Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Skip fastparquet timestamp tests when plugin cannot read/write timestamps #9831

Merged
merged 3 commits into from
Dec 1, 2023
Merged

Skip fastparquet timestamp tests when plugin cannot read/write timestamps #9831

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8693bdb
Skip fastparquet timestamp tests for non-UTC timezones.
mythrocks Nov 21, 2023
3d3c06b
Switch to standard is_not_utc().
mythrocks Nov 30, 2023
7db470f
Merge remote-tracking branch 'origin/branch-23.12' into fastparquet-tz
mythrocks Nov 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 19 additions & 6 deletions integration_tests/src/main/python/fastparquet_compatibility_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,6 +94,13 @@ def read_with_fastparquet_or_plugin(spark):
return read_with_fastparquet_or_plugin


def is_timezone_utc():
mythrocks marked this conversation as resolved.
Show resolved Hide resolved
from spark_init_internal import get_spark_i_know_what_i_am_doing
import time
spark = get_spark_i_know_what_i_am_doing()
return spark.conf.get("spark.sql.session.timeZone") == "UTC" and time.tzname[time.daylight] == "UTC"


@pytest.mark.skipif(condition=fastparquet_unavailable(),
reason="fastparquet is required for testing fastparquet compatibility")
@pytest.mark.skipif(condition=spark_version() < "3.4.0",
Expand All @@ -119,9 +126,12 @@ def read_with_fastparquet_or_plugin(spark):
marks=pytest.mark.xfail(reason="fastparquet reads dates as timestamps.")),
pytest.param(DateGen(nullable=False),
marks=pytest.mark.xfail(reason="fastparquet reads far future dates (e.g. year=8705) incorrectly.")),
TimestampGen(nullable=False,
start=pandas_min_datetime,
end=pandas_max_datetime), # Vanilla case.
pytest.param(TimestampGen(nullable=False,
start=pandas_min_datetime,
end=pandas_max_datetime),
marks=pytest.mark.skipif(condition=not is_timezone_utc(),
reason="fastparquet interprets timestamps in UTC timezone, regardless "
"of timezone settings")), # Vanilla case.
pytest.param(TimestampGen(nullable=False,
start=pandas_min_datetime,
end=pandas_max_datetime),
Expand Down Expand Up @@ -188,9 +198,12 @@ def test_reading_file_written_by_spark_cpu(data_gen, spark_tmp_path):
marks=pytest.mark.xfail(reason="fastparquet reads dates as timestamps.")),
pytest.param(DateGen(nullable=False),
marks=pytest.mark.xfail(reason="fastparquet reads far future dates (e.g. year=8705) incorrectly.")),
TimestampGen(nullable=False,
start=pandas_min_datetime,
end=pandas_max_datetime), # Vanilla case.
pytest.param(TimestampGen(nullable=False,
start=pandas_min_datetime,
end=pandas_max_datetime),
marks=pytest.mark.skipif(condition=not is_timezone_utc(),
reason="fastparquet interprets timestamps in UTC timezone, regardless "
"of timezone settings")), # Vanilla case.
pytest.param(TimestampGen(nullable=False,
start=datetime(1, 1, 1, tzinfo=timezone.utc),
end=pandas_min_datetime),
Expand Down