django1/django/db/models/sql/compiler.py

1516 lines
68 KiB
Python

import collections
import functools
import re
import warnings
from itertools import chain
from django.core.exceptions import EmptyResultSet, FieldError
from django.db.models.constants import LOOKUP_SEP
from django.db.models.expressions import OrderBy, Random, RawSQL, Ref, Subquery
from django.db.models.query_utils import QueryWrapper, select_related_descend
from django.db.models.sql.constants import (
CURSOR, GET_ITERATOR_CHUNK_SIZE, MULTI, NO_RESULTS, ORDER_DIR, SINGLE,
)
from django.db.models.sql.query import Query, get_order_dir
from django.db.transaction import TransactionManagementError
from django.db.utils import DatabaseError, NotSupportedError
from django.utils.deprecation import (
RemovedInDjango30Warning, RemovedInDjango31Warning,
)
from django.utils.hashable import make_hashable
from django.utils.inspect import func_supports_parameter
FORCE = object()
class SQLCompiler:
def __init__(self, query, connection, using):
self.query = query
self.connection = connection
self.using = using
self.quote_cache = {'*': '*'}
# The select, klass_info, and annotations are needed by QuerySet.iterator()
# these are set as a side-effect of executing the query. Note that we calculate
# separately a list of extra select columns needed for grammatical correctness
# of the query, but these columns are not included in self.select.
self.select = None
self.annotation_col_map = None
self.klass_info = None
self.ordering_parts = re.compile(r'(.*)\s(ASC|DESC)(.*)')
self._meta_ordering = None
def setup_query(self):
if all(self.query.alias_refcount[a] == 0 for a in self.query.alias_map):
self.query.get_initial_alias()
self.select, self.klass_info, self.annotation_col_map = self.get_select()
self.col_count = len(self.select)
def pre_sql_setup(self):
"""
Do any necessary class setup immediately prior to producing SQL. This
is for things that can't necessarily be done in __init__ because we
might not have all the pieces in place at that time.
"""
self.setup_query()
order_by = self.get_order_by()
self.where, self.having = self.query.where.split_having()
extra_select = self.get_extra_select(order_by, self.select)
self.has_extra_select = bool(extra_select)
group_by = self.get_group_by(self.select + extra_select, order_by)
return extra_select, order_by, group_by
def get_group_by(self, select, order_by):
"""
Return a list of 2-tuples of form (sql, params).
The logic of what exactly the GROUP BY clause contains is hard
to describe in other words than "if it passes the test suite,
then it is correct".
"""
# Some examples:
# SomeModel.objects.annotate(Count('somecol'))
# GROUP BY: all fields of the model
#
# SomeModel.objects.values('name').annotate(Count('somecol'))
# GROUP BY: name
#
# SomeModel.objects.annotate(Count('somecol')).values('name')
# GROUP BY: all cols of the model
#
# SomeModel.objects.values('name', 'pk').annotate(Count('somecol')).values('pk')
# GROUP BY: name, pk
#
# SomeModel.objects.values('name').annotate(Count('somecol')).values('pk')
# GROUP BY: name, pk
#
# In fact, the self.query.group_by is the minimal set to GROUP BY. It
# can't be ever restricted to a smaller set, but additional columns in
# HAVING, ORDER BY, and SELECT clauses are added to it. Unfortunately
# the end result is that it is impossible to force the query to have
# a chosen GROUP BY clause - you can almost do this by using the form:
# .values(*wanted_cols).annotate(AnAggregate())
# but any later annotations, extra selects, values calls that
# refer some column outside of the wanted_cols, order_by, or even
# filter calls can alter the GROUP BY clause.
# The query.group_by is either None (no GROUP BY at all), True
# (group by select fields), or a list of expressions to be added
# to the group by.
if self.query.group_by is None:
return []
expressions = []
if self.query.group_by is not True:
# If the group by is set to a list (by .values() call most likely),
# then we need to add everything in it to the GROUP BY clause.
# Backwards compatibility hack for setting query.group_by. Remove
# when we have public API way of forcing the GROUP BY clause.
# Converts string references to expressions.
for expr in self.query.group_by:
if not hasattr(expr, 'as_sql'):
expressions.append(self.query.resolve_ref(expr))
else:
expressions.append(expr)
# Note that even if the group_by is set, it is only the minimal
# set to group by. So, we need to add cols in select, order_by, and
# having into the select in any case.
for expr, _, _ in select:
cols = expr.get_group_by_cols()
for col in cols:
expressions.append(col)
for expr, (sql, params, is_ref) in order_by:
# Skip References to the select clause, as all expressions in the
# select clause are already part of the group by.
if not expr.contains_aggregate and not is_ref:
expressions.extend(expr.get_source_expressions())
having_group_by = self.having.get_group_by_cols() if self.having else ()
for expr in having_group_by:
expressions.append(expr)
result = []
seen = set()
expressions = self.collapse_group_by(expressions, having_group_by)
for expr in expressions:
sql, params = self.compile(expr)
if isinstance(expr, Subquery) and not sql.startswith('('):
# Subquery expression from HAVING clause may not contain
# wrapping () because they could be removed when a subquery is
# the "rhs" in an expression (see Subquery._prepare()).
sql = '(%s)' % sql
params_hash = make_hashable(params)
if (sql, params_hash) not in seen:
result.append((sql, params))
seen.add((sql, params_hash))
return result
def collapse_group_by(self, expressions, having):
# If the DB can group by primary key, then group by the primary key of
# query's main model. Note that for PostgreSQL the GROUP BY clause must
# include the primary key of every table, but for MySQL it is enough to
# have the main table's primary key.
if self.connection.features.allows_group_by_pk:
# Determine if the main model's primary key is in the query.
pk = None
for expr in expressions:
# Is this a reference to query's base table primary key? If the
# expression isn't a Col-like, then skip the expression.
if (getattr(expr, 'target', None) == self.query.model._meta.pk and
getattr(expr, 'alias', None) == self.query.base_table):
pk = expr
break
# If the main model's primary key is in the query, group by that
# field, HAVING expressions, and expressions associated with tables
# that don't have a primary key included in the grouped columns.
if pk:
pk_aliases = {
expr.alias for expr in expressions
if hasattr(expr, 'target') and expr.target.primary_key
}
expressions = [pk] + [
expr for expr in expressions
if expr in having or (
getattr(expr, 'alias', None) is not None and expr.alias not in pk_aliases
)
]
elif self.connection.features.allows_group_by_selected_pks:
# Filter out all expressions associated with a table's primary key
# present in the grouped columns. This is done by identifying all
# tables that have their primary key included in the grouped
# columns and removing non-primary key columns referring to them.
# Unmanaged models are excluded because they could be representing
# database views on which the optimization might not be allowed.
pks = {
expr for expr in expressions
if hasattr(expr, 'target') and expr.target.primary_key and expr.target.model._meta.managed
}
aliases = {expr.alias for expr in pks}
expressions = [
expr for expr in expressions if expr in pks or getattr(expr, 'alias', None) not in aliases
]
return expressions
def get_select(self):
"""
Return three values:
- a list of 3-tuples of (expression, (sql, params), alias)
- a klass_info structure,
- a dictionary of annotations
The (sql, params) is what the expression will produce, and alias is the
"AS alias" for the column (possibly None).
The klass_info structure contains the following information:
- The base model of the query.
- Which columns for that model are present in the query (by
position of the select clause).
- related_klass_infos: [f, klass_info] to descent into
The annotations is a dictionary of {'attname': column position} values.
"""
select = []
klass_info = None
annotations = {}
select_idx = 0
for alias, (sql, params) in self.query.extra_select.items():
annotations[alias] = select_idx
select.append((RawSQL(sql, params), alias))
select_idx += 1
assert not (self.query.select and self.query.default_cols)
if self.query.default_cols:
cols = self.get_default_columns()
else:
# self.query.select is a special case. These columns never go to
# any model.
cols = self.query.select
if cols:
select_list = []
for col in cols:
select_list.append(select_idx)
select.append((col, None))
select_idx += 1
klass_info = {
'model': self.query.model,
'select_fields': select_list,
}
for alias, annotation in self.query.annotation_select.items():
annotations[alias] = select_idx
select.append((annotation, alias))
select_idx += 1
if self.query.select_related:
related_klass_infos = self.get_related_selections(select)
klass_info['related_klass_infos'] = related_klass_infos
def get_select_from_parent(klass_info):
for ki in klass_info['related_klass_infos']:
if ki['from_parent']:
ki['select_fields'] = (klass_info['select_fields'] +
ki['select_fields'])
get_select_from_parent(ki)
get_select_from_parent(klass_info)
ret = []
for col, alias in select:
try:
sql, params = self.compile(col, select_format=True)
except EmptyResultSet:
# Select a predicate that's always False.
sql, params = '0', ()
ret.append((col, (sql, params), alias))
return ret, klass_info, annotations
def get_order_by(self):
"""
Return a list of 2-tuples of form (expr, (sql, params, is_ref)) for the
ORDER BY clause.
The order_by clause can alter the select clause (for example it
can add aliases to clauses that do not yet have one, or it can
add totally new select clauses).
"""
if self.query.extra_order_by:
ordering = self.query.extra_order_by
elif not self.query.default_ordering:
ordering = self.query.order_by
elif self.query.order_by:
ordering = self.query.order_by
elif self.query.get_meta().ordering:
ordering = self.query.get_meta().ordering
self._meta_ordering = ordering
else:
ordering = []
if self.query.standard_ordering:
asc, desc = ORDER_DIR['ASC']
else:
asc, desc = ORDER_DIR['DESC']
order_by = []
for field in ordering:
if hasattr(field, 'resolve_expression'):
if not isinstance(field, OrderBy):
field = field.asc()
if not self.query.standard_ordering:
field.reverse_ordering()
order_by.append((field, False))
continue
if field == '?': # random
order_by.append((OrderBy(Random()), False))
continue
col, order = get_order_dir(field, asc)
descending = order == 'DESC'
if col in self.query.annotation_select:
# Reference to expression in SELECT clause
order_by.append((
OrderBy(Ref(col, self.query.annotation_select[col]), descending=descending),
True))
continue
if col in self.query.annotations:
# References to an expression which is masked out of the SELECT clause
order_by.append((
OrderBy(self.query.annotations[col], descending=descending),
False))
continue
if '.' in field:
# This came in through an extra(order_by=...) addition. Pass it
# on verbatim.
table, col = col.split('.', 1)
order_by.append((
OrderBy(
RawSQL('%s.%s' % (self.quote_name_unless_alias(table), col), []),
descending=descending
), False))
continue
if not self.query._extra or col not in self.query._extra:
# 'col' is of the form 'field' or 'field1__field2' or
# '-field1__field2__field', etc.
order_by.extend(self.find_ordering_name(
field, self.query.get_meta(), default_order=asc))
else:
if col not in self.query.extra_select:
order_by.append((
OrderBy(RawSQL(*self.query.extra[col]), descending=descending),
False))
else:
order_by.append((
OrderBy(Ref(col, RawSQL(*self.query.extra[col])), descending=descending),
True))
result = []
seen = set()
for expr, is_ref in order_by:
resolved = expr.resolve_expression(self.query, allow_joins=True, reuse=None)
if self.query.combinator:
src = resolved.get_source_expressions()[0]
# Relabel order by columns to raw numbers if this is a combined
# query; necessary since the columns can't be referenced by the
# fully qualified name and the simple column names may collide.
for idx, (sel_expr, _, col_alias) in enumerate(self.select):
if is_ref and col_alias == src.refs:
src = src.source
elif col_alias:
continue
if src == sel_expr:
resolved.set_source_expressions([RawSQL('%d' % (idx + 1), ())])
break
else:
raise DatabaseError('ORDER BY term does not match any column in the result set.')
sql, params = self.compile(resolved)
# Don't add the same column twice, but the order direction is
# not taken into account so we strip it. When this entire method
# is refactored into expressions, then we can check each part as we
# generate it.
without_ordering = self.ordering_parts.search(sql).group(1)
params_hash = make_hashable(params)
if (without_ordering, params_hash) in seen:
continue
seen.add((without_ordering, params_hash))
result.append((resolved, (sql, params, is_ref)))
return result
def get_extra_select(self, order_by, select):
extra_select = []
if self.query.distinct and not self.query.distinct_fields:
select_sql = [t[1] for t in select]
for expr, (sql, params, is_ref) in order_by:
without_ordering = self.ordering_parts.search(sql).group(1)
if not is_ref and (without_ordering, params) not in select_sql:
extra_select.append((expr, (without_ordering, params), None))
return extra_select
def quote_name_unless_alias(self, name):
"""
A wrapper around connection.ops.quote_name that doesn't quote aliases
for table names. This avoids problems with some SQL dialects that treat
quoted strings specially (e.g. PostgreSQL).
"""
if name in self.quote_cache:
return self.quote_cache[name]
if ((name in self.query.alias_map and name not in self.query.table_map) or
name in self.query.extra_select or (
name in self.query.external_aliases and name not in self.query.table_map)):
self.quote_cache[name] = name
return name
r = self.connection.ops.quote_name(name)
self.quote_cache[name] = r
return r
def compile(self, node, select_format=False):
vendor_impl = getattr(node, 'as_' + self.connection.vendor, None)
if vendor_impl:
sql, params = vendor_impl(self, self.connection)
else:
sql, params = node.as_sql(self, self.connection)
if select_format is FORCE or (select_format and not self.query.subquery):
return node.output_field.select_format(self, sql, params)
return sql, params
def get_combinator_sql(self, combinator, all):
features = self.connection.features
compilers = [
query.get_compiler(self.using, self.connection)
for query in self.query.combined_queries if not query.is_empty()
]
if not features.supports_slicing_ordering_in_compound:
for query, compiler in zip(self.query.combined_queries, compilers):
if query.low_mark or query.high_mark:
raise DatabaseError('LIMIT/OFFSET not allowed in subqueries of compound statements.')
if compiler.get_order_by():
raise DatabaseError('ORDER BY not allowed in subqueries of compound statements.')
parts = ()
for compiler in compilers:
try:
# If the columns list is limited, then all combined queries
# must have the same columns list. Set the selects defined on
# the query on all combined queries, if not already set.
if not compiler.query.values_select and self.query.values_select:
compiler.query.set_values((
*self.query.extra_select,
*self.query.values_select,
*self.query.annotation_select,
))
part_sql, part_args = compiler.as_sql()
if compiler.query.combinator:
# Wrap in a subquery if wrapping in parentheses isn't
# supported.
if not features.supports_parentheses_in_compound:
part_sql = 'SELECT * FROM ({})'.format(part_sql)
# Add parentheses when combining with compound query if not
# already added for all compound queries.
elif not features.supports_slicing_ordering_in_compound:
part_sql = '({})'.format(part_sql)
parts += ((part_sql, part_args),)
except EmptyResultSet:
# Omit the empty queryset with UNION and with DIFFERENCE if the
# first queryset is nonempty.
if combinator == 'union' or (combinator == 'difference' and parts):
continue
raise
if not parts:
raise EmptyResultSet
combinator_sql = self.connection.ops.set_operators[combinator]
if all and combinator == 'union':
combinator_sql += ' ALL'
braces = '({})' if features.supports_slicing_ordering_in_compound else '{}'
sql_parts, args_parts = zip(*((braces.format(sql), args) for sql, args in parts))
result = [' {} '.format(combinator_sql).join(sql_parts)]
params = []
for part in args_parts:
params.extend(part)
return result, params
def as_sql(self, with_limits=True, with_col_aliases=False):
"""
Create the SQL for this query. Return the SQL string and list of
parameters.
If 'with_limits' is False, any limit/offset information is not included
in the query.
"""
refcounts_before = self.query.alias_refcount.copy()
try:
extra_select, order_by, group_by = self.pre_sql_setup()
for_update_part = None
# Is a LIMIT/OFFSET clause needed?
with_limit_offset = with_limits and (self.query.high_mark is not None or self.query.low_mark)
combinator = self.query.combinator
features = self.connection.features
if combinator:
if not getattr(features, 'supports_select_{}'.format(combinator)):
raise NotSupportedError('{} is not supported on this database backend.'.format(combinator))
result, params = self.get_combinator_sql(combinator, self.query.combinator_all)
else:
distinct_fields, distinct_params = self.get_distinct()
# This must come after 'select', 'ordering', and 'distinct'
# (see docstring of get_from_clause() for details).
from_, f_params = self.get_from_clause()
where, w_params = self.compile(self.where) if self.where is not None else ("", [])
having, h_params = self.compile(self.having) if self.having is not None else ("", [])
result = ['SELECT']
params = []
if self.query.distinct:
distinct_result, distinct_params = self.connection.ops.distinct_sql(
distinct_fields,
distinct_params,
)
result += distinct_result
params += distinct_params
out_cols = []
col_idx = 1
for _, (s_sql, s_params), alias in self.select + extra_select:
if alias:
s_sql = '%s AS %s' % (s_sql, self.connection.ops.quote_name(alias))
elif with_col_aliases:
s_sql = '%s AS %s' % (s_sql, 'Col%d' % col_idx)
col_idx += 1
params.extend(s_params)
out_cols.append(s_sql)
result += [', '.join(out_cols), 'FROM', *from_]
params.extend(f_params)
if self.query.select_for_update and self.connection.features.has_select_for_update:
if self.connection.get_autocommit():
raise TransactionManagementError('select_for_update cannot be used outside of a transaction.')
if with_limit_offset and not self.connection.features.supports_select_for_update_with_limit:
raise NotSupportedError(
'LIMIT/OFFSET is not supported with '
'select_for_update on this database backend.'
)
nowait = self.query.select_for_update_nowait
skip_locked = self.query.select_for_update_skip_locked
of = self.query.select_for_update_of
# If it's a NOWAIT/SKIP LOCKED/OF query but the backend
# doesn't support it, raise NotSupportedError to prevent a
# possible deadlock.
if nowait and not self.connection.features.has_select_for_update_nowait:
raise NotSupportedError('NOWAIT is not supported on this database backend.')
elif skip_locked and not self.connection.features.has_select_for_update_skip_locked:
raise NotSupportedError('SKIP LOCKED is not supported on this database backend.')
elif of and not self.connection.features.has_select_for_update_of:
raise NotSupportedError('FOR UPDATE OF is not supported on this database backend.')
for_update_part = self.connection.ops.for_update_sql(
nowait=nowait,
skip_locked=skip_locked,
of=self.get_select_for_update_of_arguments(),
)
if for_update_part and self.connection.features.for_update_after_from:
result.append(for_update_part)
if where:
result.append('WHERE %s' % where)
params.extend(w_params)
grouping = []
for g_sql, g_params in group_by:
grouping.append(g_sql)
params.extend(g_params)
if grouping:
if distinct_fields:
raise NotImplementedError('annotate() + distinct(fields) is not implemented.')
order_by = order_by or self.connection.ops.force_no_ordering()
result.append('GROUP BY %s' % ', '.join(grouping))
if self._meta_ordering:
# When the deprecation ends, replace with:
# order_by = None
warnings.warn(
"%s QuerySet won't use Meta.ordering in Django 3.1. "
"Add .order_by(%s) to retain the current query." % (
self.query.model.__name__,
', '.join(repr(f) for f in self._meta_ordering),
),
RemovedInDjango31Warning,
stacklevel=4,
)
if having:
result.append('HAVING %s' % having)
params.extend(h_params)
if self.query.explain_query:
result.insert(0, self.connection.ops.explain_query_prefix(
self.query.explain_format,
**self.query.explain_options
))
if order_by:
ordering = []
for _, (o_sql, o_params, _) in order_by:
ordering.append(o_sql)
params.extend(o_params)
result.append('ORDER BY %s' % ', '.join(ordering))
if with_limit_offset:
result.append(self.connection.ops.limit_offset_sql(self.query.low_mark, self.query.high_mark))
if for_update_part and not self.connection.features.for_update_after_from:
result.append(for_update_part)
if self.query.subquery and extra_select:
# If the query is used as a subquery, the extra selects would
# result in more columns than the left-hand side expression is
# expecting. This can happen when a subquery uses a combination
# of order_by() and distinct(), forcing the ordering expressions
# to be selected as well. Wrap the query in another subquery
# to exclude extraneous selects.
sub_selects = []
sub_params = []
for index, (select, _, alias) in enumerate(self.select, start=1):
if not alias and with_col_aliases:
alias = 'col%d' % index
if alias:
sub_selects.append("%s.%s" % (
self.connection.ops.quote_name('subquery'),
self.connection.ops.quote_name(alias),
))
else:
select_clone = select.relabeled_clone({select.alias: 'subquery'})
subselect, subparams = select_clone.as_sql(self, self.connection)
sub_selects.append(subselect)
sub_params.extend(subparams)
return 'SELECT %s FROM (%s) subquery' % (
', '.join(sub_selects),
' '.join(result),
), tuple(sub_params + params)
return ' '.join(result), tuple(params)
finally:
# Finally do cleanup - get rid of the joins we created above.
self.query.reset_refcounts(refcounts_before)
def get_default_columns(self, start_alias=None, opts=None, from_parent=None):
"""
Compute the default columns for selecting every field in the base
model. Will sometimes be called to pull in related models (e.g. via
select_related), in which case "opts" and "start_alias" will be given
to provide a starting point for the traversal.
Return a list of strings, quoted appropriately for use in SQL
directly, as well as a set of aliases used in the select statement (if
'as_pairs' is True, return a list of (alias, col_name) pairs instead
of strings as the first component and None as the second component).
"""
result = []
if opts is None:
opts = self.query.get_meta()
only_load = self.deferred_to_columns()
start_alias = start_alias or self.query.get_initial_alias()
# The 'seen_models' is used to optimize checking the needed parent
# alias for a given field. This also includes None -> start_alias to
# be used by local fields.
seen_models = {None: start_alias}
for field in opts.concrete_fields:
model = field.model._meta.concrete_model
# A proxy model will have a different model and concrete_model. We
# will assign None if the field belongs to this model.
if model == opts.model:
model = None
if from_parent and model is not None and issubclass(
from_parent._meta.concrete_model, model._meta.concrete_model):
# Avoid loading data for already loaded parents.
# We end up here in the case select_related() resolution
# proceeds from parent model to child model. In that case the
# parent model data is already present in the SELECT clause,
# and we want to avoid reloading the same data again.
continue
if field.model in only_load and field.attname not in only_load[field.model]:
continue
alias = self.query.join_parent_model(opts, model, start_alias,
seen_models)
column = field.get_col(alias)
result.append(column)
return result
def get_distinct(self):
"""
Return a quoted list of fields to use in DISTINCT ON part of the query.
This method can alter the tables in the query, and thus it must be
called before get_from_clause().
"""
result = []
params = []
opts = self.query.get_meta()
for name in self.query.distinct_fields:
parts = name.split(LOOKUP_SEP)
_, targets, alias, joins, path, _, transform_function = self._setup_joins(parts, opts, None)
targets, alias, _ = self.query.trim_joins(targets, joins, path)
for target in targets:
if name in self.query.annotation_select:
result.append(name)
else:
r, p = self.compile(transform_function(target, alias))
result.append(r)
params.append(p)
return result, params
def find_ordering_name(self, name, opts, alias=None, default_order='ASC',
already_seen=None):
"""
Return the table alias (the name might be ambiguous, the alias will
not be) and column name for ordering by the given 'name' parameter.
The 'name' is of the form 'field1__field2__...__fieldN'.
"""
name, order = get_order_dir(name, default_order)
descending = order == 'DESC'
pieces = name.split(LOOKUP_SEP)
field, targets, alias, joins, path, opts, transform_function = self._setup_joins(pieces, opts, alias)
# If we get to this point and the field is a relation to another model,
# append the default ordering for that model unless the attribute name
# of the field is specified.
if field.is_relation and opts.ordering and getattr(field, 'attname', None) != name:
# Firstly, avoid infinite loops.
already_seen = already_seen or set()
join_tuple = tuple(getattr(self.query.alias_map[j], 'join_cols', None) for j in joins)
if join_tuple in already_seen:
raise FieldError('Infinite loop caused by ordering.')
already_seen.add(join_tuple)
results = []
for item in opts.ordering:
results.extend(self.find_ordering_name(item, opts, alias,
order, already_seen))
return results
targets, alias, _ = self.query.trim_joins(targets, joins, path)
return [(OrderBy(transform_function(t, alias), descending=descending), False) for t in targets]
def _setup_joins(self, pieces, opts, alias):
"""
Helper method for get_order_by() and get_distinct().
get_ordering() and get_distinct() must produce same target columns on
same input, as the prefixes of get_ordering() and get_distinct() must
match. Executing SQL where this is not true is an error.
"""
alias = alias or self.query.get_initial_alias()
field, targets, opts, joins, path, transform_function = self.query.setup_joins(pieces, opts, alias)
alias = joins[-1]
return field, targets, alias, joins, path, opts, transform_function
def get_from_clause(self):
"""
Return a list of strings that are joined together to go after the
"FROM" part of the query, as well as a list any extra parameters that
need to be included. Subclasses, can override this to create a
from-clause via a "select".
This should only be called after any SQL construction methods that
might change the tables that are needed. This means the select columns,
ordering, and distinct must be done first.
"""
result = []
params = []
for alias in tuple(self.query.alias_map):
if not self.query.alias_refcount[alias]:
continue
try:
from_clause = self.query.alias_map[alias]
except KeyError:
# Extra tables can end up in self.tables, but not in the
# alias_map if they aren't in a join. That's OK. We skip them.
continue
clause_sql, clause_params = self.compile(from_clause)
result.append(clause_sql)
params.extend(clause_params)
for t in self.query.extra_tables:
alias, _ = self.query.table_alias(t)
# Only add the alias if it's not already present (the table_alias()
# call increments the refcount, so an alias refcount of one means
# this is the only reference).
if alias not in self.query.alias_map or self.query.alias_refcount[alias] == 1:
result.append(', %s' % self.quote_name_unless_alias(alias))
return result, params
def get_related_selections(self, select, opts=None, root_alias=None, cur_depth=1,
requested=None, restricted=None):
"""
Fill in the information needed for a select_related query. The current
depth is measured as the number of connections away from the root model
(for example, cur_depth=1 means we are looking at models with direct
connections to the root model).
"""
def _get_field_choices():
direct_choices = (f.name for f in opts.fields if f.is_relation)
reverse_choices = (
f.field.related_query_name()
for f in opts.related_objects if f.field.unique
)
return chain(direct_choices, reverse_choices, self.query._filtered_relations)
related_klass_infos = []
if not restricted and cur_depth > self.query.max_depth:
# We've recursed far enough; bail out.
return related_klass_infos
if not opts:
opts = self.query.get_meta()
root_alias = self.query.get_initial_alias()
only_load = self.query.get_loaded_field_names()
# Setup for the case when only particular related fields should be
# included in the related selection.
fields_found = set()
if requested is None:
restricted = isinstance(self.query.select_related, dict)
if restricted:
requested = self.query.select_related
def get_related_klass_infos(klass_info, related_klass_infos):
klass_info['related_klass_infos'] = related_klass_infos
for f in opts.fields:
field_model = f.model._meta.concrete_model
fields_found.add(f.name)
if restricted:
next = requested.get(f.name, {})
if not f.is_relation:
# If a non-related field is used like a relation,
# or if a single non-relational field is given.
if next or f.name in requested:
raise FieldError(
"Non-relational field given in select_related: '%s'. "
"Choices are: %s" % (
f.name,
", ".join(_get_field_choices()) or '(none)',
)
)
else:
next = False
if not select_related_descend(f, restricted, requested,
only_load.get(field_model)):
continue
klass_info = {
'model': f.remote_field.model,
'field': f,
'reverse': False,
'local_setter': f.set_cached_value,
'remote_setter': f.remote_field.set_cached_value if f.unique else lambda x, y: None,
'from_parent': False,
}
related_klass_infos.append(klass_info)
select_fields = []
_, _, _, joins, _, _ = self.query.setup_joins(
[f.name], opts, root_alias)
alias = joins[-1]
columns = self.get_default_columns(start_alias=alias, opts=f.remote_field.model._meta)
for col in columns:
select_fields.append(len(select))
select.append((col, None))
klass_info['select_fields'] = select_fields
next_klass_infos = self.get_related_selections(
select, f.remote_field.model._meta, alias, cur_depth + 1, next, restricted)
get_related_klass_infos(klass_info, next_klass_infos)
if restricted:
related_fields = [
(o.field, o.related_model)
for o in opts.related_objects
if o.field.unique and not o.many_to_many
]
for f, model in related_fields:
if not select_related_descend(f, restricted, requested,
only_load.get(model), reverse=True):
continue
related_field_name = f.related_query_name()
fields_found.add(related_field_name)
join_info = self.query.setup_joins([related_field_name], opts, root_alias)
alias = join_info.joins[-1]
from_parent = issubclass(model, opts.model) and model is not opts.model
klass_info = {
'model': model,
'field': f,
'reverse': True,
'local_setter': f.remote_field.set_cached_value,
'remote_setter': f.set_cached_value,
'from_parent': from_parent,
}
related_klass_infos.append(klass_info)
select_fields = []
columns = self.get_default_columns(
start_alias=alias, opts=model._meta, from_parent=opts.model)
for col in columns:
select_fields.append(len(select))
select.append((col, None))
klass_info['select_fields'] = select_fields
next = requested.get(f.related_query_name(), {})
next_klass_infos = self.get_related_selections(
select, model._meta, alias, cur_depth + 1,
next, restricted)
get_related_klass_infos(klass_info, next_klass_infos)
for name in list(requested):
# Filtered relations work only on the topmost level.
if cur_depth > 1:
break
if name in self.query._filtered_relations:
fields_found.add(name)
f, _, join_opts, joins, _, _ = self.query.setup_joins([name], opts, root_alias)
model = join_opts.model
alias = joins[-1]
from_parent = issubclass(model, opts.model) and model is not opts.model
def local_setter(obj, from_obj):
f.remote_field.set_cached_value(from_obj, obj)
def remote_setter(obj, from_obj):
setattr(from_obj, name, obj)
klass_info = {
'model': model,
'field': f,
'reverse': True,
'local_setter': local_setter,
'remote_setter': remote_setter,
'from_parent': from_parent,
}
related_klass_infos.append(klass_info)
select_fields = []
columns = self.get_default_columns(
start_alias=alias, opts=model._meta,
from_parent=opts.model,
)
for col in columns:
select_fields.append(len(select))
select.append((col, None))
klass_info['select_fields'] = select_fields
next_requested = requested.get(name, {})
next_klass_infos = self.get_related_selections(
select, opts=model._meta, root_alias=alias,
cur_depth=cur_depth + 1, requested=next_requested,
restricted=restricted,
)
get_related_klass_infos(klass_info, next_klass_infos)
fields_not_found = set(requested).difference(fields_found)
if fields_not_found:
invalid_fields = ("'%s'" % s for s in fields_not_found)
raise FieldError(
'Invalid field name(s) given in select_related: %s. '
'Choices are: %s' % (
', '.join(invalid_fields),
', '.join(_get_field_choices()) or '(none)',
)
)
return related_klass_infos
def get_select_for_update_of_arguments(self):
"""
Return a quoted list of arguments for the SELECT FOR UPDATE OF part of
the query.
"""
def _get_field_choices():
"""Yield all allowed field paths in breadth-first search order."""
queue = collections.deque([(None, self.klass_info)])
while queue:
parent_path, klass_info = queue.popleft()
if parent_path is None:
path = []
yield 'self'
else:
field = klass_info['field']
if klass_info['reverse']:
field = field.remote_field
path = parent_path + [field.name]
yield LOOKUP_SEP.join(path)
queue.extend(
(path, klass_info)
for klass_info in klass_info.get('related_klass_infos', [])
)
result = []
invalid_names = []
for name in self.query.select_for_update_of:
parts = [] if name == 'self' else name.split(LOOKUP_SEP)
klass_info = self.klass_info
for part in parts:
for related_klass_info in klass_info.get('related_klass_infos', []):
field = related_klass_info['field']
if related_klass_info['reverse']:
field = field.remote_field
if field.name == part:
klass_info = related_klass_info
break
else:
klass_info = None
break
if klass_info is None:
invalid_names.append(name)
continue
select_index = klass_info['select_fields'][0]
col = self.select[select_index][0]
if self.connection.features.select_for_update_of_column:
result.append(self.compile(col)[0])
else:
result.append(self.quote_name_unless_alias(col.alias))
if invalid_names:
raise FieldError(
'Invalid field name(s) given in select_for_update(of=(...)): %s. '
'Only relational fields followed in the query are allowed. '
'Choices are: %s.' % (
', '.join(invalid_names),
', '.join(_get_field_choices()),
)
)
return result
def deferred_to_columns(self):
"""
Convert the self.deferred_loading data structure to mapping of table
names to sets of column names which are to be loaded. Return the
dictionary.
"""
columns = {}
self.query.deferred_to_data(columns, self.query.get_loaded_field_names_cb)
return columns
def get_converters(self, expressions):
converters = {}
for i, expression in enumerate(expressions):
if expression:
backend_converters = self.connection.ops.get_db_converters(expression)
field_converters = expression.get_db_converters(self.connection)
if backend_converters or field_converters:
convs = []
for conv in (backend_converters + field_converters):
if func_supports_parameter(conv, 'context'):
warnings.warn(
'Remove the context parameter from %s.%s(). Support for it '
'will be removed in Django 3.0.' % (
conv.__self__.__class__.__name__,
conv.__name__,
),
RemovedInDjango30Warning,
)
conv = functools.partial(conv, context={})
convs.append(conv)
converters[i] = (convs, expression)
return converters
def apply_converters(self, rows, converters):
connection = self.connection
converters = list(converters.items())
for row in map(list, rows):
for pos, (convs, expression) in converters:
value = row[pos]
for converter in convs:
value = converter(value, expression, connection)
row[pos] = value
yield row
def results_iter(self, results=None, tuple_expected=False, chunked_fetch=False,
chunk_size=GET_ITERATOR_CHUNK_SIZE):
"""Return an iterator over the results from executing this query."""
if results is None:
results = self.execute_sql(MULTI, chunked_fetch=chunked_fetch, chunk_size=chunk_size)
fields = [s[0] for s in self.select[0:self.col_count]]
converters = self.get_converters(fields)
rows = chain.from_iterable(results)
if converters:
rows = self.apply_converters(rows, converters)
if tuple_expected:
rows = map(tuple, rows)
return rows
def has_results(self):
"""
Backends (e.g. NoSQL) can override this in order to use optimized
versions of "query has any results."
"""
# This is always executed on a query clone, so we can modify self.query
self.query.add_extra({'a': 1}, None, None, None, None, None)
self.query.set_extra_mask(['a'])
return bool(self.execute_sql(SINGLE))
def execute_sql(self, result_type=MULTI, chunked_fetch=False, chunk_size=GET_ITERATOR_CHUNK_SIZE):
"""
Run the query against the database and return the result(s). The
return value is a single data item if result_type is SINGLE, or an
iterator over the results if the result_type is MULTI.
result_type is either MULTI (use fetchmany() to retrieve all rows),
SINGLE (only retrieve a single row), or None. In this last case, the
cursor is returned if any query is executed, since it's used by
subclasses such as InsertQuery). It's possible, however, that no query
is needed, as the filters describe an empty set. In that case, None is
returned, to avoid any unnecessary database interaction.
"""
result_type = result_type or NO_RESULTS
try:
sql, params = self.as_sql()
if not sql:
raise EmptyResultSet
except EmptyResultSet:
if result_type == MULTI:
return iter([])
else:
return
if chunked_fetch:
cursor = self.connection.chunked_cursor()
else:
cursor = self.connection.cursor()
try:
cursor.execute(sql, params)
except Exception:
# Might fail for server-side cursors (e.g. connection closed)
cursor.close()
raise
if result_type == CURSOR:
# Give the caller the cursor to process and close.
return cursor
if result_type == SINGLE:
try:
val = cursor.fetchone()
if val:
return val[0:self.col_count]
return val
finally:
# done with the cursor
cursor.close()
if result_type == NO_RESULTS:
cursor.close()
return
result = cursor_iter(
cursor, self.connection.features.empty_fetchmany_value,
self.col_count if self.has_extra_select else None,
chunk_size,
)
if not chunked_fetch or not self.connection.features.can_use_chunked_reads:
try:
# If we are using non-chunked reads, we return the same data
# structure as normally, but ensure it is all read into memory
# before going any further. Use chunked_fetch if requested,
# unless the database doesn't support it.
return list(result)
finally:
# done with the cursor
cursor.close()
return result
def as_subquery_condition(self, alias, columns, compiler):
qn = compiler.quote_name_unless_alias
qn2 = self.connection.ops.quote_name
for index, select_col in enumerate(self.query.select):
lhs_sql, lhs_params = self.compile(select_col)
rhs = '%s.%s' % (qn(alias), qn2(columns[index]))
self.query.where.add(
QueryWrapper('%s = %s' % (lhs_sql, rhs), lhs_params), 'AND')
sql, params = self.as_sql()
return 'EXISTS (%s)' % sql, params
def explain_query(self):
result = list(self.execute_sql())
# Some backends return 1 item tuples with strings, and others return
# tuples with integers and strings. Flatten them out into strings.
for row in result[0]:
if not isinstance(row, str):
yield ' '.join(str(c) for c in row)
else:
yield row
class SQLInsertCompiler(SQLCompiler):
return_id = False
def field_as_sql(self, field, val):
"""
Take a field and a value intended to be saved on that field, and
return placeholder SQL and accompanying params. Check for raw values,
expressions, and fields with get_placeholder() defined in that order.
When field is None, consider the value raw and use it as the
placeholder, with no corresponding parameters returned.
"""
if field is None:
# A field value of None means the value is raw.
sql, params = val, []
elif hasattr(val, 'as_sql'):
# This is an expression, let's compile it.
sql, params = self.compile(val)
elif hasattr(field, 'get_placeholder'):
# Some fields (e.g. geo fields) need special munging before
# they can be inserted.
sql, params = field.get_placeholder(val, self, self.connection), [val]
else:
# Return the common case for the placeholder
sql, params = '%s', [val]
# The following hook is only used by Oracle Spatial, which sometimes
# needs to yield 'NULL' and [] as its placeholder and params instead
# of '%s' and [None]. The 'NULL' placeholder is produced earlier by
# OracleOperations.get_geom_placeholder(). The following line removes
# the corresponding None parameter. See ticket #10888.
params = self.connection.ops.modify_insert_params(sql, params)
return sql, params
def prepare_value(self, field, value):
"""
Prepare a value to be used in a query by resolving it if it is an
expression and otherwise calling the field's get_db_prep_save().
"""
if hasattr(value, 'resolve_expression'):
value = value.resolve_expression(self.query, allow_joins=False, for_save=True)
# Don't allow values containing Col expressions. They refer to
# existing columns on a row, but in the case of insert the row
# doesn't exist yet.
if value.contains_column_references:
raise ValueError(
'Failed to insert expression "%s" on %s. F() expressions '
'can only be used to update, not to insert.' % (value, field)
)
if value.contains_aggregate:
raise FieldError("Aggregate functions are not allowed in this query")
if value.contains_over_clause:
raise FieldError('Window expressions are not allowed in this query.')
else:
value = field.get_db_prep_save(value, connection=self.connection)
return value
def pre_save_val(self, field, obj):
"""
Get the given field's value off the given obj. pre_save() is used for
things like auto_now on DateTimeField. Skip it if this is a raw query.
"""
if self.query.raw:
return getattr(obj, field.attname)
return field.pre_save(obj, add=True)
def assemble_as_sql(self, fields, value_rows):
"""
Take a sequence of N fields and a sequence of M rows of values, and
generate placeholder SQL and parameters for each field and value.
Return a pair containing:
* a sequence of M rows of N SQL placeholder strings, and
* a sequence of M rows of corresponding parameter values.
Each placeholder string may contain any number of '%s' interpolation
strings, and each parameter row will contain exactly as many params
as the total number of '%s's in the corresponding placeholder row.
"""
if not value_rows:
return [], []
# list of (sql, [params]) tuples for each object to be saved
# Shape: [n_objs][n_fields][2]
rows_of_fields_as_sql = (
(self.field_as_sql(field, v) for field, v in zip(fields, row))
for row in value_rows
)
# tuple like ([sqls], [[params]s]) for each object to be saved
# Shape: [n_objs][2][n_fields]
sql_and_param_pair_rows = (zip(*row) for row in rows_of_fields_as_sql)
# Extract separate lists for placeholders and params.
# Each of these has shape [n_objs][n_fields]
placeholder_rows, param_rows = zip(*sql_and_param_pair_rows)
# Params for each field are still lists, and need to be flattened.
param_rows = [[p for ps in row for p in ps] for row in param_rows]
return placeholder_rows, param_rows
def as_sql(self):
# We don't need quote_name_unless_alias() here, since these are all
# going to be column names (so we can avoid the extra overhead).
qn = self.connection.ops.quote_name
opts = self.query.get_meta()
insert_statement = self.connection.ops.insert_statement(ignore_conflicts=self.query.ignore_conflicts)
result = ['%s %s' % (insert_statement, qn(opts.db_table))]
fields = self.query.fields or [opts.pk]
result.append('(%s)' % ', '.join(qn(f.column) for f in fields))
if self.query.fields:
value_rows = [
[self.prepare_value(field, self.pre_save_val(field, obj)) for field in fields]
for obj in self.query.objs
]
else:
# An empty object.
value_rows = [[self.connection.ops.pk_default_value()] for _ in self.query.objs]
fields = [None]
# Currently the backends just accept values when generating bulk
# queries and generate their own placeholders. Doing that isn't
# necessary and it should be possible to use placeholders and
# expressions in bulk inserts too.
can_bulk = (not self.return_id and self.connection.features.has_bulk_insert)
placeholder_rows, param_rows = self.assemble_as_sql(fields, value_rows)
ignore_conflicts_suffix_sql = self.connection.ops.ignore_conflicts_suffix_sql(
ignore_conflicts=self.query.ignore_conflicts
)
if self.return_id and self.connection.features.can_return_id_from_insert:
if self.connection.features.can_return_ids_from_bulk_insert:
result.append(self.connection.ops.bulk_insert_sql(fields, placeholder_rows))
params = param_rows
else:
result.append("VALUES (%s)" % ", ".join(placeholder_rows[0]))
params = [param_rows[0]]
if ignore_conflicts_suffix_sql:
result.append(ignore_conflicts_suffix_sql)
col = "%s.%s" % (qn(opts.db_table), qn(opts.pk.column))
r_fmt, r_params = self.connection.ops.return_insert_id()
# Skip empty r_fmt to allow subclasses to customize behavior for
# 3rd party backends. Refs #19096.
if r_fmt:
result.append(r_fmt % col)
params += [r_params]
return [(" ".join(result), tuple(chain.from_iterable(params)))]
if can_bulk:
result.append(self.connection.ops.bulk_insert_sql(fields, placeholder_rows))
if ignore_conflicts_suffix_sql:
result.append(ignore_conflicts_suffix_sql)
return [(" ".join(result), tuple(p for ps in param_rows for p in ps))]
else:
if ignore_conflicts_suffix_sql:
result.append(ignore_conflicts_suffix_sql)
return [
(" ".join(result + ["VALUES (%s)" % ", ".join(p)]), vals)
for p, vals in zip(placeholder_rows, param_rows)
]
def execute_sql(self, return_id=False):
assert not (
return_id and len(self.query.objs) != 1 and
not self.connection.features.can_return_ids_from_bulk_insert
)
self.return_id = return_id
with self.connection.cursor() as cursor:
for sql, params in self.as_sql():
cursor.execute(sql, params)
if not return_id:
return
if self.connection.features.can_return_ids_from_bulk_insert and len(self.query.objs) > 1:
return self.connection.ops.fetch_returned_insert_ids(cursor)
if self.connection.features.can_return_id_from_insert:
assert len(self.query.objs) == 1
return self.connection.ops.fetch_returned_insert_id(cursor)
return self.connection.ops.last_insert_id(
cursor, self.query.get_meta().db_table, self.query.get_meta().pk.column
)
class SQLDeleteCompiler(SQLCompiler):
def as_sql(self):
"""
Create the SQL for this query. Return the SQL string and list of
parameters.
"""
assert len([t for t in self.query.alias_map if self.query.alias_refcount[t] > 0]) == 1, \
"Can only delete from one table at a time."
qn = self.quote_name_unless_alias
result = ['DELETE FROM %s' % qn(self.query.base_table)]
where, params = self.compile(self.query.where)
if where:
result.append('WHERE %s' % where)
return ' '.join(result), tuple(params)
class SQLUpdateCompiler(SQLCompiler):
def as_sql(self):
"""
Create the SQL for this query. Return the SQL string and list of
parameters.
"""
self.pre_sql_setup()
if not self.query.values:
return '', ()
qn = self.quote_name_unless_alias
values, update_params = [], []
for field, model, val in self.query.values:
if hasattr(val, 'resolve_expression'):
val = val.resolve_expression(self.query, allow_joins=False, for_save=True)
if val.contains_aggregate:
raise FieldError("Aggregate functions are not allowed in this query")
if val.contains_over_clause:
raise FieldError('Window expressions are not allowed in this query.')
elif hasattr(val, 'prepare_database_save'):
if field.remote_field:
val = field.get_db_prep_save(
val.prepare_database_save(field),
connection=self.connection,
)
else:
raise TypeError(
"Tried to update field %s with a model instance, %r. "
"Use a value compatible with %s."
% (field, val, field.__class__.__name__)
)
else:
val = field.get_db_prep_save(val, connection=self.connection)
# Getting the placeholder for the field.
if hasattr(field, 'get_placeholder'):
placeholder = field.get_placeholder(val, self, self.connection)
else:
placeholder = '%s'
name = field.column
if hasattr(val, 'as_sql'):
sql, params = self.compile(val)
values.append('%s = %s' % (qn(name), placeholder % sql))
update_params.extend(params)
elif val is not None:
values.append('%s = %s' % (qn(name), placeholder))
update_params.append(val)
else:
values.append('%s = NULL' % qn(name))
table = self.query.base_table
result = [
'UPDATE %s SET' % qn(table),
', '.join(values),
]
where, params = self.compile(self.query.where)
if where:
result.append('WHERE %s' % where)
return ' '.join(result), tuple(update_params + params)
def execute_sql(self, result_type):
"""
Execute the specified update. Return the number of rows affected by
the primary update query. The "primary update query" is the first
non-empty query that is executed. Row counts for any subsequent,
related queries are not available.
"""
cursor = super().execute_sql(result_type)
try:
rows = cursor.rowcount if cursor else 0
is_empty = cursor is None
finally:
if cursor:
cursor.close()
for query in self.query.get_related_updates():
aux_rows = query.get_compiler(self.using).execute_sql(result_type)
if is_empty and aux_rows:
rows = aux_rows
is_empty = False
return rows
def pre_sql_setup(self):
"""
If the update depends on results from other tables, munge the "where"
conditions to match the format required for (portable) SQL updates.
If multiple updates are required, pull out the id values to update at
this point so that they don't change as a result of the progressive
updates.
"""
refcounts_before = self.query.alias_refcount.copy()
# Ensure base table is in the query
self.query.get_initial_alias()
count = self.query.count_active_tables()
if not self.query.related_updates and count == 1:
return
query = self.query.chain(klass=Query)
query.select_related = False
query.clear_ordering(True)
query._extra = {}
query.select = []
query.add_fields([query.get_meta().pk.name])
super().pre_sql_setup()
must_pre_select = count > 1 and not self.connection.features.update_can_self_select
# Now we adjust the current query: reset the where clause and get rid
# of all the tables we don't need (since they're in the sub-select).
self.query.where = self.query.where_class()
if self.query.related_updates or must_pre_select:
# Either we're using the idents in multiple update queries (so
# don't want them to change), or the db backend doesn't support
# selecting from the updating table (e.g. MySQL).
idents = []
for rows in query.get_compiler(self.using).execute_sql(MULTI):
idents.extend(r[0] for r in rows)
self.query.add_filter(('pk__in', idents))
self.query.related_ids = idents
else:
# The fast path. Filters and updates in one query.
self.query.add_filter(('pk__in', query))
self.query.reset_refcounts(refcounts_before)
class SQLAggregateCompiler(SQLCompiler):
def as_sql(self):
"""
Create the SQL for this query. Return the SQL string and list of
parameters.
"""
sql, params = [], []
for annotation in self.query.annotation_select.values():
ann_sql, ann_params = self.compile(annotation, select_format=FORCE)
sql.append(ann_sql)
params.extend(ann_params)
self.col_count = len(self.query.annotation_select)
sql = ', '.join(sql)
params = tuple(params)
sql = 'SELECT %s FROM (%s) subquery' % (sql, self.query.subquery)
params = params + self.query.sub_params
return sql, params
def cursor_iter(cursor, sentinel, col_count, itersize):
"""
Yield blocks of rows from a cursor and ensure the cursor is closed when
done.
"""
try:
for rows in iter((lambda: cursor.fetchmany(itersize)), sentinel):
yield rows if col_count is None else [r[:col_count] for r in rows]
finally:
cursor.close()