4d2b559d92
### What changes were proposed in this pull request? Consolidate PySpark testing utils by removing `python/pyspark/pandas/testing`, and then creating a file `pandasutils` under `python/pyspark/testing` for test utilities used in `pyspark/pandas`. ### Why are the changes needed? `python/pyspark/pandas/testing` hold test utilites for pandas-on-spark, and `python/pyspark/testing` contain test utilities for pyspark. Consolidating them makes code cleaner and easier to maintain. Updated import statements are as shown below: - from pyspark.testing.sqlutils import SQLTestUtils - from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils (PandasOnSparkTestCase is the original ReusedSQLTestCase in `python/pyspark/pandas/testing/utils.py`) Minor improvements include: - Usage of missing library's requirement_message - `except ImportError` rather than `except` - import pyspark.pandas alias as `ps` rather than `pp` ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Unit tests under python/pyspark/pandas/tests. Closes #32177 from xinrong-databricks/port.merge_utils. Authored-by: Xinrong Meng <xinrong.meng@databricks.com> Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
51 lines
1.9 KiB
Python
51 lines
1.9 KiB
Python
#
|
|
# 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.
|
|
#
|
|
|
|
from pyspark import pandas as ps
|
|
from pyspark.sql.utils import ParseException
|
|
from pyspark.testing.pandasutils import PandasOnSparkTestCase
|
|
from pyspark.testing.sqlutils import SQLTestUtils
|
|
|
|
|
|
class SQLTest(PandasOnSparkTestCase, SQLTestUtils):
|
|
def test_error_variable_not_exist(self):
|
|
msg = "The key variable_foo in the SQL statement was not found.*"
|
|
with self.assertRaisesRegex(ValueError, msg):
|
|
ps.sql("select * from {variable_foo}")
|
|
|
|
def test_error_unsupported_type(self):
|
|
msg = "Unsupported variable type dict: {'a': 1}"
|
|
with self.assertRaisesRegex(ValueError, msg):
|
|
some_dict = {"a": 1}
|
|
ps.sql("select * from {some_dict}")
|
|
|
|
def test_error_bad_sql(self):
|
|
with self.assertRaises(ParseException):
|
|
ps.sql("this is not valid sql")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.pandas.tests.test_sql 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)
|