Source: python-hypothesis Version: 6.92.2-1 Severity: important Tags: ftbfs Forwarded: https://github.com/HypothesisWorks/hypothesis/issues/3829
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 Recently, I started to see intermittent test failures for test_can_produce_multi_line_strings in Debian package builds. I don't know if this is some sort of regression in version 6.92.2 or if this test has always been a bit flaky and merely became more likely to fail because Debian runs the test suite twice at the moment (Python 3.11 and Python 3.12). Example failure for Python 3.11: https://buildd.debian.org/status/fetch.php?pkg=python-hypothesis&arch=all&ver=6.92.2-1&stamp=1703980481&raw=0 _____________________ test_can_produce_multi_line_strings ______________________ Traceback (most recent call last): File "/usr/lib/python3/dist-packages/_pytest/runner.py", line 341, in from_call result: Optional[TResult] = func() ^^^^^^ File "/usr/lib/python3/dist-packages/_pytest/runner.py", line 262, in <lambda> lambda: ihook(item=item, **kwds), when=when, reraise=reraise ^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_hooks.py", line 493, in __call__ return self._hookexec(self.name, self._hookimpls, kwargs, firstresult) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_manager.py", line 115, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_callers.py", line 152, in _multicall return outcome.get_result() ^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_result.py", line 114, in get_result raise exc.with_traceback(exc.__traceback__) File "/usr/lib/python3/dist-packages/pluggy/_callers.py", line 77, in _multicall res = hook_impl.function(*args) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/_pytest/runner.py", line 177, in pytest_runtest_call raise e File "/usr/lib/python3/dist-packages/_pytest/runner.py", line 169, in pytest_runtest_call item.runtest() File "/usr/lib/python3/dist-packages/_pytest/python.py", line 1792, in runtest self.ihook.pytest_pyfunc_call(pyfuncitem=self) File "/usr/lib/python3/dist-packages/pluggy/_hooks.py", line 493, in __call__ return self._hookexec(self.name, self._hookimpls, kwargs, firstresult) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_manager.py", line 115, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pluggy/_callers.py", line 113, in _multicall raise exception.with_traceback(exception.__traceback__) File "/usr/lib/python3/dist-packages/pluggy/_callers.py", line 77, in _multicall res = hook_impl.function(*args) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/_pytest/python.py", line 194, in pytest_pyfunc_call result = testfunction(**testargs) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/<<PKGBUILDDIR>>/.pybuild/cpython3_3.11_hypothesis/build/tests/quality/test_discovery_ability.py", line 118, in run_test raise HypothesisFalsified( tests.quality.test_discovery_ability.HypothesisFalsified: P(lambda x: "\n" in x) ~ 47 / 98 = 0.48 < 0.50; rejected Example failure for Python 3.12: https://salsa.debian.org/python-team/packages/python-hypothesis/-/jobs/5108379 _____________________ test_can_produce_multi_line_strings ______________________ def run_test(): if condition is None: def _condition(x): return True condition_string = "" else: _condition = condition condition_string = strip_lambda( reflection.get_pretty_function_description(condition) ) def test_function(data): with BuildContext(data): try: value = data.draw(specifier) except UnsatisfiedAssumption: data.mark_invalid() if not _condition(value): data.mark_invalid() if predicate(value): data.mark_interesting() successes = 0 actual_runs = 0 for actual_runs in range(1, RUNS + 1): # We choose the max_examples a bit larger than default so that we # run at least 100 examples outside of the small example generation # part of the generation phase. runner = ConjectureRunner( test_function, settings=Settings( max_examples=150, phases=no_shrink, suppress_health_check=suppress_health_check, ), ) runner.run() if runner.interesting_examples: successes += 1 if successes >= required_runs: return # If we reach a point where it's impossible to hit our target even # if every remaining attempt were to succeed, give up early and # report failure. if (required_runs - successes) > (RUNS - actual_runs): break event = reflection.get_pretty_function_description(predicate) if condition is not None: event += "|" event += condition_string > raise HypothesisFalsified( f"P({event}) ~ {successes} / {actual_runs} = " f"{successes / actual_runs:.2f} < {required_runs / RUNS:.2f}; " "rejected" ) E tests.quality.test_discovery_ability.HypothesisFalsified: P(lambda x: "\n" in x) ~ 44 / 95 = 0.46 < 0.50; rejected tests/quality/test_discovery_ability.py:118: HypothesisFalsified -----BEGIN PGP SIGNATURE----- iQGzBAEBCgAdFiEEJvtDgpxjkjCIVtam+C8H+466LVkFAmWVJEoACgkQ+C8H+466 LVlueQwAi40LADd5VRN6qzbWtut9IVZF49aAmFVyY9LliNq9GMVdski2bPuzxAj8 Meh7g9jFuAuObnPtapjw644t89maaXaPue4l17OYPiWeuhLzMJrvZd5rivQUgZXQ hLFmLIAFVdbN0mCdO0cnIj1XxI+KFpny6cYVvahla+KG7PY3HTbUm36XrSuoG9LO LHynLquooZVeZI/VU7Q6vNspWdOitcRTW133YwZy0bQrY41mr0CqC4st6DyNIVt+ x0qkevKUNZHGdUMrJ8J5J8noEo1fft95iguL6gD5+uIYejL5Zr6YpFBKrcg/3oX2 iACAAPwtLOXFjG+f3n5tUPDSENdQvf8asch7/c5s7DY/CGZlubX5JRg7t2axVDXh oO72kjjkqXC1GGcmgf4W/B/L4ioOb+UcMdFXBaC5ruq24lBXOkfcvff8m7ZipoDU CAWD1wo61iLfmvX8s8YxbM7xBEsVf9o5Q8XHOpLBVZJCPa90ikg9DjkIQQz4Bubx bjldKKvB =PuO1 -----END PGP SIGNATURE-----
