This is preferrable to writing in the current working directory because
it eliminates the risk to leak unwanted files, which can result in very
weird test failures.
Also this will help if we ever try to run these tests concurrently.
Dropped the DJANGO_TEST_TEMP_DIR environment variable.
Before this change, proper removal depended on the developer passing
dir=os.environ['DJANGO_TEST_TMP_DIR'] to tempfile functions.
These cached properies were causing problems with pickling, and in
addition they were confusingly defined: field.rel.model._meta was
not the same as field.rel.opts.
Instead users should use field.rel.related_model._meta inplace of
field.rel.opts, and field.rel.to._meta in place of field.rel.to_opts.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
This allows using a UUIDField primary key along with the JSON session
serializer.
Thanks to Trac alias jamesbeith for the report and Simon Charette
for the initial patch.
This is a performance optimization and also fixes test errors with the
upcoming merge of contrib tests into tests/. The tests failed on MySQL
because the models with GeometryField were being checked but the
non-GIS MySQL backend didn't know how to handle them.
This message was introduced to help people figure out quickly when they
aren't running the tests against the copy of Django they're editing.
There's no reason to display it when verbosity is set to 0. It defaults
to 1.
Since 1.7 models need to declare an explicit app_label if they are not
in an application in INSTALLED_APPS or were imported before their
application was loaded.
The function no longer flushes zfile after each write as doing so can
lead to the gzipped streamed content being larger than the original
content; each flush adds a 5/6 byte type 0 block. Removing this means
buf.read() may return nothing, so only yield if that has some data.
Testing shows without the flush() the buffer is being flushed every 17k
or so and compresses the same as if it had been done as a whole string.
A change in Python test discovery [1] causes the old packages that raised
an error to be discovered; now we use a common directory that's
ignored during discovery. Refs #23763.
[1] http://bugs.python.org/issue7559
make_bytes() assumed that if the Content-Encoding header is set, then
everything had already been dealt with bytes-wise, but in a streaming
situation this was not necessarily the case.
make_bytes() is only called when necessary when working with a
StreamingHttpResponse iterable, but by that point the middleware has
added the Content-Encoding header and thus make_bytes() tried to call
bytes(value) (and dies). If it had been a normal HttpResponse,
make_bytes() would have been called when the content was set, well
before the middleware set the Content-Encoding header.
This commit removes the special casing when Content-Encoding is set,
allowing unicode strings to be encoded during the iteration before they
are e.g. gzipped. This behaviour was added a long time ago for #4969 and
it doesn't appear to be necessary any more, as everything is correctly
made into bytes at the appropriate places.
Two new tests, to show that supplying non-ASCII characters to a
StreamingHttpResponse works fine normally, and when passed through the
GZip middleware (the latter dies without the change to make_bytes()).
Removes the test with a nonsense Content-Encoding and Unicode input - if
this were to happen, it can still be encoded as bytes fine.
The method is mainly intended for use with UUIDField. For UUIDField we
want to call the field's default even when primary key value is
explicitly set to None to match the behavior of AutoField.
Thanks to Marc Tamlyn and Tim Graham for review.
Specifically in rendering shortcuts, template responses, and class-based
views that return template responses.
Also added a test for render_to_response(status=...) which was missing
from fdbfc980.
Thanks Tim and Carl for the review.
An explicit `__exact` lookup in the related managers filters
was interpreted as a reference to a foreign `exact` field.
Thanks to Trac alias zhiyajun11 for the report, Josh for the investigation,
Loïc for the test name and Tim for the review.
Tim Graham
László Károlyi
Preston Timmons
Claude Paroz
Jon Dufresne
Michael Angeletti
Stanislas Guerra
Nik Nyby
Aymeric Augustin
Aymeric Augustin
Anssi Kääriäinen
Marten Kenbeek
Loic Bistuer
foresmac
Marc Tamlyn
Shai Berger
Markus Holtermann
Andriy Sokolovskiy
Josh Smeaton
Simon Charette
Lukas Klein
Collin Anderson
Daniel Pyrathon
Aron Podrigal
Varun Sharma
Matthew Somerville
mlavin
Riccardo Magliocchetti
Josh Schneier
darkryder
Samuel Colvin