In cases where the same connection (from model A to model B along the
same field) was needed multiple times in a select_related query, the
join setup code mistakenly reused an existing join.
If LEFT JOINs are required for correct results, then trimming the join
can lead to incorrect results. Consider case:
TBL A: ID | TBL B: ID A_ID
1 1 1
2
Now A.order_by('b__a') did use a join to B, and B's a_id column. This
was seen to contain the same value as A's id, and so the join was
trimmed. But this wasn't correct as the join is LEFT JOIN, and for row
A.id = 2 the B.a_id column is NULL.
There were a couple of places which used Query.join() directly. By
using setup_joins() in these places the code is more DRY, and in
addition there is no need to directly call field.get_joining_columns()
unless the field is the given join_field from get_path_info(). This
makes it easier to make sure a ForeignObject subclass generates joins
correctly in all cases.
Correctly calculate the ``aggregate_start`` offset from loaded fields,
if any are deferred, instead of ``self.query.select`` which includes all
fields on the model.
Also made some PEP 8 fixes.
The SubqueryConstraint defined relabeled_clone(), but that was never
called. Instead there is now clone() and relabel_aliases() methods for
SubqueryConstraint.
A related problem was that SubqueryConstraint didn't correctly use
quote_name_unless_alias() of the outer query. This resulted in failures
when running under PostgreSQL.
The sql/query.py add_q method did a lot of where/having tree hacking to
get complex queries to work correctly. The logic was refactored so that
it should be simpler to understand. The new logic should also produce
leaner WHERE conditions.
The changes cascade somewhat, as some other parts of Django (like
add_filter() and WhereNode) expect boolean trees in certain format or
they fail to work. So to fix the add_q() one must fix utils/tree.py,
some things in add_filter(), WhereNode and so on.
This commit also fixed add_filter to see negate clauses up the path.
A query like .exclude(Q(reversefk__in=a_list)) didn't work similarly to
.filter(~Q(reversefk__in=a_list)). The reason for this is that only
the immediate parent negate clauses were seen by add_filter, and thus a
tree like AND: (NOT AND: (AND: condition)) will not be handled
correctly, as there is one intermediary AND node in the tree. The
example tree is generated by .exclude(~Q(reversefk__in=a_list)).
Still, aggregation lost connectors in OR cases, and F() objects and
aggregates in same filter clause caused GROUP BY problems on some
databases.
Fixed#17600, fixed#13198, fixed#17025, fixed#17000, fixed#11293.
There were a couple of errors in ._dirty flag handling:
* It started as None, but was never reset to None.
* The _dirty flag was sometimes used to indicate if the connection
was inside transaction management, but this was not done
consistently. This also meant the flag had three separate values.
* The None value had a special meaning, causing for example inability
to commit() on new connection unless enter/leave tx management was
done.
* The _dirty was tracking "connection in transaction" state, but only
in managed transactions.
* Some tests never reset the transaction state of the used connection.
* And some additional less important changes.
This commit has some potential for regressions, but as the above list
shows, the current situation isn't perfect either.
There was a regression in case two models inherited the same parent,
and one contained a foreign key to other. When select_related travelled
the foreign key the other model reused the parent join made by the
first model. This was likely caused by Query.join_parent_model()
addition in commit 68985db482.
Thanks to Trac alias loic84 for report & tests.
The join promote=True was over-aggressive in select_related handling.
After that was removed, the only other user was query.combine(). That
use case is very easy to handle locally, so there is no more need for
the join(promote=True) flag.
Refs #19849.
Thanks Carl Meyer for the review.
Squashed commit of the following:
commit 4f290bdb60
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Wed Feb 13 21:21:30 2013 +0100
Used '0:00' instead of 'UTC' which doesn't always exist in Oracle.
Thanks Ian Kelly for the suggestion.
commit 01b6366f3c
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Wed Feb 13 13:38:43 2013 +0100
Made tzname a parameter of datetime_extract/trunc_sql.
This is required to work around a bug in Oracle.
commit 924a144ef8
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Wed Feb 13 14:47:44 2013 +0100
Added support for parameters in SELECT clauses.
commit b4351d2890
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Mon Feb 11 22:30:22 2013 +0100
Documented backwards incompatibilities in the two previous commits.
commit 91ef84713c
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Mon Feb 11 09:42:31 2013 +0100
Used QuerySet.datetimes for the admin's date_hierarchy.
commit 0d0de288a5
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Mon Feb 11 09:29:38 2013 +0100
Used QuerySet.datetimes in date-based generic views.
commit 9c0859ff7c
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:43:25 2013 +0100
Implemented QuerySet.datetimes on Oracle.
commit 68ab511a4f
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:43:14 2013 +0100
Implemented QuerySet.datetimes on MySQL.
commit 22d52681d3
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:42:29 2013 +0100
Implemented QuerySet.datetimes on SQLite.
commit f6800fd04c
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:43:03 2013 +0100
Implemented QuerySet.datetimes on PostgreSQL.
commit 0c829c23f4
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:41:08 2013 +0100
Added datetime-handling infrastructure in the ORM layers.
commit 104d82a777
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Mon Feb 11 10:05:55 2013 +0100
Updated null_queries tests to avoid clashing with the __second lookup.
commit c01bbb3235
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 23:07:41 2013 +0100
Updated tests of .dates().
Replaced .dates() by .datetimes() for DateTimeFields.
Replaced dates with datetimes in the expected output for DateFields.
commit 50fb7a5246
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 21:40:09 2013 +0100
Updated and added tests for QuerySet.datetimes.
commit a8451a5004
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 22:34:46 2013 +0100
Documented the new time lookups and updated the date lookups.
commit 29413eab2b
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date: Sun Feb 10 16:15:49 2013 +0100
Documented QuerySet.datetimes and updated QuerySet.dates.
The ORM didn't reuse joins for direct foreign key traversals when using
chained filters. For example:
qs.filter(fk__somefield=1).filter(fk__somefield=2))
produced two joins.
As a bonus, reverse onetoone filters can now reuse joins correctly
The regression was caused by the join() method refactor in commit
68847135bc
Thanks for Simon Charette for spotting some issues with the first draft
of the patch.
This is a rather large refactoring. The "lookup traversal" code was
splitted out from the setup_joins. There is now names_to_path() method
which does the lookup traveling, the actual work of setup_joins() is
calling names_to_path() and then adding the joins found into the query.
As a side effect it was possible to remove the "process_extra"
functionality used by genric relations. This never worked for left
joins. Now the extra restriction is appended directly to the join
condition instead of the where clause.
To generate the extra condition we need to have the join field
available in the compiler. This has the side-effect that we need more
ugly code in Query.__getstate__ and __setstate__ as Field objects
aren't pickleable.
The join trimming code got a big change - now we trim all direct joins
and never trim reverse joins. This also fixes the problem in #10790
which was join trimming in null filter cases.
The select_related code got confused when it needed to travel a
reverse relation to a model which had different parent than the
originally travelled relation.
Thanks to Trac aliases shauncutts for report and ungenio for original
patch (committed patch is somewhat modified version of that).
The problem is the same as in #10888 which was reintroduced when
bulk_insert was added. Thanks to Jani Tiainen for report, patch and
also testing the final patch on Oracle GIS.
The dupe avoidance logic was removed as it doesn't seem to do anything,
it is complicated, and it has nearly zero documentation.
The removal of dupe_avoidance allowed for refactoring of both the
implementation and signature of Query.join(). This refactoring cascades
again to some other parts. The most significant of them is the changes
in qs.combine(), and compiler.select_related_descent().
The Query.select and Query.select_fields were collapsed into one list
because the attributes had to be always in sync. Now that they are in
one attribute it is impossible to edit them out of sync.
Similar collapse was done for Query.related_select_cols and
Query.related_select_fields.
RETURNING is an extension of the SQL standard, which is not implemented
the same by all databases. Allow DatabaseOperations.return_insert_id to
return a None to allow for other 3rd party backends with a different
implementation.
Objects can be fast-path deleted if there are no signals, and there are
no further cascades. If fast-path is taken, the objects do not need to
be loaded into memory before deletion.
Thanks to Jeremy Dunck, Simon Charette and Alex Gaynor for reviewing
the patch.
When doing deeper than one level select_related() + only queries(), the
code introduced in b6c356b7bb errored
incorrectly.
Thanks to mrmachine for report & test case.
In an ideal world, nothing except django.db.models.query should have to
import stuff from django.models.sql.*. A few things were needing to get
hold of sql.constants.LOOKUP_SEP, so this commit moves it up to
django.db.models.constants.LOOKUP_SEP.
There are still a couple of places (admin) poking into sql.* to get
QUERY_TERMS, which is unfortunate, but a slightly different issue and
harder to adjust.
The joins for nested nullable foreign keys were often created as INNER
when they should have been OUTER joins. The reason was that only the
first join in the chain was promoted correctly. There were also issues
with select_related etc.
The basic structure for this problem was:
A -[nullable]-> B -[nonnull]-> C
And the basic problem was that the A->B join was correctly LOUTER,
the B->C join not.
The major change taken in this patch is that now if we promote a join
A->B, we will automatically promote joins B->X for all X in the query.
Also, we now make sure there aren't ever join chains like:
a LOUTER b INNER c
If the a -> b needs to be LOUTER, then the INNER at the end of the
chain will cancel the LOUTER join and we have a broken query.
Sebastian reported this problem and did also major portions of the
patch.
This commit tackles a couple of issues. First, in certain cases there
were some mixups if field.attname or field.name should be deferred.
Field.attname is now always used.
Another issue tackled is a case where field is both deferred by
.only(), and selected by select_related. This case is now an error.
A lot of thanks to koniiiik (Michal Petrucha) for the patch, and
to Andrei Antoukh for review.
When order_by causes new joins to be added to the query, the joins must
be LEFT OUTER joins for nullable relations, otherwise the order_by
could cause the results to be altered. This commit fixes the logic to
only promote new joins, previously all joins in the order_by lookup
path were promoted.
Thanks to Bruno Desthuilliers for spotting this corner case.
Databases with update_can_self_select = False (MySQL for example)
generated non-necessary queries when saving a multitable inherited
model, and when the save resulted in update.
Fixed#18248 -- proxy models were added to included_inherited_models
in sql.query.Query. The variable is meant to be used for multitable
inheritance only. This mistake caused problems in situations where
proxy model's query was reused.
Simon Charette
Tim Graham
Anssi Kääriäinen
Alex Gaynor
Florian Hahn
Tai Lee
Aymeric Augustin
Mike Fogel
Tobias McNulty
Luke Plant
Michael Manfre
Malcolm Tredinnick
Alex Gaynor
Claude Paroz
Adrian Holovaty