raulcd opened a new issue, #47778:
URL: https://github.com/apache/arrow/issues/47778
### Describe the bug, including details regarding any error messages,
version, and platform.
Several nightly tests and verification jobs have started failing with:
```
=================================== FAILURES
===================================
_____________________________ test_timezone_absent
_____________________________
datadir = PosixPath('/arrow/python/pyarrow/tests/data/orc')
tmpdir = local('/tmp/pytest-of-root/pytest-0/test_timezone_absent0')
def test_timezone_absent(datadir, tmpdir):
# Example file relies on the timezone "US/Pacific". It should
gracefully
# fail, not crash, if the timezone database is present but the
timezone
# is not found (GH-40633).
source_tzdir = Path('/usr/share/zoneinfo')
if not source_tzdir.exists():
pytest.skip(f"Test needs timezone database in {source_tzdir}")
tzdir = Path(tmpdir / 'zoneinfo')
try:
shutil.copytree(source_tzdir, tzdir, symlinks=True)
except OSError as e:
pytest.skip(f"Failed to copy timezone database: {e}")
(tzdir / 'US' / 'Pacific').unlink(missing_ok=True)
path = datadir / 'TestOrcFile.testDate1900.orc'
code = f"""if 1:
import os
os.environ['TZDIR'] = {str(tzdir)!r}
from pyarrow import orc
orc_file = orc.ORCFile({str(path)!r})
try:
orc_file.read()
except Exception as e:
assert "zoneinfo/US/Pacific" in str(e), e
else:
assert False, "Should have raised exception"
"""
> subprocess.run([sys.executable, "-c", code], check=True)
pyarrow/tests/test_orc.py:196:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_ _
input = None, capture_output = False, timeout = None, check = True
popenargs = (['/tmp/arrow-HEAD.oREbi/venv-source/bin/python3', '-c', 'if
1:\n import os\n os.environ[\'TZDIR\'] = \'...t
"zoneinfo/US/Pacific" in str(e), e\n else:\n assert False,
"Should have raised exception"\n '],)
kwargs = {}
process = <Popen: returncode: 1 args:
['/tmp/arrow-HEAD.oREbi/venv-source/bin/python3'...>
stdout = None, stderr = None, retcode = 1
def run(*popenargs,
input=None, capture_output=False, timeout=None, check=False,
**kwargs):
"""Run command with arguments and return a CompletedProcess instance.
The returned instance will have attributes args, returncode, stdout
and
stderr. By default, stdout and stderr are not captured, and those
attributes
will be None. Pass stdout=PIPE and/or stderr=PIPE in order to
capture them,
or pass capture_output=True to capture both.
If check is True and the exit code was non-zero, it raises a
CalledProcessError. The CalledProcessError object will have the
return code
in the returncode attribute, and output & stderr attributes if those
streams
were captured.
If timeout is given, and the process takes too long, a TimeoutExpired
exception will be raised.
There is an optional argument "input", allowing you to
pass bytes or a string to the subprocess's stdin. If you use this
argument
you may not also use the Popen constructor's "stdin" argument, as
it will be used internally.
By default, all communication is in bytes, and therefore any "input"
should
be bytes, and the stdout and stderr will be bytes. If in text mode,
any
"input" should be a string, and stdout and stderr will be strings
decoded
according to locale encoding, or by "encoding" if set. Text mode is
triggered by setting any of text, encoding, errors or
universal_newlines.
The other arguments are the same as for the Popen constructor.
"""
if input is not None:
if kwargs.get('stdin') is not None:
raise ValueError('stdin and input arguments may not both be
used.')
kwargs['stdin'] = PIPE
if capture_output:
if kwargs.get('stdout') is not None or kwargs.get('stderr') is
not None:
raise ValueError('stdout and stderr arguments may not be
used '
'with capture_output.')
kwargs['stdout'] = PIPE
kwargs['stderr'] = PIPE
with Popen(*popenargs, **kwargs) as process:
try:
stdout, stderr = process.communicate(input, timeout=timeout)
except TimeoutExpired as exc:
process.kill()
if _mswindows:
# Windows accumulates the output in a single blocking
# read() call run on child threads, with the timeout
# being done in a join() on those threads. communicate()
# _after_ kill() is required to collect that and add it
# to the exception.
exc.stdout, exc.stderr = process.communicate()
else:
# POSIX _communicate already populated the output so
# far into the TimeoutExpired exception.
process.wait()
raise
except: # Including KeyboardInterrupt, communicate handled that.
process.kill()
# We don't call process.wait() as .__exit__ does that for us.
raise
retcode = process.poll()
if check and retcode:
> raise CalledProcessError(retcode, process.args,
output=stdout, stderr=stderr)
E subprocess.CalledProcessError: Command
'['/tmp/arrow-HEAD.oREbi/venv-source/bin/python3', '-c', 'if 1:\n import
os\n os.environ[\'TZDIR\'] =
\'/tmp/pytest-of-root/pytest-0/test_timezone_absent0/zoneinfo\'\n\n from
pyarrow import orc\n orc_file =
orc.ORCFile(\'/arrow/python/pyarrow/tests/data/orc/TestOrcFile.testDate1900.orc\')\n
try:\n orc_file.read()\n except Exception as e:\n
assert "zoneinfo/US/Pacific" in str(e), e\n else:\n
assert False, "Should have raised exception"\n ']' returned non-zero exit
status 1.
/usr/lib/python3.10/subprocess.py:526: CalledProcessError
----------------------------- Captured stderr call
-----------------------------
Traceback (most recent call last):
File "<string>", line 12, in <module>
AssertionError: Should have raised exception
```
-
[verify-rc-source-python-linux-almalinux-8-amd64](https://github.com/ursacomputing/crossbow/actions/runs/18377086908/job/52353665688)
-
[verify-rc-source-python-linux-conda-latest-amd64](https://github.com/ursacomputing/crossbow/actions/runs/18377087568/job/52353668008)
-
[verify-rc-source-python-linux-ubuntu-22.04-amd64](https://github.com/ursacomputing/crossbow/actions/runs/18377087861/job/52353669078)
-
[verify-rc-source-python-linux-ubuntu-24.04-amd64](https://github.com/ursacomputing/crossbow/actions/runs/18377087016/job/52353665960)
-
[test-debian-12-python-3-amd64](https://github.com/ursacomputing/crossbow/actions/runs/18392907979/job/52406673630)
-
[test-debian-12-python-3-i386](https://github.com/ursacomputing/crossbow/actions/runs/18392907412/job/52406671621)
-
[test-ubuntu-22.04-python-3](https://github.com/ursacomputing/crossbow/actions/runs/18392906905/job/52406670146)
-
[test-ubuntu-22.04-python-313-freethreading](https://github.com/ursacomputing/crossbow/actions/runs/18392907589/job/52406672144)
-
[test-ubuntu-24.04-python-3](https://github.com/ursacomputing/crossbow/actions/runs/18392907963/job/52406673398)
This seems related to the ORC upgrade:
- https://github.com/apache/arrow/issues/47747
I am trying to reproduce locally.
### Component(s)
Continuous Integration, Python
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
