This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new f5924cf6bee [SPARK-42009][CONNECT][TESTS] Reuse
pyspark.sql.tests.test_serde test cases
f5924cf6bee is described below
commit f5924cf6beef1253af7cc89f6b292569caff3973
Author: Hyukjin Kwon <[email protected]>
AuthorDate: Thu Jan 12 18:15:06 2023 +0900
[SPARK-42009][CONNECT][TESTS] Reuse pyspark.sql.tests.test_serde test cases
### What changes were proposed in this pull request?
This PR reuses PySpark `pyspark.sql.tests.test_serde` tests in Spark
Connect that pass for now.
### Why are the changes needed?
To make sure on the test coverage.
### Does this PR introduce _any_ user-facing change?
No, test-only.
### How was this patch tested?
Manually ran it in my local.
Closes #39527 from HyukjinKwon/SPARK-42009.
Authored-by: Hyukjin Kwon <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
dev/sparktestsupport/modules.py | 1 +
.../pyspark/sql/tests/connect/test_parity_serde.py | 58 ++++++++++++++++++++++
python/pyspark/sql/tests/test_serde.py | 6 ++-
3 files changed, 64 insertions(+), 1 deletion(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index 0ffffe39323..785dcf42498 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -520,6 +520,7 @@ pyspark_connect = Module(
"pyspark.sql.tests.connect.test_connect_column",
"pyspark.sql.tests.connect.test_parity_datasources",
"pyspark.sql.tests.connect.test_parity_catalog",
+ "pyspark.sql.tests.connect.test_parity_serde",
"pyspark.sql.tests.connect.test_parity_functions",
"pyspark.sql.tests.connect.test_parity_group",
"pyspark.sql.tests.connect.test_parity_dataframe",
diff --git a/python/pyspark/sql/tests/connect/test_parity_serde.py
b/python/pyspark/sql/tests/connect/test_parity_serde.py
new file mode 100644
index 00000000000..ba198636126
--- /dev/null
+++ b/python/pyspark/sql/tests/connect/test_parity_serde.py
@@ -0,0 +1,58 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import unittest
+
+from pyspark.sql.tests.test_serde import SerdeTestsMixin
+from pyspark.testing.connectutils import ReusedConnectTestCase
+
+
+class SerdeParityTests(SerdeTestsMixin, ReusedConnectTestCase):
+ # TODO(SPARK-42014): Support aware datetimes for createDataFrame
+ @unittest.skip("Fails in Spark Connect, should enable.")
+ def test_filter_with_datetime_timezone(self):
+ super().test_filter_with_datetime_timezone()
+
+ @unittest.skip("Spark Connect does not support RDD but the tests depend on
them.")
+ def test_int_array_serialization(self):
+ super().test_int_array_serialization()
+
+ @unittest.skip("Spark Connect does not support RDD but the tests depend on
them.")
+ def test_serialize_nested_array_and_map(self):
+ super().test_serialize_nested_array_and_map()
+
+ @unittest.skip("Spark Connect does not support RDD but the tests depend on
them.")
+ def test_struct_in_map(self):
+ super().test_struct_in_map()
+
+ # TODO(SPARK-42014): Support aware datetimes for createDataFrame
+ @unittest.skip("Fails in Spark Connect, should enable.")
+ def test_time_with_timezone(self):
+ super().test_time_with_timezone()
+
+
+if __name__ == "__main__":
+ import unittest
+ from pyspark.sql.tests.connect.test_parity_serde import * # noqa: F401
+
+ try:
+ import xmlrunner # type: ignore[import]
+
+ testRunner = xmlrunner.XMLTestRunner(output="target/test-reports",
verbosity=2)
+ except ImportError:
+ testRunner = None
+ unittest.main(testRunner=testRunner, verbosity=2)
diff --git a/python/pyspark/sql/tests/test_serde.py
b/python/pyspark/sql/tests/test_serde.py
index e8017cfd38a..f24a716f4a6 100644
--- a/python/pyspark/sql/tests/test_serde.py
+++ b/python/pyspark/sql/tests/test_serde.py
@@ -26,7 +26,7 @@ from pyspark.sql.types import StructType, StructField,
DecimalType, BinaryType
from pyspark.testing.sqlutils import ReusedSQLTestCase, UTCOffsetTimezone
-class SerdeTests(ReusedSQLTestCase):
+class SerdeTestsMixin:
def test_serialize_nested_array_and_map(self):
d = [Row(lst=[Row(a=1, b="s")], d={"key": Row(c=1.0, d="2")})]
rdd = self.sc.parallelize(d)
@@ -140,6 +140,10 @@ class SerdeTests(ReusedSQLTestCase):
self.assertEqual(df.first().col, bytearray(b"abcd"))
+class SerdeTests(SerdeTestsMixin, ReusedSQLTestCase):
+ pass
+
+
if __name__ == "__main__":
import unittest
from pyspark.sql.tests.test_serde import * # noqa: F401
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
