There's no reason to assume that sys.path[0] is an appropriate location
for generating code. Specifically that doesn't work with extend_sys_path
which puts the additional directories at the end of sys.path.
In order to create a new migrations module, instead of using an
arbitrary entry from sys.path, import as much as possible from the path
to the module, then create missing submodules from there.
Without this change, the tests introduced in the following commit fail,
which seems sufficient to prevent regressions for such a refactoring.
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 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.
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.
Instead of naively reloading only directly related models (FK, O2O, M2M
relationship) the project state needs to reload their relations as well
as the model changes as well. Furthermore inheriting models (and super
models) need to be reloaded in order to keep inherited fields in sync.
To prevent endless recursive calls an iterative approach is taken.
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.
During direct assignment, evaluating the iterable before the transaction
is started avoids leaving the transaction dirty if an exception is raised.
This is slightly more wasteful but probably not enough to warrant a change
of behavior.
Thanks Anssi for the feedback. Refs #6707.
Instead of splitting filter clauses to where and having parts before
adding them to query.where or query.having, add all filter clauses to
query.where, and when compiling the query split the where to having and
where parts.
Tim Graham
László Károlyi
Claude Paroz
Aymeric Augustin
Anssi Kääriäinen
Marten Kenbeek
Michael Manfre
Michael Angeletti
Don Kirkby
Loic Bistuer
Marc Tamlyn
Shai Berger
Adam Chainz
Markus Holtermann
Aymeric Augustin
Josh Smeaton
Simon Charette
Daniel Pyrathon
Aron Podrigal
я котик пур-пур
Collin Anderson
Anssi Kääriäinen