This was an issue anymore on backends that allows conflicts to be
ignored (Refs #19544) as long the provided values were coercible to the
expected type. However on the remaining backends that don't support
this feature, namely Oracle, this could still result in an
IntegrityError.
By attempting to coerce the provided values to the expected types in
Python beforehand we allow the existing value set intersection in
ManyRelatedManager._get_missing_target_ids to prevent the problematic
insertion attempts.
Thanks Baptiste Mispelon for triaging this old ticket against the
current state of the master branch.
This prevent having to pass simple_col through multiple function calls
by defining whether or not references should be resolved with aliases
at the Query level.
MySQL & MariaDB support the standard IS NULL and IS NOT NULL so
the same workaround used for NULLS FIRST and NULLS LAST that is
used for SQLite < 3.30.0 can be used.
Thanks Simon Charette for the discussion.
Allows expected behavior when cast to str, also matching behaviour of
created instances with those fetched from the DB.
Thanks to Simon Charette, Nick Pope, and Shai Berger for reviews.
This required moving the entirety of DELETE SQL generation to the
compiler where it should have been in the first place and implementing
a specialized compiler on MySQL/MariaDB.
The MySQL compiler relies on the "DELETE table FROM table JOIN" syntax
for queries spanning over multiple tables.
Added internal interface to QuerySet that allows to defer next filter
call till .query is accessed. Used it to optimize prefetch_related().
Thanks Simon Charette for the review.
Reduced the number of queries required when performing cascade deletion
for a model referenced multiple time by another one by performing an
union of reference lookups.
Changed __eq__ to return NotImplemented instead of False if compared to
an object of the same type, as is recommended by the Python data model
reference. Now these models can be compared to ANY (or other objects
with __eq__ overwritten) without returning False automatically.
Use pre-existing select fields (and thereby GROUP BY fields) from
subquery if they were specified, instead of always defaulting to pk.
Thanks Aur Saraf for the report and Simon Charette for guidance.
SQLite doesn't repoint table aliases in partial index conditions on table
rename which breaks the documented table alteration procedure.
Thanks Pēteris Caune for the report.
These classes can serve as a base class for user enums, supporting
translatable human-readable names, or names automatically inferred
from the enum member name.
Additional properties make it easy to access the list of names, values
and display labels.
Thanks to the following for ideas and reviews:
Carlton Gibson, Fran Hrženjak, Ian Foote, Mariusz Felisiak, Shai Berger.
Co-authored-by: Shai Berger <shai@platonix.com>
Co-authored-by: Nick Pope <nick.pope@flightdataservices.com>
Co-authored-by: Mariusz Felisiak <felisiak.mariusz@gmail.com>
OuterRef right hand sides have to be nested, just like F rhs have to,
during the subquery pushdown split_exclude performs to ensure they are
resolved against the outer query aliases.
Expressions should never be prepared as other Lookup.get_prep_lookup
implementations hint at by returning early on the presence of the
resolve_expression attribute.
The previous solution was only handling lookups against related fields
pointing at AutoFields and would break for foreign keys to other fields.
It was also causing bidirectional coupling between model fields and
expressions which the method level import of OuterRef was a symptom of.
This allows using expressions that have an output_field that is a
BooleanField to be used directly in a queryset filters, or in the
When() clauses of a Case() expression.
Thanks Josh Smeaton, Tim Graham, Simon Charette, Mariusz Felisiak, and
Adam Johnson for reviews.
Co-Authored-By: NyanKiyoshi <hello@vanille.bid>
This reduces duplication by allowing AutoField, BigAutoField and
SmallAutoField to inherit from IntegerField, BigIntegerField and
SmallIntegerField respectively. Doing so also allows for enabling the
max_length warning check and minimum/maximum value validation for auto
fields, as well as providing a mixin that can be used for other possible
future auto field types such as a theoretical UUIDAutoField.
Made sql.Where resolve lhs of its child nodes. This is necessary to
allow filter lookups against nested subquery expressions to properly
resolve their OuterRefs to Cols.
Thanks Oskar Persson for the simplified test case.
Oracle requires the EXISTS expression to be wrapped in a CASE WHEN in
the following cases.
1. When part of a SELECT clause.
2. When part of a ORDER BY clause.
3. When compared against another expression in the WHERE clause.
This commit moves the systematic CASE WHEN wrapping of Exists.as_oracle
to contextual .select_format, Lookup.as_oracle, and OrderBy.as_oracle
methods in order to avoid unnecessary wrapping.
Expressions referring to different bound fields should not be
considered equal.
Thanks Julien Enselme for the detailed report.
Regression in bc7e288ca9.
Filters in annotations crashed when used with numerical-type
aggregations (i.e. Avg, StdDev, and Variance). This was caused as the
source expressions no not necessarily have an output_field (such as the
filter field), which lead to an AttributeError: 'WhereNode' object has
no attribute output_field.
Thanks to Chuan-Zheng Lee for the report.
Regression in c690afb873 and two following
commits.
Simon Charette
Daniel Izquierdo
Caio Ariede
Simon Charette
George Marshall
Hasan Ramezani
Nick Pope
Carlton Gibson
Mariusz Felisiak
Dan Moore
Alex Aktsipetrov
Ahmet Kucuk
André Ericson
sage
Simon Charette
Anatol Ulrich
ElizabethU
Mads Jensen
Johannes Hoppe
Ian Foote
James Timmins
Vojtech Bocek
Shai Berger
Matthew Schinckel
Andrew Brown
Claude Paroz
zeyneloz
Diederik van der Boor
Étienne Beaulé
Jon Dufresne
can
Nadège Michel
CruxBox
葛汉斌
Rob