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 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 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)(.*)') 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: if expr.contains_aggregate: continue # We can skip References to select clause, as all expressions in # the select clause are already part of the group by. if is_ref: continue 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 (sql, tuple(params)) not in seen: result.append((sql, params)) seen.add((sql, tuple(params))) 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) 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: - Which model to instantiate - 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: select_list = [] for c in self.get_default_columns(): select_list.append(select_idx) select.append((c, None)) select_idx += 1 klass_info = { 'model': self.query.model, 'select_fields': select_list, } # self.query.select is a special case. These columns never go to # any model. for col in self.query.select: select.append((col, None)) select_idx += 1 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 else: ordering = (self.query.order_by or self.query.get_meta().ordering or []) 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 = True if order == 'DESC' else False 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: if self.query.combinator: src = expr.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: expr.set_source_expressions([RawSQL('%d' % (idx + 1), ())]) break else: raise DatabaseError('ORDER BY term does not match any column in the result set.') resolved = expr.resolve_expression( self.query, allow_joins=True, reuse=None) 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) if (without_ordering, tuple(params)) in seen: continue seen.add((without_ordering, tuple(params))) 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: parts += (compiler.as_sql(),) 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 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 = 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: result.append(self.connection.ops.distinct_sql(distinct_fields)) 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.append(', '.join(out_cols)) result.append('FROM') result.extend(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_limits 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.') if not order_by: order_by = self.connection.ops.force_no_ordering() result.append('GROUP BY %s' % ', '.join(grouping)) if having: result.append('HAVING %s' % having) params.extend(h_params) 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_limits: if self.query.high_mark is not None: result.append('LIMIT %d' % (self.query.high_mark - self.query.low_mark)) if self.query.low_mark: if self.query.high_mark is None: val = self.connection.ops.no_limit_value() if val: result.append('LIMIT %d' % val) result.append('OFFSET %d' % self.query.low_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 select, _, alias in self.select: 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) AS subquery' % ( ', '.join(sub_selects), ' '.join(result), ), 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() if not start_alias: start_alias = 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(). """ qn = self.quote_name_unless_alias qn2 = self.connection.ops.quote_name result = [] opts = self.query.get_meta() for name in self.query.distinct_fields: parts = name.split(LOOKUP_SEP) _, targets, alias, joins, path, _ = 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: result.append("%s.%s" % (qn(alias), qn2(target.column))) return result 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 = True if order == 'DESC' else False pieces = name.split(LOOKUP_SEP) field, targets, alias, joins, path, opts = 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. if not already_seen: already_seen = 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(t.get_col(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. """ if not alias: alias = self.query.get_initial_alias() field, targets, opts, joins, path = self.query.setup_joins( pieces, opts, alias) alias = joins[-1] return field, targets, alias, joins, path, opts 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 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) related_klass_infos = [] if not restricted and self.query.max_depth 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: if isinstance(self.query.select_related, dict): requested = self.query.select_related restricted = True else: restricted = False 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, '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, '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) 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: path = parent_path + [klass_info['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', []): if related_klass_info['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): """Return an iterator over the results from executing this query.""" if results is None: results = self.execute_sql(MULTI) 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. """ if not result_type: result_type = 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: # Caller didn't specify a result_type, so just give them back 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 and 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. 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 class SQLInsertCompiler(SQLCompiler): def __init__(self, *args, **kwargs): self.return_id = False super().__init__(*args, **kwargs) 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") 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() result = ['INSERT INTO %s' % qn(opts.db_table)] has_fields = bool(self.query.fields) fields = self.query.fields if has_fields else [opts.pk] result.append('(%s)' % ', '.join(qn(f.column) for f in fields)) if has_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) 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]] 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)) return [(" ".join(result), tuple(p for ps in param_rows for p in ps))] else: 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 and cursor): 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") 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()