Commit Graph

6499 Commits

Author SHA1 Message Date
Marten Kenbeek 78d43a5e10 Fixed #24366 -- Optimized traversal of large migration dependency graphs.
Switched from an adjancency list and uncached, iterative depth-first
search to a Node-based design with direct parent/child links and a
cached, recursive depth-first search. With this change, calculating
a migration plan for a large graph takes several seconds instead of
several hours.

Marked test `migrations.test_graph.GraphTests.test_dfs` as an expected
failure due to reaching the maximum recursion depth.
2015-02-23 12:38:53 +01:00
Aymeric Augustin c688460df6 Removed rmtree_errorhandler.
The stated reason for its introduction in d18d37ce no longer applies
since Django's code repository was switched from Subversion to git.

Furthermore it never had any effect because shutil.rmtree ignores its
onerror argument when ignore_errors is True.

The reason for its use in template management commands is unclear.
2015-02-22 23:09:42 +01:00
Aymeric Augustin 88a5f17d25 Fixed #24389 -- Isolated the CSRF view from the TEMPLATES setting.
Thanks uranusjr for the report and analysis.
2015-02-22 15:46:35 +01:00
Michael Angeletti ea3168dc6c Fixed #24376 -- added verbose_name arg to UUIDField 2015-02-21 13:27:49 -05:00
Aymeric Augustin 787dd6519a Removed obsolete reference to media directory. 2015-02-21 17:52:24 +01:00
Aymeric Augustin bd059e3f8c Removed workaround for SVN limitations.
In addition to simplifying the code, this reduces the number of writes.
2015-02-21 17:52:24 +01:00
Aymeric Augustin 2bb5b0e098 Avoided collecting admin static files in tests.
This makes the staticfiles tests 2.5 times faster.
2015-02-21 17:46:26 +01:00
Aymeric Augustin 1d9d39fa1c Removed TestServeAdminMedia.
It should have been removed when the ADMIN_MEDIA_PREFIX setting was deprecated.
2015-02-21 17:46:26 +01:00
Loic Bistuer fa5f936b48 Fixed allow_migrate signature in one of the tests.
Refs #24351.
2015-02-21 23:13:14 +07:00
foresmac 1d1d5d1c31 Fixed #24341 -- Added specific error messages to RangeField subclasses 2015-02-20 16:49:15 -05:00
Anssi Kääriäinen bad5f262bf Fixed #24328 -- cleaned up Options._get_fields() implementation 2015-02-20 13:00:12 -05:00
Loic Bistuer bed504d70b Fixed #24351, #24346 -- Changed the signature of allow_migrate().
The new signature enables better support for routing RunPython and
RunSQL operations, especially w.r.t. reusable and third-party apps.

This commit also takes advantage of the deprecation cycle for the old
signature to remove the backward incompatibility introduced in #22583;
RunPython and RunSQL won't call allow_migrate() when when the router
has the old signature.

Thanks Aymeric Augustin and Tim Graham for helping shape up the patch.

Refs 22583.
2015-02-20 21:34:09 +07:00
Marc Tamlyn c490e410af Fixed #24373 -- Added run_validators to ArrayField.
Thanks to DavidMuller for the report.
2015-02-20 11:51:46 +00:00
Marc Tamlyn 32d4db66b9 Update converters to take a consistent set of parameters.
As suggested by Anssi. This has the slightly strange side effect of
passing the expression to Expression.convert_value has the expression
passed back to it, but it allows more complex patterns of expressions.
2015-02-20 11:35:52 +00:00
Marc Tamlyn 4755f8fc25 Fixed #24343 -- Ensure db converters are used for foreign keys.
Joint effort between myself, Josh, Anssi and Shai.
2015-02-20 11:35:51 +00:00
Tim Graham c8074d62f8 Fixed typo in error message in the test. 2015-02-19 19:36:20 -05:00
Aymeric Augustin 1bfcc950ab Set context.template instead of context.engine while rendering.
This opens more possibilities, like accessing context.template.origin.

It also follows the chain of objects instead of following a shortcut.
2015-02-19 22:08:11 +01:00
Claude Paroz efb1f99f94 Fixed #20889 -- Prevented BadHeaderError when Python inserts newline
Workaround for http://bugs.python.org/issue20747.
In some corner cases, Python 2 inserts a newline in a header value
despite `maxlinelen` passed in Header constructor.
Thanks Tim Graham for the review.
2015-02-19 20:18:31 +01:00
Shai Berger ceadc94f09 Fixed #24307: Avoided redundant column nullability modifications on Oracle
Thanks Joris Benschop for the report, and Tim Graham for the tests.
2015-02-19 02:39:41 +02:00
Shai Berger f7d34fe741 Fixed #24362: Made test run each migration operation in its own schema editor
Thanks Tim Graham for pointing out the fix.
2015-02-18 22:47:15 +02:00
Marten Kenbeek 15dc8d1c9d Fixed #24291 - Fixed migration ModelState generation with unused swappable models
Swapped out models don't have a _default_manager unless they have
explicitly defined managers. ModelState.from_model() now accounts for
this case and uses an empty list for managers if no explicit managers
are defined and a model is swapped out.
2015-02-18 19:05:10 +01:00
Tim Graham b8d6cdbcc9 Refs #24324 -- Skipped fixtures_regress tests that fail on Python 2 on a non-ASCII path. 2015-02-18 07:25:36 -05:00
Tim Graham 307c0f299a Refs #24324 -- Fixed Python 2 test failures when path to Django source contains non-ASCII characters. 2015-02-17 19:03:03 -05:00
Tim Graham ad50b6c853 Fixed "environment can only contain strings" in model_regress test on Windows. 2015-02-17 13:54:18 -05:00
Tim Graham d316b43d0a Refs #24324 -- Fixed UnicodeDecodeError in model_regress test on non-ASCII path. 2015-02-17 07:32:48 -05:00
Tim Graham 8b39f33d78 Fixed #24290 -- Skipped postgres_tests if not running with PostgreSQL. 2015-02-17 06:34:13 -05:00
Tim Graham 3adc5f1ee6 Fixed #24335 -- Bumped required psycopg2 version to 2.4.5 (2.5 for contrib.postgres). 2015-02-16 18:07:27 -05:00
Tim Graham 664c038f2c Moved contrib.contenttypes tests out of contrib. 2015-02-16 17:45:38 -05:00
Markus Holtermann d538e37e1b Added tests for get_related_models_recursive 2015-02-16 19:31:52 +01:00
Markus Holtermann 273bc4b667 Refs #24282 -- Added failing test case for assigning models of wrong type to FK
Thanks Jeff Singer for the test case.
2015-02-16 19:31:51 +01:00
Markus Holtermann cc22b009e0 Refs #24264 -- Added failing test case for updating a FK when changing a PK
When the primary key column is altered, foreign keys of referencing
models must be aware of a possible data type change as well and thus
need to be re-rendered.

Thanks Tim Graham for the report.
2015-02-16 19:31:51 +01:00
Claude Paroz 58d0dd9260 Refs #24225 -- Added failing test case for removing a previously added field in migrations
When a related field is deleted, the related model must be updated. As
unchanged models are shared in migration states, the related model must
be re-rendered so that the change applies to a new copy of the related
model.

Thanks Henrik Heimbuerger for the report.
2015-02-16 19:31:51 +01:00
Marten Kenbeek f668bac9d2 Fixed #24345 -- Isolated sitemaps_tests from contenttypes_tests; refs #11505 2015-02-16 08:42:43 -05:00
Loic Bistuer c5a77721e2 Merged ManyRelatedObjectsDescriptor and ReverseManyRelatedObjectsDescriptor
and made all "many" related objects descriptors inherit from
ForeignRelatedObjectsDescriptor.
2015-02-16 20:40:04 +07:00
Aymeric Augustin 15b711b5ee Deprecated TEMPLATE_DEBUG setting. 2015-02-15 20:47:04 +01:00
Tim Graham e0b3926026 Isolated auth_tests from contenttypes_tests; refs #11505. 2015-02-14 22:04:48 -05:00
Michael Angeletti 49647bec6e Added missing return value to DurationField.prepare_value(); refs #24339. 2015-02-14 18:38:50 -05:00
Aymeric Augustin 76356d963c Fixed #24318 -- Set the transaction isolation level with psycopg >= 2.4.2. 2015-02-14 18:51:11 +01:00
Michael Angeletti 8a21d25033 Fixed #24339 -- Fixed crash with empty DurationField form field. 2015-02-14 07:37:18 -05:00
Claude Paroz 1791a7e75a Fixed #15779 -- Allowed 'add' primary key in admin edition
Thanks Marwan Alsabbagh for the report, and Simon Charette and
Tim Graham for the reviews.
2015-02-14 11:19:55 +01:00
Aymeric Augustin 47ee7b48ad Fixed #24338 -- Accepted Template wrapper in {% extends %}.
Explicitly checking for django.template.Template subclasses is
preferrable to duck-typing because both the django.template.Template and
django.template.backends.django.Template have a render() method.

Thanks spectras for the report.
2015-02-14 10:21:06 +01:00
Loic Bistuer 18c0aaa912 Fixed #24289 -- Reversed usage of Field.many_to_one and one_to_many.
Thanks Carl Meyer and Tim Graham for the reviews and to all involved
in the discussion.
2015-02-14 02:28:24 +07:00
Andriy Sokolovskiy 5c995dcfc2 Fixed #24320 - Used field.value_to_string() in serialization of foreign key.
This fixes serialization of a ForeignKey to a UUIDField as the
test indicates.
2015-02-13 12:37:23 -05:00
Tim Graham 002425fe39 Fixed #24315 -- Fixed auth.views.password_reset_confirm() with a UUID user. 2015-02-13 09:56:31 -05:00
Tim Graham fdf20093e0 Fixed #24334 -- Allowed admin password reset to work with non-digit custom user model primary key.
Thanks Loic for help and Simon for review.
2015-02-13 09:42:49 -05:00
Markus Holtermann f287bec583 Fixed #24184 -- Prevented automatic soft-apply of migrations
Previously Django only checked for the table name in CreateModel
operations in initial migrations and faked the migration automatically.
This led to various errors and unexpected behavior. The newly introduced
--fake-initial flag to the migrate command must be passed to get the
same behavior again. With this change Django will bail out in with a
"duplicate relation / table" error instead.

Thanks Carl Meyer and Tim Graham for the documentation update, report
and review.
2015-02-13 14:29:59 +01:00
Markus Holtermann b4e1090ab2 Removed explicit pointers to migration modules for contrib apps in runtest
Thanks Tim Graham for the patch
2015-02-13 14:29:45 +01:00
Markus Holtermann b06935a486 Refs #22962 -- Made test case use non-conflicting table names 2015-02-13 14:01:54 +01:00
Loic Bistuer 00a889167f Fixed #24295 -- Allowed ModelForm meta to specify form field classes.
Thanks Carl Meyer and Markus Holtermann for the reviews.
2015-02-13 19:13:05 +07:00
Tim Graham e8cf4f8abe Fixed #24332 -- Fixed contrib.sites create_default_site() when 'default' DATABASES is empty. 2015-02-13 07:01:28 -05:00