Skip fastparquet timestamp tests for non-UTC timezones.

Fixes NVIDIA#9776.

`fastparquet` seems to read Parquet timestamp columns and interpret them
in the UTC timezone, regardless of timestamp settings.
The Spark RAPIDS plugin falls back on Apache Spark (CPU) to interpret
timestamp columns, when it detects that the timezone is non-UTC.
Apache Spark seems to correctly interpret the timestamps based on
timezone.

This causes the `fastparquet` timestamp tests to fail in cases where
the timezone is unspecified.

This commit xfails the timestamp tests when a non-UTC timezone is
detected.

Signed-off-by: MithunR <[email protected]>

integration_tests/src/main/python/fastparquet_compatibility_test.py

@@ -94,6 +94,13 @@ def read_with_fastparquet_or_plugin(spark):
     return read_with_fastparquet_or_plugin
 
 
+def is_timezone_utc():
+    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",
@@ -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.xfail(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),
@@ -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.xfail(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),