1784 lines
73 KiB
Python
1784 lines
73 KiB
Python
"""
|
|
The main QuerySet implementation. This provides the public API for the ORM.
|
|
"""
|
|
|
|
import copy
|
|
import operator
|
|
import warnings
|
|
from collections import OrderedDict, 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 F
|
|
from django.db.models.fields import AutoField
|
|
from django.db.models.functions import 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.utils import timezone
|
|
from django.utils.deprecation import RemovedInDjango30Warning
|
|
from django.utils.functional import cached_property, partition
|
|
from django.utils.version import get_version
|
|
|
|
# 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)
|
|
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, if there are any
|
|
if queryset._known_related_objects:
|
|
for field, rel_objs in queryset._known_related_objects.items():
|
|
# Avoid overwriting objects loaded e.g. by select_related
|
|
if field.is_cached(obj):
|
|
continue
|
|
pk = getattr(obj, field.get_attname())
|
|
try:
|
|
rel_obj = rel_objs[pk]
|
|
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)
|
|
|
|
field_names = list(query.values_select)
|
|
extra_names = list(query.extra_select)
|
|
annotation_names = list(query.annotation_select)
|
|
|
|
# extra(select=...) cols are always at the start of the row.
|
|
names = extra_names + field_names + annotation_names
|
|
|
|
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:
|
|
field_names = list(query.values_select)
|
|
extra_names = list(query.extra_select)
|
|
annotation_names = list(query.annotation_select)
|
|
|
|
# extra(select=...) cols are always at the start of the row.
|
|
names = extra_names + field_names + annotation_names
|
|
|
|
fields = list(queryset._fields) + [f for f in annotation_names 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)
|
|
return chain.from_iterable(compiler.results_iter(chunked_fetch=self.chunked_fetch, chunk_size=self.chunk_size))
|
|
|
|
|
|
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()
|
|
obj_dict = self.__dict__.copy()
|
|
obj_dict[DJANGO_VERSION_PICKLE_KEY] = get_version()
|
|
return obj_dict
|
|
|
|
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
|
|
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
|
|
combined = self._chain()
|
|
combined._merge_known_related_objects(other)
|
|
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 + tuple(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.filter(*args, **kwargs)
|
|
if self.query.can_filter() and not self.query.distinct_fields:
|
|
clone = clone.order_by()
|
|
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)
|
|
)
|
|
|
|
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):
|
|
"""
|
|
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_ids_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_ids_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)
|
|
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)
|
|
if connection.features.can_return_ids_from_bulk_insert:
|
|
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 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.
|
|
"""
|
|
lookup, params = self._extract_model_params(defaults, **kwargs)
|
|
# 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(**lookup), False
|
|
except self.model.DoesNotExist:
|
|
return self._create_object_from_params(lookup, 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 {}
|
|
lookup, params = self._extract_model_params(defaults, **kwargs)
|
|
self._for_write = True
|
|
with transaction.atomic(using=self.db):
|
|
try:
|
|
obj = self.select_for_update().get(**lookup)
|
|
except self.model.DoesNotExist:
|
|
obj, created = self._create_object_from_params(lookup, params)
|
|
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):
|
|
"""
|
|
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:
|
|
return self.get(**lookup), False
|
|
except self.model.DoesNotExist:
|
|
pass
|
|
raise e
|
|
|
|
def _extract_model_params(self, defaults, **kwargs):
|
|
"""
|
|
Prepare `lookup` (kwargs that are valid model attributes), `params`
|
|
(for creating a model instance) based on given kwargs; for use by
|
|
get_or_create() and update_or_create().
|
|
"""
|
|
defaults = defaults or {}
|
|
lookup = kwargs.copy()
|
|
for f in self.model._meta.fields:
|
|
if f.attname in lookup:
|
|
lookup[f.name] = lookup.pop(f.attname)
|
|
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 lookup, params
|
|
|
|
def _earliest_or_latest(self, *fields, field_name=None):
|
|
"""
|
|
Return the latest object, according to the model's
|
|
'get_latest_by' option or optional given field_name.
|
|
"""
|
|
if fields and field_name is not None:
|
|
raise ValueError('Cannot use both positional arguments and the field_name keyword argument.')
|
|
|
|
if field_name is not None:
|
|
warnings.warn(
|
|
'The field_name keyword argument to earliest() and latest() '
|
|
'is deprecated in favor of passing positional arguments.',
|
|
RemovedInDjango30Warning,
|
|
)
|
|
order_by = (field_name,)
|
|
elif 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 self.query.can_filter(), \
|
|
"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, field_name=None):
|
|
return self._earliest_or_latest(*fields, field_name=field_name)
|
|
|
|
def latest(self, *fields, field_name=None):
|
|
return self.reverse()._earliest_or_latest(*fields, field_name=field_name)
|
|
|
|
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 self.query.can_filter(), \
|
|
"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 self.query.can_filter(), \
|
|
"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 self.query.can_filter(), \
|
|
"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 = None
|
|
with transaction.atomic(using=self.db, savepoint=False):
|
|
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 self.query.can_filter(), \
|
|
"Cannot update a query once a slice has been taken."
|
|
query = self.query.chain(sql.UpdateQuery)
|
|
query.add_update_fields(values)
|
|
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
|
|
|
|
##################################################
|
|
# 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
|
|
return RawQuerySet(raw_query, model=self.model, params=params, translations=translations, using=using)
|
|
|
|
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", "day"), \
|
|
"'kind' must be one of 'year', 'month' 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", "day", "hour", "minute", "second"), \
|
|
"'kind' must be one of 'year', 'month', '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.
|
|
"""
|
|
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.
|
|
"""
|
|
return self._filter_or_exclude(True, *args, **kwargs)
|
|
|
|
def _filter_or_exclude(self, negate, *args, **kwargs):
|
|
if args or kwargs:
|
|
assert self.query.can_filter(), \
|
|
"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.
|
|
"""
|
|
|
|
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.
|
|
"""
|
|
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._validate_values_are_expressions(args + tuple(kwargs.values()), method_name='annotate')
|
|
annotations = OrderedDict() # To preserve ordering of args
|
|
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 = {f.name for f 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 self.query.can_filter(), \
|
|
"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 self.query.can_filter(), \
|
|
"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."""
|
|
assert self.query.can_filter(), \
|
|
"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 not self.query.can_filter():
|
|
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.
|
|
"""
|
|
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.
|
|
"""
|
|
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.
|
|
"""
|
|
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):
|
|
"""
|
|
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)
|
|
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):
|
|
"""
|
|
Helper method for bulk_create() to insert objs one batch at a time.
|
|
"""
|
|
ops = connections[self.db].ops
|
|
batch_size = (batch_size or max(ops.bulk_batch_size(fields, objs), 1))
|
|
inserted_ids = []
|
|
for item in [objs[i:i + batch_size] for i in range(0, len(objs), batch_size)]:
|
|
if connections[self.db].features.can_return_ids_from_bulk_insert:
|
|
inserted_id = self._insert(item, fields=fields, using=self.db, return_id=True)
|
|
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)
|
|
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),
|
|
)
|
|
)
|
|
|
|
|
|
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 {}
|
|
|
|
def resolve_model_init_order(self):
|
|
"""Resolve the init field names and value positions."""
|
|
converter = connections[self.db].introspection.column_name_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 __iter__(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.table_name_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:
|
|
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 (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
|