset.db)
if queryset._fields:
# extra(select=...) cols are always at the start of the row.
names = [
*query.extra_select,
*query.values_select,
*query.annotation_select,
]
fields = [*queryset._fields, *(f for f in query.annotation_select if f not in queryset._fields)]
if fields != names:
# Reorder according to fields.
index_map = {name: idx for idx, name in enumerate(names)}
rowfactory = operator.itemgetter(*[index_map[f] for f in fields])
return map(
rowfactory,
compiler.results_iter(chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size)
)
return compiler.results_iter(tuple_expected=True, chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size)
class NamedValuesListIterable(ValuesListIterable):
"""
Iterable returned by QuerySet.values_list(named=True) that yields a
namedtuple for each row.
"""
@staticmethod
@lru_cache()
def create_namedtuple_class(*names):
# Cache namedtuple() with @lru_cache() since it's too slow to be
# called for every QuerySet evaluation.
return namedtuple('Row', names)
def __iter__(self):
queryset = self.queryset
if queryset._fields:
names = queryset._fields
else:
query = queryset.query
names = [*query.extra_select, *query.values_select, *query.annotation_select]
tuple_class = self.create_namedtuple_class(*names)
new = tuple.__new__
for row in super().__iter__():
yield new(tuple_class, row)
class FlatValuesListIterable(BaseIterable):
"""
Iterable returned by QuerySet.values_list(flat=True) that yields single
values.
"""
def __iter__(self):
queryset = self.queryset
compiler = queryset.query.get_compiler(queryset.db)
for row in compiler.results_iter(chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size):
yield row[0]
class QuerySet:
"""Represent a lazy database lookup for a set of objects."""
def __init__(self, model=None, query=None, using=None, hints=None):
self.model = model
self._db = using
self._hints = hints or {}
self.query = query or sql.Query(self.model)
self._result_cache = None
self._sticky_filter = False
self._for_write = False
self._prefetch_related_lookups = ()
self._prefetch_done = False
self._known_related_objects = {} # {rel_field: {pk: rel_obj}}
self._iterable_class = ModelIterable
self._fields = None
def as_manager(cls):
# Address the circular dependency between `Queryset` and `Manager`.
from django.db.models.manager import Manager
manager = Manager.from_queryset(cls)()
manager._built_with_as_manager = True
return manager
as_manager.queryset_only = True
as_manager = classmethod(as_manager)
########################
# PYTHON MAGIC METHODS #
########################
def __deepcopy__(self, memo):
"""Don't populate the QuerySet's cache."""
obj = self.__class__()
for k, v in self.__dict__.items():
if k == '_result_cache':
obj.__dict__[k] = None
else:
obj.__dict__[k] = copy.deepcopy(v, memo)
return obj
def __getstate__(self):
# Force the cache to be fully populated.
self._fetch_all()
return {**self.__dict__, DJANGO_VERSION_PICKLE_KEY: get_version()}
def __setstate__(self, state):
msg = None
pickled_version = state.get(DJANGO_VERSION_PICKLE_KEY)
if pickled_version:
current_version = get_version()
if current_version != pickled_version:
msg = (
"Pickled queryset instance's Django version %s does not "
"match the current version %s." % (pickled_version, current_version)
)
else:
msg = "Pickled queryset instance's Django version is not specified."
if msg:
warnings.warn(msg, RuntimeWarning, stacklevel=2)
self.__dict__.update(state)
def __repr__(self):
data = list(self[:REPR_OUTPUT_SIZE + 1])
if len(data) > REPR_OUTPUT_SIZE:
data[-1] = "...(remaining elements truncated)..."
return '<%s %r>' % (self.__class__.__name__, data)
def __len__(self):
self._fetch_all()
return len(self._result_cache)
def __iter__(self):
"""
The queryset iterator protocol uses three nested iterators in the
default case:
1. sql.compiler.execute_sql()
- Returns 100 rows at time (constants.GET_ITERATOR_CHUNK_SIZE)
using cursor.fetchmany(). This part is responsible for
doing some column masking, and returning the rows in chunks.
2. sql.compiler.results_iter()
- Returns one row at time. At this point the rows are still just
tuples. In some cases the return values are converted to
Python values at this location.
3. self.iterator()
- Responsible for turning the rows into model objects.
"""
self._fetch_all()
return iter(self._result_cache)
def __bool__(self):
self._fetch_all()
return bool(self._result_cache)
def __getitem__(self, k):
"""Retrieve an item or slice from the set of results."""
if not isinstance(k, (int, slice)):
raise TypeError(
'QuerySet indices must be integers or slices, not %s.'
% type(k).__name__
)
assert ((not isinstance(k, slice) and (k >= 0)) or
(isinstance(k, slice) and (k.start is None or k.start >= 0) and
(k.stop is None or k.stop >= 0))), \
"Negative indexing is not supported."
if self._result_cache is not None:
return self._result_cache[k]
if isinstance(k, slice):
qs = self._chain()
if k.start is not None:
start = int(k.start)
else:
start = None
if k.stop is not None:
stop = int(k.stop)
else:
stop = None
qs.query.set_limits(start, stop)
return list(qs)[::k.step] if k.step else qs
qs = self._chain()
qs.query.set_limits(k, k + 1)
qs._fetch_all()
return qs._result_cache[0]
def __and__(self, other):
self._merge_sanity_check(other)
if isinstance(other, EmptyQuerySet):
return other
if isinstance(self, EmptyQuerySet):
return self
combined = self._chain()
combined._merge_known_related_objects(other)
combined.query.combine(other.query, sql.AND)
return combined
def __or__(self, other):
self._merge_sanity_check(other)
if isinstance(self, EmptyQuerySet):
return other
if isinstance(other, EmptyQuerySet):
return self
query = self if self.query.can_filter() else self.model._base_manager.filter(pk__in=self.values('pk'))
combined = query._chain()
combined._merge_known_related_objects(other)
if not other.query.can_filter():
other = other.model._base_manager.filter(pk__in=other.values('pk'))
combined.query.combine(other.query, sql.OR)
return combined
####################################
# METHODS THAT DO DATABASE QUERIES #
####################################
def _iterator(self, use_chunked_fetch, chunk_size):
yield from self._iterable_class(self, chunked_fetch=use_chunked_fetch, chunk_size=chunk_size)
def iterator(self, chunk_size=2000):
"""
An iterator over the results from applying this QuerySet to the
database.
"""
if chunk_size <= 0:
raise ValueError('Chunk size must be strictly positive.')
use_chunked_fetch = not connections[self.db].settings_dict.get('DISABLE_SERVER_SIDE_CURSORS')
return self._iterator(use_chunked_fetch, chunk_size)
def aggregate(self, *args, **kwargs):
"""
Return a dictionary containing the calculations (aggregation)
over the current queryset.
If args is present the expression is passed as a kwarg using
the Aggregate object's default alias.
"""
if self.query.distinct_fields:
raise NotImplementedError("aggregate() + distinct(fields) not implemented.")
self._validate_values_are_expressions((*args, *kwargs.values()), method_name='aggregate')
for arg in args:
# The default_alias property raises TypeError if default_alias
# can't be set automatically or AttributeError if it isn't an
# attribute.
try:
arg.default_alias
except (AttributeError, TypeError):
raise TypeError("Complex aggregates require an alias")
kwargs[arg.default_alias] = arg
query = self.query.chain()
for (alias, aggregate_expr) in kwargs.items():
query.add_annotation(aggregate_expr, alias, is_summary=True)
if not query.annotations[alias].contains_aggregate:
raise TypeError("%s is not an aggregate expression" % alias)
return query.get_aggregation(self.db, kwargs)
def count(self):
"""
Perform a SELECT COUNT() and return the number of records as an
integer.
If the QuerySet is already fully cached, return the length of the
cached results set to avoid multiple SELECT COUNT(*) calls.
"""
if self._result_cache is not None:
return len(self._result_cache)
return self.query.get_count(using=self.db)
def get(self, *args, **kwargs):
"""
Perform the query and return a single object matching the given
keyword arguments.
"""
clone = self._chain() if self.query.combinator else self.filter(*args, **kwargs)
if self.query.can_filter() and not self.query.distinct_fields:
clone = clone.order_by()
limit = None
if not clone.query.select_for_update or connections[clone.db].features.supports_select_for_update_with_limit:
limit = MAX_GET_RESULTS
clone.query.set_limits(high=limit)
num = len(clone)
if num == 1:
return clone._result_cache[0]
if not num:
raise self.model.DoesNotExist(
"%s matching query does not exist." %
self.model._meta.object_name
)
raise self.model.MultipleObjectsReturned(
'get() returned more than one %s -- it returned %s!' % (
self.model._meta.object_name,
num if not limit or num < limit else 'more than %s' % (limit - 1),
)
)
def create(self, **kwargs):
"""
Create a new object with the given kwargs, saving it to the database
and returning the created object.
"""
obj = self.model(**kwargs)
self._for_write = True
obj.save(force_insert=True, using=self.db)
return obj
def _populate_pk_values(self, objs):
for obj in objs:
if obj.pk is None:
obj.pk = obj._meta.pk.get_pk_value_on_save(obj)
def bulk_create(self, objs, batch_size=None, ignore_conflicts=False):
"""
Insert each of the instances into the database. Do *not* call
save() on each of the instances, do not send any pre/post_save
signals, and do not set the primary key attribute if it is an
autoincrement field (except if features.can_return_rows_from_bulk_insert=True).
Multi-table models are not supported.
"""
# When you bulk insert you don't get the primary keys back (if it's an
# autoincrement, except if can_return_rows_from_bulk_insert=True), so
# you can't insert into the child tables which references this. There
# are two workarounds:
# 1) This could be implemented if you didn't have an autoincrement pk
# 2) You could do it by doing O(n) normal inserts into the parent
# tables to get the primary keys back and then doing a single bulk
# insert into the childmost table.
# We currently set the primary keys on the objects when using
# PostgreSQL via the RETURNING ID clause. It should be possible for
# Oracle as well, but the semantics for extracting the primary keys is
# trickier so it's not done yet.
assert batch_size is None or batch_size > 0
# Check that the parents share the same concrete model with the our
# model to detect the inheritance pattern ConcreteGrandParent ->
# MultiTableParent -> ProxyChild. Simply checking self.model._meta.proxy
# would not identify that case as involving multiple tables.
for parent in self.model._meta.get_parent_list():
if parent._meta.concrete_model is not self.model._meta.concrete_model:
raise ValueError("Can't bulk create a multi-table inherited model")
if not objs:
return objs
self._for_write = True
connection = connections[self.db]
fields = self.model._meta.concrete_fields
objs = list(objs)
self._populate_pk_values(objs)
with transaction.atomic(using=self.db, savepoint=False):
objs_with_pk, objs_without_pk = partition(lambda o: o.pk is None, objs)
if objs_with_pk:
self._batched_insert(objs_with_pk, fields, batch_size, ignore_conflicts=ignore_conflicts)
for obj_with_pk in objs_with_pk:
obj_with_pk._state.adding = False
obj_with_pk._state.db = self.db
if objs_without_pk:
fields = [f for f in fields if not isinstance(f, AutoField)]
ids = self._batched_insert(objs_without_pk, fields, batch_size, ignore_conflicts=ignore_conflicts)
if connection.features.can_return_rows_from_bulk_insert and not ignore_conflicts:
assert len(ids) == len(objs_without_pk)
for obj_without_pk, pk in zip(objs_without_pk, ids):
obj_without_pk.pk = pk
obj_without_pk._state.adding = False
obj_without_pk._state.db = self.db
return objs
def bulk_update(self, objs, fields, batch_size=None):
"""
Update the given fields in each of the given objects in the database.
"""
if batch_size is not None and batch_size < 0:
raise ValueError('Batch size must be a positive integer.')
if not fields:
raise ValueError('Field names must be given to bulk_update().')
objs = tuple(objs)
if any(obj.pk is None for obj in objs):
raise ValueError('All bulk_update() objects must have a primary key set.')
fields = [self.model._meta.get_field(name) for name in fields]
if any(not f.concrete or f.many_to_many for f in fields):
raise ValueError('bulk_update() can only be used with concrete fields.')
if any(f.primary_key for f in fields):
raise ValueError('bulk_update() cannot be used with primary key fields.')
if not objs:
return
# PK is used twice in the resulting update query, once in the filter
# and once in the WHEN. Each field will also have one CAST.
max_batch_size = connections[self.db].ops.bulk_batch_size(['pk', 'pk'] + fields, objs)
batch_size = min(batch_size, max_batch_size) if batch_size else max_batch_size
requires_casting = connections[self.db].features.requires_casted_case_in_updates
batches = (objs[i:i + batch_size] for i in range(0, len(objs), batch_size))
updates = []
for batch_objs in batches:
update_kwargs = {}
for field in fields:
when_statements = []
for obj in batch_objs:
attr = getattr(obj, field.attname)
if not isinstance(attr, Expression):
attr = Value(attr, output_field=field)
when_statements.append(When(pk=obj.pk, then=attr))
case_statement = Case(*when_statements, output_field=field)
if requires_casting:
case_statement = Cast(case_statement, output_field=field)
update_kwargs[field.attname] = case_statement
updates.append(([obj.pk for obj in batch_objs], update_kwargs))
with transaction.atomic(using=self.db, savepoint=False):
for pks, update_kwargs in updates:
self.filter(pk__in=pks).update(**update_kwargs)
bulk_update.alters_data = True
def get_or_create(self, defaults=None, **kwargs):
"""
Look up an object with the given kwargs, creating one if necessary.
Return a tuple of (object, created), where created is a boolean
specifying whether an object was created.
"""
# The get() needs to be targeted at the write database in order
# to avoid potential transaction consistency problems.
self._for_write = True
try:
return self.get(**kwargs), False
except self.model.DoesNotExist:
params = self._extract_model_params(defaults, **kwargs)
return self._create_object_from_params(kwargs, params)
def update_or_create(self, defaults=None, **kwargs):
"""
Look up an object with the given kwargs, updating one with defaults
if it exists, otherwise create a new one.
Return a tuple (object, created), where created is a boolean
specifying whether an object was created.
"""
defaults = defaults or {}
self._for_write = True
with transaction.atomic(using=self.db):
try:
obj = self.select_for_update().get(**kwargs)
except self.model.DoesNotExist:
params = self._extract_model_params(defaults, **kwargs)
# Lock the row so that a concurrent update is blocked until
# after update_or_create() has performed its save.
obj, created = self._create_object_from_params(kwargs, params, lock=True)
if created:
return obj, created
for k, v in defaults.items():
setattr(obj, k, v() if callable(v) else v)
obj.save(using=self.db)
return obj, False
def _create_object_from_params(self, lookup, params, lock=False):
"""
Try to create an object using passed params. Used by get_or_create()
and update_or_create().
"""
try:
with transaction.atomic(using=self.db):
params = {k: v() if callable(v) else v for k, v in params.items()}
obj = self.create(**params)
return obj, True
except IntegrityError as e:
try:
qs = self.select_for_update() if lock else self
return qs.get(**lookup), False
except self.model.DoesNotExist:
pass
raise e
def _extract_model_params(self, defaults, **kwargs):
"""
Prepare `params` for creating a model instance based on the given
kwargs; for use by get_or_create() and update_or_create().
"""
defaults = defaults or {}
params = {k: v for k, v in kwargs.items() if LOOKUP_SEP not in k}
params.update(defaults)
property_names = self.model._meta._property_names
invalid_params = []
for param in params:
try:
self.model._meta.get_field(param)
except exceptions.FieldDoesNotExist:
# It's okay to use a model's property if it has a setter.
if not (param in property_names and getattr(self.model, param).fset):
invalid_params.append(param)
if invalid_params:
raise exceptions.FieldError(
"Invalid field name(s) for model %s: '%s'." % (
self.model._meta.object_name,
"', '".join(sorted(invalid_params)),
))
return params
def _earliest(self, *fields):
"""
Return the earliest object according to fields (if given) or by the
model's Meta.get_latest_by.
"""
if fields:
order_by = fields
else:
order_by = getattr(self.model._meta, 'get_latest_by')
if order_by and not isinstance(order_by, (tuple, list)):
order_by = (order_by,)
if order_by is None:
raise ValueError(
"earliest() and latest() require either fields as positional "
"arguments or 'get_latest_by' in the model's Meta."
)
assert not self.query.is_sliced, \
"Cannot change a query once a slice has been taken."
obj = self._chain()
obj.query.set_limits(high=1)
obj.query.clear_ordering(force_empty=True)
obj.query.add_ordering(*order_by)
return obj.get()
def earliest(self, *fields):
return self._earliest(*fields)
def latest(self, *fields):
return self.reverse()._earliest(*fields)
def first(self):
"""Return the first object of a query or None if no match is found."""
for obj in (self if self.ordered else self.order_by('pk'))[:1]:
return obj
def last(self):
"""Return the last object of a query or None if no match is found."""
for obj in (self.reverse() if self.ordered else self.order_by('-pk'))[:1]:
return obj
def in_bulk(self, id_list=None, *, field_name='pk'):
"""
Return a dictionary mapping each of the given IDs to the object with
that ID. If `id_list` isn't provided, evaluate the entire QuerySet.
"""
assert not self.query.is_sliced, \
"Cannot use 'limit' or 'offset' with in_bulk"
if field_name != 'pk' and not self.model._meta.get_field(field_name).unique:
raise ValueError("in_bulk()'s field_name must be a unique field but %r isn't." % field_name)
if id_list is not None:
if not id_list:
return {}
filter_key = '{}__in'.format(field_name)
batch_size = connections[self.db].features.max_query_params
id_list = tuple(id_list)
# If the database has a limit on the number of query parameters
# (e.g. SQLite), retrieve objects in batches if necessary.
if batch_size and batch_size < len(id_list):
qs = ()
for offset in range(0, len(id_list), batch_size):
batch = id_list[offset:offset + batch_size]
qs += tuple(self.filter(**{filter_key: batch}).order_by())
else:
qs = self.filter(**{filter_key: id_list}).order_by()
else:
qs = self._chain()
return {getattr(obj, field_name): obj for obj in qs}
def delete(self):
"""Delete the records in the current QuerySet."""
assert not self.query.is_sliced, \
"Cannot use 'limit' or 'offset' with delete."
if self._fields is not None:
raise TypeError("Cannot call delete() after .values() or .values_list()")
del_query = self._chain()
# The delete is actually 2 queries - one to find related objects,
# and one to delete. Make sure that the discovery of related
# objects is performed on the same database as the deletion.
del_query._for_write = True
# Disable non-supported fields.
del_query.query.select_for_update = False
del_query.query.select_related = False
del_query.query.clear_ordering(force_empty=True)
collector = Collector(using=del_query.db)
collector.collect(del_query)
deleted, _rows_count = collector.delete()
# Clear the result cache, in case this QuerySet gets reused.
self._result_cache = None
return deleted, _rows_count
delete.alters_data = True
delete.queryset_only = True
def _raw_delete(self, using):
"""
Delete objects found from the given queryset in single direct SQL
query. No signals are sent and there is no protection for cascades.
"""
return sql.DeleteQuery(self.model).delete_qs(self, using)
_raw_delete.alters_data = True
def update(self, **kwargs):
"""
Update all elements in the current QuerySet, setting all the given
fields to the appropriate values.
"""
assert not self.query.is_sliced, \
"Cannot update a query once a slice has been taken."
self._for_write = True
query = self.query.chain(sql.UpdateQuery)
query.add_update_values(kwargs)
# Clear any annotations so that they won't be present in subqueries.
query.annotations = {}
with transaction.mark_for_rollback_on_error(using=self.db):
rows = query.get_compiler(self.db).execute_sql(CURSOR)
self._result_cache = None
return rows
update.alters_data = True
def _update(self, values):
"""
A version of update() that accepts field objects instead of field names.
Used primarily for model saving and not intended for use by general
code (it requires too much poking around at model internals to be
useful at that level).
"""
assert not self.query.is_sliced, \
"Cannot update a query once a slice has been taken."
query = self.query.chain(sql.UpdateQuery)
query.add_update_fields(values)
# Clear any annotations so that they won't be present in subqueries.
query.annotations = {}
self._result_cache = None
return query.get_compiler(self.db).execute_sql(CURSOR)
_update.alters_data = True
_update.queryset_only = False
def exists(self):
if self._result_cache is None:
return self.query.has_results(using=self.db)
return bool(self._result_cache)
def _prefetch_related_objects(self):
# This method can only be called once the result cache has been filled.
prefetch_related_objects(self._result_cache, *self._prefetch_related_lookups)
self._prefetch_done = True
def explain(self, *, format=None, **options):
return self.query.explain(using=self.db, format=format, **options)
##################################################
# PUBLIC METHODS THAT RETURN A QUERYSET SUBCLASS #
##################################################
def raw(self, raw_query, params=None, translations=None, using=None):
if using is None:
using = self.db
qs = RawQuerySet(raw_query, model=self.model, params=params, translations=translations, using=using)
qs._prefetch_related_lookups = self._prefetch_related_lookups[:]
return qs
def _values(self, *fields, **expressions):
clone = self._chain()
if expressions:
clone = clone.annotate(**expressions)
clone._fields = fields
clone.query.set_values(fields)
return clone
def values(self, *fields, **expressions):
fields += tuple(expressions)
clone = self._values(*fields, **expressions)
clone._iterable_class = ValuesIterable
return clone
def values_list(self, *fields, flat=False, named=False):
if flat and named:
raise TypeError("'flat' and 'named' can't be used together.")
if flat and len(fields) > 1:
raise TypeError("'flat' is not valid when values_list is called with more than one field.")
field_names = {f for f in fields if not hasattr(f, 'resolve_expression')}
_fields = []
expressions = {}
counter = 1
for field in fields:
if hasattr(field, 'resolve_expression'):
field_id_prefix = getattr(field, 'default_alias', field.__class__.__name__.lower())
while True:
field_id = field_id_prefix + str(counter)
counter += 1
if field_id not in field_names:
break
expressions[field_id] = field
_fields.append(field_id)
else:
_fields.append(field)
clone = self._values(*_fields, **expressions)
clone._iterable_class = (
NamedValuesListIterable if named
else FlatValuesListIterable if flat
else ValuesListIterable
)
return clone
def dates(self, field_name, kind, order='ASC'):
"""
Return a list of date objects representing all available dates for
the given field_name, scoped to 'kind'.
"""
assert kind in ('year', 'month', 'week', 'day'), \
"'kind' must be one of 'year', 'month', 'week', or 'day'."
assert order in ('ASC', 'DESC'), \
"'order' must be either 'ASC' or 'DESC'."
return self.annotate(
datefield=Trunc(field_name, kind, output_field=DateField()),
plain_field=F(field_name)
).values_list(
'datefield', flat=True
).distinct().filter(plain_field__isnull=False).order_by(('-' if order == 'DESC' else '') + 'datefield')
def datetimes(self, field_name, kind, order='ASC', tzinfo=None):
"""
Return a list of datetime objects representing all available
datetimes for the given field_name, scoped to 'kind'.
"""
assert kind in ('year', 'month', 'week', 'day', 'hour', 'minute', 'second'), \
"'kind' must be one of 'year', 'month', 'week', 'day', 'hour', 'minute', or 'second'."
assert order in ('ASC', 'DESC'), \
"'order' must be either 'ASC' or 'DESC'."
if settings.USE_TZ:
if tzinfo is None:
tzinfo = timezone.get_current_timezone()
else:
tzinfo = None
return self.annotate(
datetimefield=Trunc(field_name, kind, output_field=DateTimeField(), tzinfo=tzinfo),
plain_field=F(field_name)
).values_list(
'datetimefield', flat=True
).distinct().filter(plain_field__isnull=False).order_by(('-' if order == 'DESC' else '') + 'datetimefield')
def none(self):
"""Return an empty QuerySet."""
clone = self._chain()
clone.query.set_empty()
return clone
##################################################################
# PUBLIC METHODS THAT ALTER ATTRIBUTES AND RETURN A NEW QUERYSET #
##################################################################
def all(self):
"""
Return a new QuerySet that is a copy of the current one. This allows a
QuerySet to proxy for a model manager in some cases.
"""
return self._chain()
def filter(self, *args, **kwargs):
"""
Return a new QuerySet instance with the args ANDed to the existing
set.
"""
self._not_support_combined_queries('filter')
return self._filter_or_exclude(False, *args, **kwargs)
def exclude(self, *args, **kwargs):
"""
Return a new QuerySet instance with NOT (args) ANDed to the existing
set.
"""
self._not_support_combined_queries('exclude')
return self._filter_or_exclude(True, *args, **kwargs)
def _filter_or_exclude(self, negate, *args, **kwargs):
if args or kwargs:
assert not self.query.is_sliced, \
"Cannot filter a query once a slice has been taken."
clone = self._chain()
if negate:
clone.query.add_q(~Q(*args, **kwargs))
else:
clone.query.add_q(Q(*args, **kwargs))
return clone
def complex_filter(self, filter_obj):
"""
Return a new QuerySet instance with filter_obj added to the filters.
filter_obj can be a Q object or a dictionary of keyword lookup
arguments.
This exists to support framework features such as 'limit_choices_to',
and usually it will be more natural to use other methods.
"""
if isinstance(filter_obj, Q):
clone = self._chain()
clone.query.add_q(filter_obj)
return clone
else:
return self._filter_or_exclude(None, **filter_obj)
def _combinator_query(self, combinator, *other_qs, all=False):
# Clone the query to inherit the select list and everything
clone = self._chain()
# Clear limits and ordering so they can be reapplied
clone.query.clear_ordering(True)
clone.query.clear_limits()
clone.query.combined_queries = (self.query,) + tuple(qs.query for qs in other_qs)
clone.query.combinator = combinator
clone.query.combinator_all = all
return clone
def union(self, *other_qs, all=False):
# If the query is an EmptyQuerySet, combine all nonempty querysets.
if isinstance(self, EmptyQuerySet):
qs = [q for q in other_qs if not isinstance(q, EmptyQuerySet)]
return qs[0]._combinator_query('union', *qs[1:], all=all) if qs else self
return self._combinator_query('union', *other_qs, all=all)
def intersection(self, *other_qs):
# If any query is an EmptyQuerySet, return it.
if isinstance(self, EmptyQuerySet):
return self
for other in other_qs:
if isinstance(other, EmptyQuerySet):
return other
return self._combinator_query('intersection', *other_qs)
def difference(self, *other_qs):
# If the query is an EmptyQuerySet, return it.
if isinstance(self, EmptyQuerySet):
return self
return self._combinator_query('difference', *other_qs)
def select_for_update(self, nowait=False, skip_locked=False, of=()):
"""
Return a new QuerySet instance that will select objects with a
FOR UPDATE lock.
"""
if nowait and skip_locked:
raise ValueError('The nowait option cannot be used with skip_locked.')
obj = self._chain()
obj._for_write = True
obj.query.select_for_update = True
obj.query.select_for_update_nowait = nowait
obj.query.select_for_update_skip_locked = skip_locked
obj.query.select_for_update_of = of
return obj
def select_related(self, *fields):
"""
Return a new QuerySet instance that will select related objects.
If fields are specified, they must be ForeignKey fields and only those
related objects are included in the selection.
If select_related(None) is called, clear the list.
"""
self._not_support_combined_queries('select_related')
if self._fields is not None:
raise TypeError("Cannot call select_related() after .values() or .values_list()")
obj = self._chain()
if fields == (None,):
obj.query.select_related = False
elif fields:
obj.query.add_select_related(fields)
else:
obj.query.select_related = True
return obj
def prefetch_related(self, *lookups):
"""
Return a new QuerySet instance that will prefetch the specified
Many-To-One and Many-To-Many related objects when the QuerySet is
evaluated.
When prefetch_related() is called more than once, append to the list of
prefetch lookups. If prefetch_related(None) is called, clear the list.
"""
self._not_support_combined_queries('prefetch_related')
clone = self._chain()
if lookups == (None,):
clone._prefetch_related_lookups = ()
else:
for lookup in lookups:
if isinstance(lookup, Prefetch):
lookup = lookup.prefetch_to
lookup = lookup.split(LOOKUP_SEP, 1)[0]
if lookup in self.query._filtered_relations:
raise ValueError('prefetch_related() is not supported with FilteredRelation.')
clone._prefetch_related_lookups = clone._prefetch_related_lookups + lookups
return clone
def annotate(self, *args, **kwargs):
"""
Return a query set in which the returned objects have been annotated
with extra data or aggregations.
"""
self._not_support_combined_queries('annotate')
self._validate_values_are_expressions(args + tuple(kwargs.values()), method_name='annotate')
annotations = {}
for arg in args:
# The default_alias property may raise a TypeError.
try:
if arg.default_alias in kwargs:
raise ValueError("The named annotation '%s' conflicts with the "
"default name for another annotation."
% arg.default_alias)
except TypeError:
raise TypeError("Complex annotations require an alias")
annotations[arg.default_alias] = arg
annotations.update(kwargs)
clone = self._chain()
names = self._fields
if names is None:
names = set(chain.from_iterable(
(field.name, field.attname) if hasattr(field, 'attname') else (field.name,)
for field in self.model._meta.get_fields()
))
for alias, annotation in annotations.items():
if alias in names:
raise ValueError("The annotation '%s' conflicts with a field on "
"the model." % alias)
if isinstance(annotation, FilteredRelation):
clone.query.add_filtered_relation(annotation, alias)
else:
clone.query.add_annotation(annotation, alias, is_summary=False)
for alias, annotation in clone.query.annotations.items():
if alias in annotations and annotation.contains_aggregate:
if clone._fields is None:
clone.query.group_by = True
else:
clone.query.set_group_by()
break
return clone
def order_by(self, *field_names):
"""Return a new QuerySet instance with the ordering changed."""
assert not self.query.is_sliced, \
"Cannot reorder a query once a slice has been taken."
obj = self._chain()
obj.query.clear_ordering(force_empty=False)
obj.query.add_ordering(*field_names)
return obj
def distinct(self, *field_names):
"""
Return a new QuerySet instance that will select only distinct results.
"""
assert not self.query.is_sliced, \
"Cannot create distinct fields once a slice has been taken."
obj = self._chain()
obj.query.add_distinct_fields(*field_names)
return obj
def extra(self, select=None, where=None, params=None, tables=None,
order_by=None, select_params=None):
"""Add extra SQL fragments to the query."""
self._not_support_combined_queries('extra')
assert not self.query.is_sliced, \
"Cannot change a query once a slice has been taken"
clone = self._chain()
clone.query.add_extra(select, select_params, where, params, tables, order_by)
return clone
def reverse(self):
"""Reverse the ordering of the QuerySet."""
if self.query.is_sliced:
raise TypeError('Cannot reverse a query once a slice has been taken.')
clone = self._chain()
clone.query.standard_ordering = not clone.query.standard_ordering
return clone
def defer(self, *fields):
"""
Defer the loading of data for certain fields until they are accessed.
Add the set of deferred fields to any existing set of deferred fields.
The only exception to this is if None is passed in as the only
parameter, in which case removal all deferrals.
"""
self._not_support_combined_queries('defer')
if self._fields is not None:
raise TypeError("Cannot call defer() after .values() or .values_list()")
clone = self._chain()
if fields == (None,):
clone.query.clear_deferred_loading()
else:
clone.query.add_deferred_loading(fields)
return clone
def only(self, *fields):
"""
Essentially, the opposite of defer(). Only the fields passed into this
method and that are not already specified as deferred are loaded
immediately when the queryset is evaluated.
"""
self._not_support_combined_queries('only')
if self._fields is not None:
raise TypeError("Cannot call only() after .values() or .values_list()")
if fields == (None,):
# Can only pass None to defer(), not only(), as the rest option.
# That won't stop people trying to do this, so let's be explicit.
raise TypeError("Cannot pass None as an argument to only().")
for field in fields:
field = field.split(LOOKUP_SEP, 1)[0]
if field in self.query._filtered_relations:
raise ValueError('only() is not supported with FilteredRelation.')
clone = self._chain()
clone.query.add_immediate_loading(fields)
return clone
def using(self, alias):
"""Select which database this QuerySet should execute against."""
clone = self._chain()
clone._db = alias
return clone
###################################
# PUBLIC INTROSPECTION ATTRIBUTES #
###################################
@property
def ordered(self):
"""
Return True if the QuerySet is ordered -- i.e. has an order_by()
clause or a default ordering on the model (or is empty).
"""
if isinstance(self, EmptyQuerySet):
return True
if self.query.extra_order_by or self.query.order_by:
return True
elif self.query.default_ordering and self.query.get_meta().ordering:
return True
else:
return False
@property
def db(self):
"""Return the database used if this query is executed now."""
if self._for_write:
return self._db or router.db_for_write(self.model, **self._hints)
return self._db or router.db_for_read(self.model, **self._hints)
###################
# PRIVATE METHODS #
###################
def _insert(self, objs, fields, return_id=False, raw=False, using=None, ignore_conflicts=False):
"""
Insert a new record for the given model. This provides an interface to
the InsertQuery class and is how Model.save() is implemented.
"""
self._for_write = True
if using is None:
using = self.db
query = sql.InsertQuery(self.model, ignore_conflicts=ignore_conflicts)
query.insert_values(fields, objs, raw=raw)
return query.get_compiler(using=using).execute_sql(return_id)
_insert.alters_data = True
_insert.queryset_only = False
def _batched_insert(self, objs, fields, batch_size, ignore_conflicts=False):
"""
Helper method for bulk_create() to insert objs one batch at a time.
"""
if ignore_conflicts and not connections[self.db].features.supports_ignore_conflicts:
raise NotSupportedError('This database backend does not support ignoring conflicts.')
ops = connections[self.db].ops
batch_size = (batch_size or max(ops.bulk_batch_size(fields, objs), 1))
inserted_ids = []
bulk_return = connections[self.db].features.can_return_rows_from_bulk_insert
for item in [objs[i:i + batch_size] for i in range(0, len(objs), batch_size)]:
if bulk_return and not ignore_conflicts:
inserted_id = self._insert(
item, fields=fields, using=self.db, return_id=True,
ignore_conflicts=ignore_conflicts,
)
if isinstance(inserted_id, list):
inserted_ids.extend(inserted_id)
else:
inserted_ids.append(inserted_id)
else:
self._insert(item, fields=fields, using=self.db, ignore_conflicts=ignore_conflicts)
return inserted_ids
def _chain(self, **kwargs):
"""
Return a copy of the current QuerySet that's ready for another
operation.
"""
obj = self._clone()
if obj._sticky_filter:
obj.query.filter_is_sticky = True
obj._sticky_filter = False
obj.__dict__.update(kwargs)
return obj
def _clone(self):
"""
Return a copy of the current QuerySet. A lightweight alternative
to deepcopy().
"""
c = self.__class__(model=self.model, query=self.query.chain(), using=self._db, hints=self._hints)
c._sticky_filter = self._sticky_filter
c._for_write = self._for_write
c._prefetch_related_lookups = self._prefetch_related_lookups[:]
c._known_related_objects = self._known_related_objects
c._iterable_class = self._iterable_class
c._fields = self._fields
return c
def _fetch_all(self):
if self._result_cache is None:
self._result_cache = list(self._iterable_class(self))
if self._prefetch_related_lookups and not self._prefetch_done:
self._prefetch_related_objects()
def _next_is_sticky(self):
"""
Indicate that the next filter call and the one following that should
be treated as a single filter. This is only important when it comes to
determining when to reuse tables for many-to-many filters. Required so
that we can filter naturally on the results of related managers.
This doesn't return a clone of the current QuerySet (it returns
"self"). The method is only used internally and should be immediately
followed by a filter() that does create a clone.
"""
self._sticky_filter = True
return self
def _merge_sanity_check(self, other):
"""Check that two QuerySet classes may be merged."""
if self._fields is not None and (
set(self.query.values_select) != set(other.query.values_select) or
set(self.query.extra_select) != set(other.query.extra_select) or
set(self.query.annotation_select) != set(other.query.annotation_select)):
raise TypeError(
"Merging '%s' classes must involve the same values in each case."
% self.__class__.__name__
)
def _merge_known_related_objects(self, other):
"""
Keep track of all known related objects from either QuerySet instance.
"""
for field, objects in other._known_related_objects.items():
self._known_related_objects.setdefault(field, {}).update(objects)
def resolve_expression(self, *args, **kwargs):
if self._fields and len(self._fields) > 1:
# values() queryset can only be used as nested queries
# if they are set up to select only a single field.
raise TypeError('Cannot use multi-field values as a filter value.')
query = self.query.resolve_expression(*args, **kwargs)
query._db = self._db
return query
resolve_expression.queryset_only = True
def _add_hints(self, **hints):
"""
Update hinting information for use by routers. Add new key/values or
overwrite existing key/values.
"""
self._hints.update(hints)
def _has_filters(self):
"""
Check if this QuerySet has any filtering going on. This isn't
equivalent with checking if all objects are present in results, for
example, qs[1:]._has_filters() -> False.
"""
return self.query.has_filters()
@staticmethod
def _validate_values_are_expressions(values, method_name):
invalid_args = sorted(str(arg) for arg in values if not hasattr(arg, 'resolve_expression'))
if invalid_args:
raise TypeError(
'QuerySet.%s() received non-expression(s): %s.' % (
method_name,
', '.join(invalid_args),
)
)
def _not_support_combined_queries(self, operation_name):
if self.query.combinator:
raise NotSupportedError(
'Calling QuerySet.%s() after %s() is not supported.'
% (operation_name, self.query.combinator)
)
class InstanceCheckMeta(type):
def __instancecheck__(self, instance):
return isinstance(instance, QuerySet) and instance.query.is_empty()
class EmptyQuerySet(metaclass=InstanceCheckMeta):
"""
Marker class to checking if a queryset is empty by .none():
isinstance(qs.none(), EmptyQuerySet) -> True
"""
def __init__(self, *args, **kwargs):
raise TypeError("EmptyQuerySet can't be instantiated")
class RawQuerySet:
"""
Provide an iterator which converts the results of raw SQL queries into
annotated model instances.
"""
def __init__(self, raw_query, model=None, query=None, params=None,
translations=None, using=None, hints=None):
self.raw_query = raw_query
self.model = model
self._db = using
self._hints = hints or {}
self.query = query or sql.RawQuery(sql=raw_query, using=self.db, params=params)
self.params = params or ()
self.translations = translations or {}
self._result_cache = None
self._prefetch_related_lookups = ()
self._prefetch_done = False
def resolve_model_init_order(self):
"""Resolve the init field names and value positions."""
converter = connections[self.db].introspection.identifier_converter
model_init_fields = [f for f in self.model._meta.fields if converter(f.column) in self.columns]
annotation_fields = [(column, pos) for pos, column in enumerate(self.columns)
if column not in self.model_fields]
model_init_order = [self.columns.index(converter(f.column)) for f in model_init_fields]
model_init_names = [f.attname for f in model_init_fields]
return model_init_names, model_init_order, annotation_fields
def prefetch_related(self, *lookups):
"""Same as QuerySet.prefetch_related()"""
clone = self._clone()
if lookups == (None,):
clone._prefetch_related_lookups = ()
else:
clone._prefetch_related_lookups = clone._prefetch_related_lookups + lookups
return clone
def _prefetch_related_objects(self):
prefetch_related_objects(self._result_cache, *self._prefetch_related_lookups)
self._prefetch_done = True
def _clone(self):
"""Same as QuerySet._clone()"""
c = self.__class__(
self.raw_query, model=self.model, query=self.query, params=self.params,
translations=self.translations, using=self._db, hints=self._hints
)
c._prefetch_related_lookups = self._prefetch_related_lookups[:]
return c
def _fetch_all(self):
if self._result_cache is None:
self._result_cache = list(self.iterator())
if self._prefetch_related_lookups and not self._prefetch_done:
self._prefetch_related_objects()
def __len__(self):
self._fetch_all()
return len(self._result_cache)
def __bool__(self):
self._fetch_all()
return bool(self._result_cache)
def __iter__(self):
self._fetch_all()
return iter(self._result_cache)
def iterator(self):
# Cache some things for performance reasons outside the loop.
db = self.db
compiler = connections[db].ops.compiler('SQLCompiler')(
self.query, connections[db], db
)
query = iter(self.query)
try:
model_init_names, model_init_pos, annotation_fields = self.resolve_model_init_order()
if self.model._meta.pk.attname not in model_init_names:
raise InvalidQuery('Raw query must include the primary key')
model_cls = self.model
fields = [self.model_fields.get(c) for c in self.columns]
converters = compiler.get_converters([
f.get_col(f.model._meta.db_table) if f else None for f in fields
])
if converters:
query = compiler.apply_converters(query, converters)
for values in query:
# Associate fields to values
model_init_values = [values[pos] for pos in model_init_pos]
instance = model_cls.from_db(db, model_init_names, model_init_values)
if annotation_fields:
for column, pos in annotation_fields:
setattr(instance, column, values[pos])
yield instance
finally:
# Done iterating the Query. If it has its own cursor, close it.
if hasattr(self.query, 'cursor') and self.query.cursor:
self.query.cursor.close()
def __repr__(self):
return "<%s: %s>" % (self.__class__.__name__, self.query)
def __getitem__(self, k):
return list(self)[k]
@property
def db(self):
"""Return the database used if this query is executed now."""
return self._db or router.db_for_read(self.model, **self._hints)
def using(self, alias):
"""Select the database this RawQuerySet should execute against."""
return RawQuerySet(
self.raw_query, model=self.model,
query=self.query.chain(using=alias),
params=self.params, translations=self.translations,
using=alias,
)
@cached_property
def columns(self):
"""
A list of model field names in the order they'll appear in the
query results.
"""
columns = self.query.get_columns()
# Adjust any column names which don't match field names
for (query_name, model_name) in self.translations.items():
# Ignore translations for nonexistent column names
try:
index = columns.index(query_name)
except ValueError:
pass
else:
columns[index] = model_name
return columns
@cached_property
def model_fields(self):
"""A dict mapping column names to model field names."""
converter = connections[self.db].introspection.identifier_converter
model_fields = {}
for field in self.model._meta.fields:
name, column = field.get_attname_column()
model_fields[converter(column)] = field
return model_fields
class Prefetch:
def __init__(self, lookup, queryset=None, to_attr=None):
# `prefetch_through` is the path we traverse to perform the prefetch.
self.prefetch_through = lookup
# `prefetch_to` is the path to the attribute that stores the result.
self.prefetch_to = lookup
if queryset is not None and not issubclass(queryset._iterable_class, ModelIterable):
raise ValueError('Prefetch querysets cannot use values().')
if to_attr:
self.prefetch_to = LOOKUP_SEP.join(lookup.split(LOOKUP_SEP)[:-1] + [to_attr])
self.queryset = queryset
self.to_attr = to_attr
def __getstate__(self):
obj_dict = self.__dict__.copy()
if self.queryset is not None:
# Prevent the QuerySet from being evaluated
obj_dict['queryset'] = self.queryset._chain(
_result_cache=[],
_prefetch_done=True,
)
return obj_dict
def add_prefix(self, prefix):
self.prefetch_through = prefix + LOOKUP_SEP + self.prefetch_through
self.prefetch_to = prefix + LOOKUP_SEP + self.prefetch_to
def get_current_prefetch_to(self, level):
return LOOKUP_SEP.join(self.prefetch_to.split(LOOKUP_SEP)[:level + 1])
def get_current_to_attr(self, level):
parts = self.prefetch_to.split(LOOKUP_SEP)
to_attr = parts[level]
as_attr = self.to_attr and level == len(parts) - 1
return to_attr, as_attr
def get_current_queryset(self, level):
if self.get_current_prefetch_to(level) == self.prefetch_to:
return self.queryset
return None
def __eq__(self, other):
return isinstance(other, Prefetch) and self.prefetch_to == other.prefetch_to
def __hash__(self):
return hash((self.__class__, self.prefetch_to))
def normalize_prefetch_lookups(lookups, prefix=None):
"""Normalize lookups into Prefetch objects."""
ret = []
for lookup in lookups:
if not isinstance(lookup, Prefetch):
lookup = Prefetch(lookup)
if prefix:
lookup.add_prefix(prefix)
ret.append(lookup)
return ret
def prefetch_related_objects(model_instances, *related_lookups):
"""
Populate prefetched object caches for a list of model instances based on
the lookups/Prefetch instances given.
"""
if not model_instances:
return # nothing to do
# We need to be able to dynamically add to the list of prefetch_related
# lookups that we look up (see below). So we need some book keeping to
# ensure we don't do duplicate work.
done_queries = {} # dictionary of things like 'foo__bar': [results]
auto_lookups = set() # we add to this as we go through.
followed_descriptors = set() # recursion protection
all_lookups = normalize_prefetch_lookups(reversed(related_lookups))
while all_lookups:
lookup = all_lookups.pop()
if lookup.prefetch_to in done_queries:
if lookup.queryset is not None:
raise ValueError("'%s' lookup was already seen with a different queryset. "
"You may need to adjust the ordering of your lookups." % lookup.prefetch_to)
continue
# Top level, the list of objects to decorate is the result cache
# from the primary QuerySet. It won't be for deeper levels.
obj_list = model_instances
through_attrs = lookup.prefetch_through.split(LOOKUP_SEP)
for level, through_attr in enumerate(through_attrs):
# Prepare main instances
if not obj_list:
break
prefetch_to = lookup.get_current_prefetch_to(level)
if prefetch_to in done_queries:
# Skip any prefetching, and any object preparation
obj_list = done_queries[prefetch_to]
continue
# Prepare objects:
good_objects = True
for obj in obj_list:
# Since prefetching can re-use instances, it is possible to have
# the same instance multiple times in obj_list, so obj might
# already be prepared.
if not hasattr(obj, '_prefetched_objects_cache'):
try:
obj._prefetched_objects_cache = {}
except (AttributeError, TypeError):
# Must be an immutable object from
# values_list(flat=True), for example (TypeError) or
# a QuerySet subclass that isn't returning Model
# instances (AttributeError), either in Django or a 3rd
# party. prefetch_related() doesn't make sense, so quit.
good_objects = False
break
if not good_objects:
break
# Descend down tree
# We assume that objects retrieved are homogeneous (which is the premise
# of prefetch_related), so what applies to first object applies to all.
first_obj = obj_list[0]
to_attr = lookup.get_current_to_attr(level)[0]
prefetcher, descriptor, attr_found, is_fetched = get_prefetcher(first_obj, through_attr, to_attr)
if not attr_found:
raise AttributeError("Cannot find '%s' on %s object, '%s' is an invalid "
"parameter to prefetch_related()" %
(through_attr, first_obj.__class__.__name__, lookup.prefetch_through))
if level == len(through_attrs) - 1 and prefetcher is None:
# Last one, this *must* resolve to something that supports
# prefetching, otherwise there is no point adding it and the
# developer asking for it has made a mistake.
raise ValueError("'%s' does not resolve to an item that supports "
"prefetching - this is an invalid parameter to "
"prefetch_related()." % lookup.prefetch_through)
if prefetcher is not None and not is_fetched:
obj_list, additional_lookups = prefetch_one_level(obj_list, prefetcher, lookup, level)
# We need to ensure we don't keep adding lookups from the
# same relationships to stop infinite recursion. So, if we
# are already on an automatically added lookup, don't add
# the new lookups from relationships we've seen already.
if not (prefetch_to in done_queries and lookup in auto_lookups and descriptor in followed_descriptors):
done_queries[prefetch_to] = obj_list
new_lookups = normalize_prefetch_lookups(reversed(additional_lookups), prefetch_to)
auto_lookups.update(new_lookups)
all_lookups.extend(new_lookups)
followed_descriptors.add(descriptor)
else:
# Either a singly related object that has already been fetched
# (e.g. via select_related), or hopefully some other property
# that doesn't support prefetching but needs to be traversed.
# We replace the current list of parent objects with the list
# of related objects, filtering out empty or missing values so
# that we can continue with nullable or reverse relations.
new_obj_list = []
for obj in obj_list:
if through_attr in getattr(obj, '_prefetched_objects_cache', ()):
# If related objects have been prefetched, use the
# cache rather than the object's through_attr.
new_obj = list(obj._prefetched_objects_cache.get(through_attr))
else:
try:
new_obj = getattr(obj, through_attr)
except exceptions.ObjectDoesNotExist:
continue
if new_obj is None:
continue
# We special-case `list` rather than something more generic
# like `Iterable` because we don't want to accidentally match
# user models that define __iter__.
if isinstance(new_obj, list):
new_obj_list.extend(new_obj)
else:
new_obj_list.append(new_obj)
obj_list = new_obj_list
def get_prefetcher(instance, through_attr, to_attr):
"""
For the attribute 'through_attr' on the given instance, find
an object that has a get_prefetch_queryset().
Return a 4 tuple containing:
(the object with get_prefetch_queryset (or None),
the descriptor object representing this relationship (or None),
a boolean that is False if the attribute was not found at all,
a boolean that is True if the attribute has already been fetched)
"""
prefetcher = None
is_fetched = False
# For singly related objects, we have to avoid getting the attribute
# from the object, as this will trigger the query. So we first try
# on the class, in order to get the descriptor object.
rel_obj_descriptor = getattr(instance.__class__, through_attr, None)
if rel_obj_descriptor is None:
attr_found = hasattr(instance, through_attr)
else:
attr_found = True
if rel_obj_descriptor:
# singly related object, descriptor object has the
# get_prefetch_queryset() method.
if hasattr(rel_obj_descriptor, 'get_prefetch_queryset'):
prefetcher = rel_obj_descriptor
if rel_obj_descriptor.is_cached(instance):
is_fetched = True
else:
# descriptor doesn't support prefetching, so we go ahead and get
# the attribute on the instance rather than the class to
# support many related managers
rel_obj = getattr(instance, through_attr)
if hasattr(rel_obj, 'get_prefetch_queryset'):
prefetcher = rel_obj
if through_attr != to_attr:
# Special case cached_property instances because hasattr
# triggers attribute computation and assignment.
if isinstance(getattr(instance.__class__, to_attr, None), cached_property):
is_fetched = to_attr in instance.__dict__
else:
is_fetched = hasattr(instance, to_attr)
else:
is_fetched = through_attr in instance._prefetched_objects_cache
return prefetcher, rel_obj_descriptor, attr_found, is_fetched
def prefetch_one_level(instances, prefetcher, lookup, level):
"""
Helper function for prefetch_related_objects().
Run prefetches on all instances using the prefetcher object,
assigning results to relevant caches in instance.
Return the prefetched objects along with any additional prefetches that
must be done due to prefetch_related lookups found from default managers.
"""
# prefetcher must have a method get_prefetch_queryset() which takes a list
# of instances, and returns a tuple:
# (queryset of instances of self.model that are related to passed in instances,
# callable that gets value to be matched for returned instances,
# callable that gets value to be matched for passed in instances,
# boolean that is True for singly related objects,
# cache or field name to assign to,
# boolean that is True when the previous argument is a cache name vs a field name).
# The 'values to be matched' must be hashable as they will be used
# in a dictionary.
rel_qs, rel_obj_attr, instance_attr, single, cache_name, is_descriptor = (
prefetcher.get_prefetch_queryset(instances, lookup.get_current_queryset(level)))
# We have to handle the possibility that the QuerySet we just got back
# contains some prefetch_related lookups. We don't want to trigger the
# prefetch_related functionality by evaluating the query. Rather, we need
# to merge in the prefetch_related lookups.
# Copy the lookups in case it is a Prefetch object which could be reused
# later (happens in nested prefetch_related).
additional_lookups = [
copy.copy(additional_lookup) for additional_lookup
in getattr(rel_qs, '_prefetch_related_lookups', ())
]
if additional_lookups:
# Don't need to clone because the manager should have given us a fresh
# instance, so we access an internal instead of using public interface
# for performance reasons.
rel_qs._prefetch_related_lookups = ()
all_related_objects = list(rel_qs)
rel_obj_cache = {}
for rel_obj in all_related_objects:
rel_attr_val = rel_obj_attr(rel_obj)
rel_obj_cache.setdefault(rel_attr_val, []).append(rel_obj)
to_attr, as_attr = lookup.get_current_to_attr(level)
# Make sure `to_attr` does not conflict with a field.
if as_attr and instances:
# We assume that objects retrieved are homogeneous (which is the premise
# of prefetch_related), so what applies to first object applies to all.
model = instances[0].__class__
try:
model._meta.get_field(to_attr)
except exceptions.FieldDoesNotExist:
pass
else:
msg = 'to_attr={} conflicts with a field on the {} model.'
raise ValueError(msg.format(to_attr, model.__name__))
# Whether or not we're prefetching the last part of the lookup.
leaf = len(lookup.prefetch_through.split(LOOKUP_SEP)) - 1 == level
for obj in instances:
instance_attr_val = instance_attr(obj)
vals = rel_obj_cache.get(instance_attr_val, [])
if single:
val = vals[0] if vals else None
if as_attr:
# A to_attr has been given for the prefetch.
setattr(obj, to_attr, val)
elif is_descriptor:
# cache_name points to a field name in obj.
# This field is a descriptor for a related object.
setattr(obj, cache_name, val)
else:
# No to_attr has been given for this prefetch operation and the
# cache_name does not point to a descriptor. Store the value of
# the field in the object's field cache.
obj._state.fields_cache[cache_name] = val
else:
if as_attr:
setattr(obj, to_attr, vals)
else:
manager = getattr(obj, to_attr)
if leaf and lookup.queryset is not None:
qs = manager._apply_rel_filters(lookup.queryset)
else:
qs = manager.get_queryset()
qs._result_cache = vals
# We don't want the individual qs doing prefetch_related now,
# since we have merged this into the current work.
qs._prefetch_done = True
obj._prefetched_objects_cache[cache_name] = qs
return all_related_objects, additional_lookups
class RelatedPopulator:
"""
RelatedPopulator is used for select_related() object instantiation.
The idea is that each select_related() model will be populated by a
different RelatedPopulator instance. The RelatedPopulator instances get
klass_info and select (computed in SQLCompiler) plus the used db as
input for initialization. That data is used to compute which columns
to use, how to instantiate the model, and how to populate the links
between the objects.
The actual creation of the objects is done in populate() method. This
method gets row and from_obj as input and populates the select_related()
model instance.
"""
def __init__(self, klass_info, select, db):
self.db = db
# Pre-compute needed attributes. The attributes are:
# - model_cls: the possibly deferred model class to instantiate
# - either:
# - cols_start, cols_end: usually the columns in the row are
# in the same order model_cls.__init__ expects them, so we
# can instantiate by model_cls(*row[cols_start:cols_end])
# - reorder_for_init: When select_related descends to a child
# class, then we want to reuse the already selected parent
# data. However, in this case the parent data isn't necessarily
# in the same order that Model.__init__ expects it to be, so
# we have to reorder the parent data. The reorder_for_init
# attribute contains a function used to reorder the field data
# in the order __init__ expects it.
# - pk_idx: the index of the primary key field in the reordered
# model data. Used to check if a related object exists at all.
# - init_list: the field attnames fetched from the database. For
# deferred models this isn't the same as all attnames of the
# model's fields.
# - related_populators: a list of RelatedPopulator instances if
# select_related() descends to related models from this model.
# - local_setter, remote_setter: Methods to set cached values on
# the object being populated and on the remote object. Usually
# these are Field.set_cached_value() methods.
select_fields = klass_info['select_fields']
from_parent = klass_info['from_parent']
if not from_parent:
self.cols_start = select_fields[0]
self.cols_end = select_fields[-1] + 1
self.init_list = [
f[0].target.attname for f in select[self.cols_start:self.cols_end]
]
self.reorder_for_init = None
else:
attname_indexes = {select[idx][0].target.attname: idx for idx in select_fields}
model_init_attnames = (f.attname for f in klass_info['model']._meta.concrete_fields)
self.init_list = [attname for attname in model_init_attnames if attname in attname_indexes]
self.reorder_for_init = operator.itemgetter(*[attname_indexes[attname] for attname in self.init_list])
self.model_cls = klass_info['model']
self.pk_idx = self.init_list.index(self.model_cls._meta.pk.attname)
self.related_populators = get_related_populators(klass_info, select, self.db)
self.local_setter = klass_info['local_setter']
self.remote_setter = klass_info['remote_setter']
def populate(self, row, from_obj):
if self.reorder_for_init:
obj_data = self.reorder_for_init(row)
else:
obj_data = row[self.cols_start:self.cols_end]
if obj_data[self.pk_idx] is None:
obj = None
else:
obj = self.model_cls.from_db(self.db, self.init_list, obj_data)
for rel_iter in self.related_populators:
rel_iter.populate(row, obj)
self.local_setter(from_obj, obj)
if obj is not None:
self.remote_setter(obj, from_obj)
def get_related_populators(klass_info, select, db):
iterators = []
related_klass_infos = klass_info.get('related_klass_infos', [])
for rel_klass_info in related_klass_infos:
rel_cls = RelatedPopulator(rel_klass_info, select, db)
iterators.append(rel_cls)
return iterators