When we have a metaclass which returns something truthy (like a method) in its
__getattr__, we collected the class because pytest thought its __test__
attribute was set to True.
We can work around this to some degree by assuming __test__ will always be set
to an explicit True if that's what the user has intended, and if it's something
other than that, this is probably a mistake.
Fixes#1204.
When an object has a custom __getattr__ which always returns a non-int, we
tried to get compat_co_firstlineno from it and checked it was a integer, which
caused an exception if such a class is mistakenly collected.
If we still mistakenly collect such a class (which is likely to be something
other than a test), we now skip it with a warning (because it probably has an
__init__) instead of producing an error.
See #1204.
Fixes issue 331
previously to this change the collection code would issue a warning for
when ever it encountered a variable that looked like a test but wasn't a
function saying that it wouldn't collect it because it wasn't a function.
This fixes the logic so that if that warning is issued it really isn't
collected.
However previously special cases existed to support tests that were
created using functools.wraps and functools.partial. So the condition for
issuing that warning has been updated to take that in to account
Also try the old way of detecting functions just for proper integration
with mock.path in python 2.7 the get_real_func returned the unbound method
Works in a similar manner to `raises`, but for warnings instead
of exceptions. Also refactored `recwarn.py` so that all the
warning recording and checking use the same core code.
- integrate conftest into pytester plugin
- introduce runpytest() to either call runpytest_inline (default) or
runpytest_subprocess (python -m pytest)
- move testdir.inline_runsource1 to pdb tests
- strike some unneccessary methods.
- a new section "writing plugins" and some better pytester docs
--HG--
branch : testrefactor
instead of prepending. This better allows to run test modules
against installated versions of a package even if the package
under test has the same import root. In this example::
testing/__init__.py
testing/test_pkg_under_test.py
pkg_under_test/
the tests will preferrably run against the installed version
of pkg_under_test whereas before they would always pick
up the local version.
--HG--
branch : prefer_installed
CWD outside a test package pytest would get fixture discovery wrong.
Thanks to Wolfgang Schnerring for figuring out a reproducable example.
--HG--
branch : conftest-nodeid
This strips the line number, /@\d/, from the verbose output so it is
directly the node ID of the test. This in turn means no special logic
for accepting the line number as part of the node ID is needed when
parsing the command line.
The new "--tb=auto" option (default) will only display long tracebacks
for the first and last entry. You can get the old behaviour of printing
all entries as long entries with "--tb=long". Also short entries by
default are now printed very similarly to "--tb=native" ones.
Without this if a session scoped fixture fails it's setup it will
be re-tried each time it is requested. Especially in case of
skip or failure exceptions this can be undesirable, but caching
makes sense for all exceptions.
If the type is not checked then an incomprehensible error will occur
later. This enforces the type and raies the same exception/msg as
CPython does in that case.
Docstring unmodified, just re-justified for pep8 compat.
Replace the verbose per-test reporting format of `file:line test_name RESULT`
with the node ID of the test, i.e. `file@line::class::method[param] RESULT`.
This patch does not update the examples in the docs; @hpk42 has a script
to regenerate those.
--HG--
branch : issue504
The need for comparing two separately instantiated nodes seems to be historic
(related to an already-gone mode of pytest-xdist which would re-collect nodes)
and not actually needed anymore.
in a test invocation will have a corresponding FixtureDef instance.
also fixes issue246 (again).
simplify parametrized fixture teardown by making it work lazy:
during the setup of a parametrized fixture instance any previously
setup instance which was setup with a different param is torn down
before setting up the new one.
implemented by a slight internal refactoring and the introduction
of a new hook ``pytest_exception_interact`` hook.
- fix issue341: introduce new experimental hook for IDEs/terminals to
intercept debugging: ``pytest_exception_interact(node, call, report)``.
don't use autouse fixtures for now because it would cause a proliferation
and overhead for the execution of every test. Rather introduce a
node.addfinalizer(fin) to attach a finalizer to the respective node
and call it from node.setup() functions if the setup phase succeeded
(i.e. there is no setup function or it finished successfully)
When an autouse fixture in a plugin was encountered None was stored as nodeid
where it used to be ''. This broke the lookup of autouse fixtures later on.
This also adds another test for the normal fixture ordering which was slightly
wrong: a fixture without location was always added at the front of the fixture
list rather then at the end of the fixtures without location but before the
fixtures with location.
Conftests are plugins with a location attached to them while other
plugins do not have a location. When ordering fixturedefs those from
plugins without a location need to be listed first.
- When not specifying ids, let None and bools use their native string form (like str, int, float) rather than obfuscated form used for objects
- When specifying ids, explicitly raise a ValueError if a different number of ids are specified compared to the test cases
- Add tests for both these items.
address some comments by @hpk42 on 0b9d82e :
- move tests into their own class, rename
- add test showing metafunc.parametrize called in pytest_generate_tests rather than as decorator
- add test and fix single-argname case
- convert two loops into one in parametrize()
also
- renamed 'input' to 'n', since 'input' is a built-in
pytest-rerunfailures plugins) by re-initializing and removing
request/funcargs information in runtestprotocol() - which is a slightly
odd place to add funcarg-related functionality but it allows all
pytest_runtest_setup/teardown hooks to properly see a valid
request/funcarg content on test items.
When the conftest.py files are looked for intially they got loaded
starting from the subdir ending at the parent dir(s). Later on during
collection any conftest.py files are loaded starting from the parent
dir ending at the subdir. Due to how extending fixtures works the
latter is correct as otherwise the wrong fixture will be available.
So this changes the initial conftest loading to start at the root and
go towards the subdir.
This does also affect the order of other hooks, hence the order of the
reporting being different in testing/test_terminal.py.
Bruno Oliveira
Georgy Dyuldin
aselus-hub
Ronny Pfannschmidt
Florian Bruhin
Michael Birtwell
TomV
holger krekel (rather uses bitbucket/hpk42)
Michael Droettboom
holger krekel
Brianna Laugher
elizabeth
Markus Unterwaditzer
Eric Hunsberger
Jan Bednařík
Anatoly Bubenkov
Daniel Hahler
Floris Bruynooghe
Nicolas Delaby
Andy Freeland
schlamar
Chris Gilling
James Lan
Mathieu Agopian
Brianna Laugher
Ronny Pfannschmidt