This also prevents state modifications from corrupting previous states.
Previously, when a model defining a relation was unregistered first,
clearing the cache would cause its related models' _meta to be cleared
and would result in the old models losing track of their relations.
This change:
* Makes the InclusionNode cache-safe by removing render-time side effects
to its nodelist.
* Ensures the render_context stack is properly scoped and reset by updating
the render call to use Template.render rather than Nodelist.render.
Rendering a Jinja template with self in the context threw an error.
While self is a reserved variable in Jinja, including self in the
context is not an error, so Django should respect that.
Made MigrationGraph forwards_plan() and backwards_plan() fall back to an
iterative approach in case the recursive approach exceeds the recursion
depth limit.
This introduces a force_append_slash argument for request.get_full_path()
which is used by RedirectFallbackMiddleware and CommonMiddleware when
handling redirects for settings.APPEND_SLASH.
This adds a new method, Apps.lazy_model_operation(), and a helper function,
lazy_related_operation(), which together supersede add_lazy_relation() and
make lazy model operations the responsibility of the App registry. This
system no longer uses the class_prepared signal.
Field.rel is now deprecated. Rel objects have now also remote_field
attribute. This means that self == self.remote_field.remote_field.
In addition, made the Rel objects a bit more like Field objects. Still,
marked ManyToManyFields as null=True.
Previously related fields didn't implement get_lookup, instead
related fields were treated specially. This commit removed some of
the special handling. In particular, related fields return Lookup
instances now, too.
Other notable changes in this commit is removal of support for
annotations in names_to_path().
If Field.choices is provided as an iterator, consume it in __init__ instead
of using itertools.tee (which ends up holding everything in memory
anyway). Fixes a bug where deconstruct() was consuming the iterator but
bypassing the call to `tee`.
When reversing, only outer parameters are used if captured parameters are
nested. Added tests to check the edge cases and documentation for the
behavior with an example to avoid it.
This reverts commit e0cc36f615.
The problem is the following:
* With non-gis backends, gis_tests sub apps are not discovered
(see runtests.py)
* Consequently, the app_label is inferred from the gis_tests
AppConfig
* Then models with same names in different sub apps conflict
because of same model_name/app_label pair.
Patryk Zawadzki
Jon Dufresne
Marten Kenbeek
Claude Paroz
Simon Charette
Baptiste Mispelon
Tim Graham
Preston Timmons
Tim Heap
Andriy Sokolovskiy
Markus Holtermann
Moritz Sichert
Caroline Simpson
Marco Fucci
Bas Peschier
Bas Peschier
Bertrand Bordage
Andrei Kulakov
Alex Hill
Raúl Cumplido
Anssi Kääriäinen
Michael Blatherwick
David Szotten
Varun Sharma
Berker Peksag
Alain IVARS
Josh Smeaton