The query used a construct of qs.annotate().values().aggregate() where
the first annotate used an F-object reference and the values() and
aggregate() calls referenced that F-object.
Also made sure the inner query's select clause is as simple as possible,
and made sure .values().distinct().aggreate() works correctly.
Instead of splitting filter clauses to where and having parts before
adding them to query.where or query.having, add all filter clauses to
query.where, and when compiling the query split the where to having and
where parts.
Refactored compiler SELECT, GROUP BY and ORDER BY generation.
While there, also refactored select_related() implementation
(get_cached_row() and get_klass_info() are now gone!).
Made get_db_converters() method work on expressions instead of
internal_type. This allows the backend converters to target
specific expressions if need be.
Added query.context, this can be used to set per-query state.
Also changed the signature of database converters. They now accept
context as an argument.
Also removed Query.join_map. This structure was used to speed up join
reuse calculation. Initial benchmarking shows that this isn't actually
needed. If there are use cases where the removal has real-world
performance implications, it should be relatively straightforward to
reintroduce it as map {alias: [Join-like objects]}.
Aggregation over subquery produced syntactically incorrect queries in
some cases as Django didn't ensure that source expressions of the
aggregation were present in the subquery.
The .dates() queries were implemented by using custom Query, QuerySet,
and Compiler classes. Instead implement them by using expressions and
database converters APIs.
Added relabeled_clone() method to sql.Query to fix the problem. It
manifested itself in rare cases where at least double nested subquery's
filter condition might target non-existing alias.
Thanks to Trac alias ris for reporting the problem.
Complete rework of translating data values from database
Deprecation of SubfieldBase, removal of resolve_columns and
convert_values in favour of a more general converter based approach and
public API Field.from_db_value(). Now works seamlessly with aggregation,
.values() and raw queries.
Thanks to akaariai in particular for extensive advice and inspiration,
also to shaib, manfre and timograham for their reviews.
Ordering by reverse foreign key was broken by custom lookups patch
(commit 20bab2cf9d).
Thanks to everybody who helped solving this issue. Special thanks to
Trac alias takis for reporting this.
Allowed users to specify which lookups or transforms ("nested lookus")
are available for fields. The implementation is now class based.
Squashed commit of the following:
commit fa7a7195f1
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 18 10:53:24 2014 +0200
Added lookup registration API docs
commit eb1c8ce164
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Tue Jan 14 18:59:36 2014 +0200
Release notes and other minor docs changes
commit 11501c29c9
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Jan 12 20:53:03 2014 +0200
Forgot to add custom_lookups tests in prev commit
commit 83173b960e
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Jan 12 19:59:12 2014 +0200
Renamed Extract -> Transform
commit 3b18d9f3a1
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Jan 12 19:51:53 2014 +0200
Removed suggestion of temporary lookup registration from docs
commit 21d0c7631c
Merge: 2509006f2dc442
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Jan 12 09:38:23 2014 -0800
Merge pull request #2 from mjtamlyn/lookups_3
Reworked custom lookups docs.
commit f2dc4429a1
Author: Marc Tamlyn <marc.tamlyn@gmail.com>
Date: Sun Jan 12 13:15:05 2014 +0000
Reworked custom lookups docs.
Mostly just formatting and rewording, but also replaced the example
using ``YearExtract`` to use an example which is unlikely to ever be
possible directly in the ORM.
commit 2509006506
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Jan 12 13:19:13 2014 +0200
Removed unused import
commit 4fba5dfaa0
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 22:34:41 2014 +0200
Added docs to index
commit 6d53963f37
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 22:10:24 2014 +0200
Dead code removal
commit f9cc039007
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 19:00:43 2014 +0200
A new try for docs
commit 33aa18a6e3
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 14:57:12 2014 +0200
Renamed get_cols to get_group_by_cols
commit c7d5f8661b
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 14:45:53 2014 +0200
Altered query string customization for backends vendors
The new way is trying to call first method 'as_' + connection.vendor.
If that doesn't exist, then call as_sql().
Also altered how lookup registration is done. There is now
RegisterLookupMixin class that is used by Field, Extract and
sql.Aggregate. This allows one to register lookups for extracts and
aggregates in the same way lookup registration is done for fields.
commit 90e7004ec1
Merge: 66649fff7c2c0a
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 13:21:01 2014 +0200
Merge branch 'master' into lookups_3
commit 66649ff891
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Jan 11 13:16:01 2014 +0200
Some rewording in docs
commit 31b8faa627
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 29 15:52:29 2013 +0200
Cleanup based on review comments
commit 1016159f34
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 28 18:37:04 2013 +0200
Proof-of-concept fix for #16731
Implemented only for SQLite and PostgreSQL, and only for startswith
and istartswith lookups.
commit 193cd097ca
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 28 17:57:58 2013 +0200
Fixed#11722 -- iexact=F() produced invalid SQL
commit 08ed3c3b49
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 21 23:59:52 2013 +0200
Made Lookup and Extract available from django.db.models
commit b99c8d83c9
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 21 23:06:29 2013 +0200
Fixed review notes by Loic
commit 049eebc070
Merge: ed8fab7b80a835
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 21 22:53:10 2013 +0200
Merge branch 'master' into lookups_3
Conflicts:
django/db/models/fields/__init__.py
django/db/models/sql/compiler.py
django/db/models/sql/query.py
tests/null_queries/tests.py
commit ed8fab7fe8
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Dec 21 22:47:23 2013 +0200
Made Extracts aware of full lookup path
commit 27a57b7aed
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 1 21:10:11 2013 +0200
Removed debugger import
commit 074e0f5aca
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 1 21:02:16 2013 +0200
GIS lookup support added
commit 760e28e72b
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 1 20:04:31 2013 +0200
Removed usage of Constraint, used Lookup instead
commit eac4776684
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 1 02:22:30 2013 +0200
Minor cleanup of Lookup API
commit 2adf50428d
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sun Dec 1 02:14:19 2013 +0200
Added documentation, polished implementation
commit 32c04357a8
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Nov 30 23:10:15 2013 +0200
Avoid OrderedDict creation on lookup aggregate check
commit 7c8b3a32cc
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Sat Nov 30 23:04:34 2013 +0200
Implemented nested lookups
But there is no support of using lookups outside filtering yet.
commit 4d219d4cde
Author: Anssi Kääriäinen <akaariai@gmail.com>
Date: Wed Nov 27 22:07:30 2013 +0200
Initial implementation of custom lookups
This commit introduced a new class JoinPromoter that can be used to
abstract away join promotion problems for complex filter conditions.
Query._add_q() and Query.combine() now use the new class.
Also, added a lot of comments about why join promotion is done the way
it is.
Thanks to Tim Graham for original report and testing the changes, and
for Loic Bistuer for review.
select_related('foo').select_related('bar') is now equivalent to
select_related('foo', 'bar').
Also reworded docs to recommend select_related(*fields) over select_related()
The use of OrderedDict (even an empty one) was surprisingly slow. By
initializing OrderedDict only when needed it is possible to save
non-trivial amount of computing time (Model.save() is around 30% faster
for example).
This commit targetted sql.Query only, there are likely other places
which could use similar optimizations.
The bug was already fixed by 01b9c3d519,
so only tests added.
At the same time promote_joins()'s uncoditional flag is gone, it isn't
needed for anything any more.
In the combination of .values().aggregate() the aggregate_select_mask
didn't include the aggregates added. This resulted in bogus query.
Thanks to Trac alias debanshuk for report.
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.
The join used by select_related was incorrectly INNER when the query
had an ORed filter for nullable join that was trimmed away. Fixed this
by forcing the join type to LOUTER even when a join was trimmed away
in ORed queries.
The patch for #19385 caused a regression in certain generic relations
.exclude() filters if a subquery was needed. The fix contains a
refactoring to how Query.split_exclude() and Query.trim_start()
interact.
Thanks to Trac alias nferrari for the report.
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.
Before there was need to have both .relabel_aliases() and .clone() for
many structs. Now there is only relabeled_clone() for those structs
where alias is the only mutable attribute.
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.
The refactoring mainly concentrates on making sure the inner and outer
query agree about the split position. The split position is where the
multijoin happens, and thus the split position also determines the
columns used in the "WHERE col1 IN (SELECT col2 from ...)" condition.
This commit fixes a regression caused by #10790 and commit
69597e5bcc. The regression was caused
by wrong cols in the split position.
Previously it was possible to call clear_ordering without the
force_empty argument. The result was that the query was still ordered
by model's meta ordering if that was defined. By making the arg
mandatory it will be easier to spot possible errors caused by assuming
clear_ordering will remove all ordering.
Thanks to Dylan Klomparens for the suggestion. Refs #19720.
The original problem was that queryset cloning was really expensive
when filtering with F() clauses. The __deepcopy__ went too deep copying
_meta attributes of the models used. To fix this the use of
__deepcopy__ in qs cloning was removed.
This commit results in some speed improvements across the djangobench
benchmark suite. Most query_* tests are 20-30% faster, save() is 50%
faster and finally complex filtering situations can see 2x to order
of magnitude improvments.
Thanks to Suor, Alex and lrekucki for valuable feedback.
The guarantee that no queries will be made when accessing results is
done by new EmptyWhere class which is used for query.where and having.
Thanks to Simon Charette for reviewing and valuable suggestions.
The added promotion logic is based on promoting any joins used in only
some of the childs of an OR clause unless the join existed before the
OR clause addition.
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 trim argument was used by split_exclude() only to trim the last
join from the given lookup. It is cleaner to just trim the last part
from the lookup in split_exclude() directly so that there is no need
to burden add_filter() with the logic needed for only split_exclude().
F() expressions reuse joins like any lookup in a .filter() call -
reuse multijoins generated in the same .filter() call else generate
new joins. Also, lookups can now reuse joins generated by F().
This change is backwards incompatible, but it is required to prevent
dict randomization from generating different queries depending on
.filter() kwarg ordering. The new way is also more consistent in how
joins are reused.
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.
There was a bug introduced in #18676 which caused fast-path deletes
implemented as "DELETE WHERE pk IN <subquery>" to fail if the SELECT
clause contained additional stuff (for example extra() and annotate()).
Thanks to Trac alias pressureman for spotting this regression.
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.
The ORM generated a query with INNER JOIN instead of LEFT OUTER JOIN
in a somewhat complicated case. The main issue was that there was a
chain of nullable FK -> non-nullble FK, and the join promotion logic
didn't see the need to promote the non-nullable FK even if the
previous nullable FK was already promoted to LOUTER JOIN. This resulted
in a query like a LOUTER b INNER c, which incorrectly prunes results.
* Renamed smart_unicode to smart_text (but kept the old name under
Python 2 for backwards compatibility).
* Renamed smart_str to smart_bytes.
* Re-introduced smart_str as an alias for smart_text under Python 3
and smart_bytes under Python 2 (which is backwards compatible).
Thus smart_str always returns a str objects.
* Used the new smart_str in a few places where both Python 2 and 3
want a str.
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.
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.
Fixed#17957 -- when using Oracle and character fields, the fields
were set null = True to ease the handling of empty strings. This
caused problems when using multiple databases from different vendors,
or when the character field happened to be also a primary key.
The handling was changed so that NOT NULL is not emitted on Oracle
even if field.null = False, and field.null is not touched otherwise.
Thanks to bhuztez for the report, ramiro for triaging & comments,
ikelly for the patch and alex for reviewing.
QuerySet had previously some complex logic for dealing with nullable
fields in negated add_filter() calls. It seems the logic is leftover
from a time where the WhereNode wasn't as intelligent in handling
field__in=[] conditions.
Thanks to aaugustin for comments on the patch.
only consider some fields (PostgreSQL only).
For this, the ``distinct()`` QuerySet method now accepts an optional
list of model fields names and generates ``DISTINCT ON`` clauses on
these cases. Thanks Jeffrey Gelens and Anssi Kääriäinen for their work.
Fixes#6422.
git-svn-id: http://code.djangoproject.com/svn/django/trunk@17244 bcc190cf-cafb-0310-a4f2-bffc1f526a37
Anssi Kääriäinen
Marc Tamlyn
Tim Graham
Anssi Kääriäinen
Loic Bistuer
Josh Smeaton
Michał Modzelewski
Daniel Pyrathon
Piotr Pawlaczek
Jon Dufresne
Collin Anderson
Thomas Chaumeny
Gabe Jackson
Thomas Chaumeny
Matt Robenolt
Andrew Torpedov
Anubhav Joshi
Alex Hill
Lovas Bence
Jorge C. Leitão
Alex Gaynor
Claude Paroz
Rodolfo Carvalho
Martin Matusiak
Baptiste Mispelon
Denis Moskalets
Loic Bistuer
Christopher Medrela
coagulant
Alasdair Nicol
Simon Charette
Curtis Maloney
Florian Hahn
Aymeric Augustin
Mike Fogel
Tai Lee
Malcolm Tredinnick
Alex Gaynor
Adrian Holovaty
Carl Meyer
Julien Phalip
Ramiro Morales