The introduction of the Expression.empty_aggregate_value interface
allows the compilation stage to enable the EmptyResultSet optimization
if all the aggregates expressions implement it.
This also removes unnecessary RegrCount/Count.convert_value() methods.
Disabling the empty result set aggregation optimization when it wasn't
appropriate prevented None returned for a Count aggregation value.
Thanks Nick Pope for the review.
Subquery deconstruction support required implementing complex and
expensive equality rules for sql.Query objects for little benefit as
the latter cannot themselves be made deconstructible to their reference
to model classes.
Making Expression @deconstructible and not BaseExpression allows
interested parties to conform to the "expression" API even if they are
not deconstructible as it's only a requirement for expressions allowed
in Model fields and meta options (e.g. constraints, indexes).
Thanks Phillip Cutter for the report.
This also fixes a performance regression in bbf141bcdc.
As mentioned in the pre-existing split_exclude() docstring EXISTS is
easier to optimize for query planers and circumvents the IN (NULL)
handling issue.
The latter is already optimized to limit the number of results, avoid
selecting unnecessary fields, and drop ordering if possible without
altering the semantic of the query.
This required implementing a limited form of dynamic dispatch to combine
expressions with numerical output. Refs #26355 should eventually provide
a better interface for that.
Previously unresolved Value() instances were only allowed to be
compiled if they weren't initialized with an output_field.
Given the usage of unresolved Value() instances is relatively common in
as_sql() overrides it's less controversial to add explicit support for
this previously undefined behavior now and revisit whether or not it
should be deprecated in the future.
Both backends order NULLs first on ascending ordering and last on
descending ordering which makes ORDER BY IS (NOT)? NULL wasteful when
asc(nulls_first) and desc(nulls_last) are used since it prevents indice
usage.
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.
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.
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>
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.
David Wobrock
Ian Foote
Simon Charette
Mariusz Felisiak
Tobias Bengfort
David Beitey
Hasan Ramezani
Hannes Ljungberg
Hannes Ljungberg
Nick Pope
Simon Charette
Sergey Fedoseev
Thodoris Sotiropoulos
Ryan Heard
Rohit
Simon Charette
ElizabethU
Matthew Schinckel
Andrew Brown