For decorated functions, the lineno of the FunctionDef AST node points
to the `def` line, not to the first decorator line. On the other hand,
in code objects, the `co_firstlineno` points to the first decorator
line.
Assertion rewriting inserts some imports to code it rewrites. The
imports are inserted at the lineno of the first statement in the AST. In
turn, the code object compiled from the rewritten AST uses the lineno of
the first statement (which is the first inserted import).
This means that given a module like this,
```py
@foo
@bar
def baz(): pass
```
the lineno of the code object without assertion rewriting
(`--assertion=plain`) is 1, but with assertion rewriting it is 3.
And *this* causes some issues for the exception repr when e.g. the
decorator line is invalid and raises during collection. The code becomes
confused and crashes with
INTERNALERROR> File "_pytest/_code/code.py", line 638, in get_source
INTERNALERROR> lines.append(space_prefix + source.lines[line_index].strip())
INTERNALERROR> IndexError: list index out of range
Fix it by special casing decorators. Maybe there are other cases like
this but off hand I can't think of another Python construct where the
lineno of the item would be after its first line, and this is the only
such issue we have had reported.
Warnings are a central part of Python, so much that Python itself has
command-line and environtment variables to handle warnings.
By moving the concept of warning handling into Config, it becomes natural to
filter warnings issued as early as possible, even before the "_pytest.warnings"
plugin is given a chance to spring into action. This also avoids the weird
coupling between config and the warnings plugin that was required before.
Fix#6681Fix#2891Fix#7620Fix#7626Close#7649
Co-authored-by: Ran Benita <ran@unusedvar.com>
Inline `_makeitem()` so that `self.ihook` (which is moderately
expensive) can be called only once.
Note: the removed test "test_makeitem_non_underscore" comes from an old
behavior of skipping names that start with `_` which has since been
generalized, making the test no longer relevant.
When a Python object (module/class/instance) is collected, for each name
in `obj.__dict__` (and up its MRO) the pytest_pycollect_makeitem hook is
called for potentially creating a node for it.
These Python objects have a bunch of builtin attributes that are
extremely unlikely to be collected. But due to their pervasiveness,
dispatching the hook for them ends up being mildly expensive and also
pollutes PYTEST_DEBUG=1 output and such.
Let's just ignore these attributes.
On the pandas test suite commit 04e9e0afd476b1b8bed930e47bf60e,
collect only, irrelevant lines snipped, about 5% improvement:
Before:
```
51195095 function calls (48844352 primitive calls) in 39.089 seconds
ncalls tottime percall cumtime percall filename:lineno(function)
226602/54 0.145 0.000 38.940 0.721 manager.py:90(_hookexec)
72227 0.285 0.000 20.146 0.000 python.py:424(_makeitem)
72227 0.171 0.000 16.678 0.000 python.py:218(pytest_pycollect_makeitem)
```
After:
```
48410921 function calls (46240870 primitive calls) in 36.950 seconds
ncalls tottime percall cumtime percall filename:lineno(function)
181429/54 0.113 0.000 36.777 0.681 manager.py:90(_hookexec)
27054 0.130 0.000 17.755 0.001 python.py:465(_makeitem)
27054 0.121 0.000 16.219 0.001 python.py:218(pytest_pycollect_makeitem)
```
In ff8b7884e8 NOTSET was changed to a
singleton enum, which ended up unexpectedly triggering a code path in ID
generation which checks for `isinstance(Enum)`.
Add an explicit case for it, which is not too bad anyway.
The path part of a `<path>::part1::part2` style collection argument must
be a file, not a directory.
Previously this crashed with an uncool assert "invalid arg".
The `CaptureManager.global_and_fixture_disabled()` context manager (and
`CaptureFixture.disabled()` which calls it) did `suspend(); ...;
resume()` but if the capturing was already suspended, the `resume()`
would resume it when it shouldn't.
This caused caused some messages to be swallowed when `--log-cli` is
used because it uses `global_and_fixture_disabled` when capturing is not
necessarily resumed.
This fixes an issue where pylint complains about missing implementations
of abstract methods in subclasses of `File` which only override
`collect()` (as they should).
It is also cleaner and makes sense, these methods really don't need to
be overridden.
The previous methods defined directly on `FSCollector` and `Package` are
deprecated, to be removed in pytest 7.
See commits e2934c3f8c and
f10ab021e2 for reference.
This makes mypy raise an error whenever it detects code which is
statically unreachable, e.g.
x: int
if isinstance(x, str):
... # Statement is unreachable [unreachable]
This is really neat and finds quite a few logic and typing bugs.
Sometimes the code is intentionally unreachable in terms of types, e.g.
raising TypeError when a function is given an argument with a wrong
type. In these cases a `type: ignore[unreachable]` is needed, but I
think it's a nice code hint.
This prevents referring to a generic type without filling in its generic
type parameters.
The FixtureDef typing might need some more refining in the future.
In Python, if module A defines a name `name`, and module B does `import
name from A`, then another module C can `import name from B`.
Sometimes it is intentional -- module B is meant to "reexport" `name`.
But sometimes it is just confusion/inconsistency on where `name` should
be imported from.
mypy has a flag `--no-implicit-reexport` which puts some order into
this. A name can only be imported from a module if
1. The module defines the name
2. The module's `__all__` includes the name
3. The module imports the name as `from ... import .. as name`.
This flag is included in mypy's `--strict` flag.
I like this flag, but I realize it is a bit controversial, and in
particular item 3 above is a bit unfriendly to contributors who don't
know about it. So I didn't intend to add it to pytest.
But while investigating issue 7589 I came upon mypy issue 8754 which
causes `--no-implicit-reexport` to leak into installed libraries and
causes some unexpected typing differences *in pytest* if the user uses
this flag.
Since the diff mostly makes sense, let's just conform to it.
We barely use it; the couple places that do are not really worth the
extra dependency, I think the code is clearer without it.
Also simplifies one (regular) itertools usage.
Also improves a check and an error message in `pytest.raises`.
Part of the effort to reduce dependency on the py library.
Besides that, py.xml implements its own XML serialization which is
pretty scary.
I tried to keep the code with minimal changes (though it could use some
cleanups). The differences in behavior I have noticed are:
- Attributes in the output are not sorted.
- Some unneeded escaping is no longer performed, for example escaping
`"` to `"` in a text node.
Part of reducing dependency on `py`. Also enables upcoming improvements.
In cases where there are simpler alternatives (in tests), I used those.
What's left are a couple of uses in `_pytest.main` and `_pytest.python`
and they only have modest requirements, so all of the featureful code
from py is not needed.
This fixes CI on Windows since GitHub Actions started installing WSL on
their images which apparently installs some wrapper `bash` which does
not run actual bash.
The previous typing had an object passed to the user, which they can't
do anything with without asserting, which is inconvenient. Change it to
Any instead.
Note that what comes *back* to pytest (the return value) should be an
`object`, because we want to handle arbitrary objects without assuming
anything about them.
If a test runtest phase (not setup) dynamically adds a pytest.mark.xfail
mark to the item, it should be respected, but it wasn't. This regressed
in 3e6fe92b7e (not released).
Fix it by just always refreshing the mark if needed. This is mostly what
was done before but in a more roundabout way.
Setting log_level via the CLI or .ini will control the log level of the
report that is dumped upon failure of a test.
If caplog modified the log level during the execution of that test, it
should not impact the level that is displayed upon failure in the
"captured log report" section.
[
ran:
- rebased
- reused handler
- changed store keys also to "caplog_handler_*"
- added changelog
all bugs are mine :)
]
Previously, skipif/xfail marks were evaluated using a `MarkEvaluator`
class. I found this class very difficult to understand.
Instead of `MarkEvaluator`, rewrite using straight functions which are
hopefully easier to follow.
I tried to keep the semantics exactly as before, except improving a few
error messages.
There are state transitions start/done/suspend/resume and two additional
operations snap/writeorg.
Previously it was not well defined in what order they can be called, and
which operations are idempotent.
Formalize this and enforce using assert checks with informative error
messages if they fail (rather than random AttributeErrors).
`TerminalWriter`, imported recently from `py`, contains its own
incomplete wcwidth (`char_with`/`get_line_width`) implementation. The
`TerminalReporter` also needs this, but uses the external `wcwidth`
package.
This commit brings the `TerminalWriter` implementation up-to-par with
`wcwidth`, moves to implementation to a new file `_pytest._io.wcwidth`
which is used everywhere, and removes the dependency.
The differences compared to the `wcwidth` package are:
- Normalizes the string before counting.
- Uses Python's `unicodedata` instead of vendored Unicode tables. This
means the data corresponds to the Python's version Unicode version
instead of the `wcwidth`'s package version.
- Apply some optimizations.
_pytest.timing is an indirection to 'time' functions, which pytest production
code should use instead of 'time' directly.
'mock_timing' is a new fixture which then mocks those functions, allowing us
to write time-reliable tests which run instantly and are not flaky.
This was triggered by recent flaky junitxml tests on Windows related to timing
issues.
The `FDCapture`/`FDCaptureBinary` classes, used by `capfd`/`capfdbinary`
fixtures and the `--capture=fd` option (set by default), redirect FDs
1/2 (stdout/stderr) to a temporary file. To do this, they need to save
the old file by duplicating the FD before redirecting it, to be restored
once finished.
Previously, if this duplicating (`os.dup()`) failed, most likely due to
that FD being invalid, the FD redirection would silently not be done. The
FD capturing also performs python-level redirection (monkeypatching
`sys.stdout`/`sys.stderr`) which would still be done, but direct writes
to the FDs would fail.
This is not great. If pytest is run with `--capture=fd`, or a test is
using `capfd`, it expects writes to the FD to work and be captured,
regardless of external circumstances.
So, instead of disabling FD capturing, keep the redirection to a
temporary file, just don't restore it after closing, because there is
nothing to restore to.
Currently, a bad logging call, e.g.
logger.info('oops', 'first', 2)
triggers the default logging handling, which is printing an error to
stderr but otherwise continuing.
For regular programs this behavior makes sense, a bad log message
shouldn't take down the program. But during tests, it is better not to
skip over such mistakes, but propagate them to the user.
Previously, a LoggingCaptureHandler was instantiated for each test's
setup/call/teardown which turns out to be expensive.
Instead, only keep one instance and reset it between runs.
The tests came via c629f6b18 and c61ff31ffa.
The fixes from there are kind of obsoleted by 4cd08f9 (moving to importlib),
but it makes sense to keep them as integration tests in general.
The default message is often hard to read:
E _pytest.config.ConftestImportFailure: (local('D:\\projects\\pytest\\.tmp\\root\\foo\\conftest.py'), (<class 'RuntimeError'>, RuntimeError('some error',), <traceback object at 0x000001CCC3E39348>))
Using a shorter message is better:
E _pytest.config.ConftestImportFailure: RuntimeError: some error (from D:\projects\pytest\.tmp\root\foo\conftest.py)
And we don't really lose any information due to exception chaining.
Only filter with known failures, and explicitly keep paths of passed
arguments.
This also displays the "run-last-failure" status before collected files,
and does not update the cache with "--collect-only".
Fixes https://github.com/pytest-dev/pytest/issues/6968.
The previous commit made this possible, so utilize it.
Since legacy.py becomes pretty bare, I inlined it into __init__.py. I'm
not sure it's really "legacy" anyway!
Using a simple 50000 items benchmark with `--collect-only -k nomatch`:
Before (two commits ago):
======================== 50000 deselected in 10.31s =====================
19129345 function calls (18275596 primitive calls) in 10.634 seconds
Ordered by: cumulative time
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.001 0.001 2.270 2.270 __init__.py:149(pytest_collection_modifyitems)
1 0.036 0.036 2.270 2.270 __init__.py:104(deselect_by_keyword)
50000 0.055 0.000 2.226 0.000 legacy.py:87(matchkeyword)
After:
======================== 50000 deselected in 9.37s =========================
18029363 function calls (17175972 primitive calls) in 9.701 seconds
Ordered by: cumulative time
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.000 0.000 1.394 1.394 __init__.py:239(pytest_collection_modifyitems)
1 0.057 0.057 1.393 1.393 __init__.py:162(deselect_by_keyword)
The matching itself can be optimized more but that's a different story.
In current pytest, the same expression is matched against all items. But
it is re-parsed for every match.
Add support for "compiling" an expression and reusing the result. Errors
may only occur during compilation.
This is done by parsing the expression into a Python `ast.Expression`,
then `compile()`ing it into a code object. Evaluation is then done using
`eval()`.
Note: historically we used to use `eval` directly on the user input --
this is not the case here, the expression is entirely under our control
according to our grammar, we just JIT-compile it to Python as a
(completely safe) optimization.
New errors:
testing/test_setupplan.py:104:15: E741 ambiguous variable name 'l'
testing/test_setupplan.py:107:15: E741 ambiguous variable name 'l'
extra/get_issues.py:48:29: E741 ambiguous variable name 'l'
testing/test_error_diffs.py:270:32: E741 ambiguous variable name 'l'
Not so sure about it but easier to just fix.
But more importantly, is a large amount of typing-related issues there
were fixed which necessitated noqa's which can now be removed.
The `-k '-expr'` syntax is an old alias to `-k 'not expr'`. It's also
not a very convenient to have syntax that start with `-` on the CLI.
Deprecate it and suggest replacing with `not`.
---
The `-k 'expr:'` syntax discards all items until the first match and
keeps all subsequent, e.g. `-k foo` with
test_bar
test_foo
test_baz
results in `test_foo`, `test_baz`. That's a bit weird, so deprecate it
without a replacement. If someone complains we can reconsider or devise
a better alternative.
Running `pytest | head -1` and similar causes an annoying error to be
printed to stderr:
Exception ignored in: <_io.TextIOWrapper name='<stdout>' mode='w' encoding='utf-8'>
BrokenPipeError: [Errno 32] Broken pipe
(or possibly even a propagating exception in older/other Python versions).
The standard UNIX behavior is to handle the EPIPE silently. To
recommended method to do this in Python is described here:
https://docs.python.org/3/library/signal.html#note-on-sigpipe
It is not appropriate to apply this recommendation to `pytest.main()`,
which is used programmatically for in-process runs. Hence, change
pytest's entrypoint to a new `pytest.console_main()` function, to be
used exclusively by pytest's CLI, and add the SIGPIPE code there.
Fixes#4375.
- replace "tests with warnings" with just warnings: they a) might not
come from a test in the first place, and b) a single test might have
multiple warnings.
- fix usage of (unused) argument to `collapsed_location_report`
Co-authored-by: Ran Benita <ran@unusedvar.com>
Move {Passthrough,CaptureIO} to capture module, and rename Passthrough
-> Tee to match the existing terminology.
Co-authored-by: Ran Benita <ran@unusedvar.com>
Also delay calling tearDown() when --pdb is given, so users still have
access to the instance variables (which are usually cleaned up during tearDown())
when debugging.
Fix#6947
Instead of trying to handle unittest-async functions in pytest_pyfunc_call,
let the unittest framework handle them instead.
This lets us remove the hack in pytest_pyfunc_call, with the upside that
we should support any unittest-async based framework.
Also included 'asynctest' as test dependency for py37-twisted, and renamed
'twisted' to 'unittestextras' to better reflect that we install 'twisted' and
'asynctest' now.
This also fixes the problem of cleanUp functions not being properly called
for async functions.
Fix#7110Fix#6924
Ran Benita
Bruno Oliveira
Anthony Sottile
Maximilian Cosmo Sitter
hp310780
Zac Hatfield-Dodds
Lewis Cowles
Simon K
Hugo van Kemenade
Arvin Firouzi
Vlad-Radz
Ruaridh Williamson
Gleb Nikonorov
gdhameeja
David Diaz Barquero
Ram Rachum
Andrew
Ronny Pfannschmidt
Zac-HD
ibriquem
piotrhm
Prashant Anand
Fabio Zadrozny
Tor Colvin
Katarzyna Król
Florian Dahlitz
Claire Cecil
Daniel Hahler
Daniel Hahler
Felix Nieuwenhuizen
Pavel Karateev
Katarzyna
Keri Volans