With the introduction of multiple template engines these exceptions are no
longer DTL-specific. It makes more sense for them to be moved out of
DTL-related modules.
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.
This patch does three major things:
* Merges the django.template.debug implementation into django.template.base.
* Simplifies the debug implementation.
The old implementation copied debug information to every token and node.
The django_template_source attribute was set in multiple places, some
quite hacky, like django.template.defaulttags.ForNode.
Debug information is now annotated in two high-level places:
* Template.compile_nodelist for errors during parsing
* Node.render_annotated for errors during rendering
These were chosen because they have access to the template and context
as well as to all exceptions that happen during either the parse or
render phase.
* Moves the contextual line traceback information creation from
django.views.debug into django.template.base.Template. The debug views now
only deal with the presentation of the debug information.
This may cause some backwards compatibility issues, but may also
resolve security issues in third party projects that fail to heed warnings
in our documentation.
Thanks Markus Holtermann for help with tests and docs.
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.
This significantly improves performance on PyPy. The previous
implementation would generate a new class on every single request,
which is relatively slow.
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.
A deprecation path is required because the return type of
django.template.loader.get_template changed during the
multiple template engines refactor.
test_csrf_token_in_404 was incorrect: it tested the case when the
hardcoded template was rendered, and that template doesn't depend on the
CSRF token. This commit makes it test the case when a custom template is
rendered.
This is for consistency with Template.render.
It adds a little bit of knowledge about HTTP requests in
django.template.loader but I think consistency trumps purity.
This is the expected behavior, but given RequestContext's tortuous
implementation, a straightforward use of its API results in the
opposite.
This commits fixes a regression that must have happened at different
points in the multiple templates engine refactor for different features.
Piotr Jakimiak
Preston Timmons
Aymeric Augustin
Curtis Maloney
Tommy Beadle
Craig Oldford
Tim Heap
Caroline Simpson
Jon Walsh
Claude Paroz
Erik Romijn
Tim Graham
Corey Farwell
Aymeric Augustin
Alex Gaynor
Collin Anderson
David Robles
Ola Sitarska