spark-instrumented-optimizer/python/pyspark/sql/tests/test_conf.py

57 lines
2.3 KiB
Python
Raw Normal View History

[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
#
# 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.testing.sqlutils import ReusedSQLTestCase
class ConfTests(ReusedSQLTestCase):
def test_conf(self):
spark = self.spark
spark.conf.set("bogo", "sipeo")
self.assertEqual(spark.conf.get("bogo"), "sipeo")
spark.conf.set("bogo", "ta")
self.assertEqual(spark.conf.get("bogo"), "ta")
self.assertEqual(spark.conf.get("bogo", "not.read"), "ta")
self.assertEqual(spark.conf.get("not.set", "ta"), "ta")
self.assertRaisesRegexp(Exception, "not.set", lambda: spark.conf.get("not.set"))
spark.conf.unset("bogo")
self.assertEqual(spark.conf.get("bogo", "colombia"), "colombia")
self.assertEqual(spark.conf.get("hyukjin", None), None)
# This returns 'STATIC' because it's the default value of
# 'spark.sql.sources.partitionOverwriteMode', and `defaultValue` in
# `spark.conf.get` is unset.
self.assertEqual(spark.conf.get("spark.sql.sources.partitionOverwriteMode"), "STATIC")
# This returns None because 'spark.sql.sources.partitionOverwriteMode' is unset, but
# `defaultValue` in `spark.conf.get` is set to None.
self.assertEqual(spark.conf.get("spark.sql.sources.partitionOverwriteMode", None), None)
if __name__ == "__main__":
import unittest
from pyspark.sql.tests.test_conf import *
try:
import xmlrunner
[SPARK-28130][PYTHON] Print pretty messages for skipped tests when xmlrunner is available in PySpark ## What changes were proposed in this pull request? Currently, pretty skipped message added by https://github.com/apache/spark/commit/f7435bec6a9348cfbbe26b13c230c08545d16067 mechanism seems not working when xmlrunner is installed apparently. This PR fixes two things: 1. When `xmlrunner` is installed, seems `xmlrunner` does not respect `vervosity` level in unittests (default is level 1). So the output looks as below ``` Running tests... ---------------------------------------------------------------------- SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS ---------------------------------------------------------------------- ``` So it is not caught by our message detection mechanism. 2. If we manually set the `vervocity` level to `xmlrunner`, it prints messages as below: ``` test_mixed_udf (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) test_mixed_udf_and_sql (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) ... ``` This is different in our Jenkins machine: ``` test_createDataFrame_column_name_encoding (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' test_createDataFrame_does_not_modify_input (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' ... ``` Note that last `SKIP` is different. This PR fixes the regular expression to catch `SKIP` case as well. ## How was this patch tested? Manually tested. **Before:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (0s) ... Tests passed in 562 seconds ======================================================================== ... ``` **After:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (48s) ... 93 tests were skipped ... Tests passed in 560 seconds Skipped tests pyspark.... with python2.7: pyspark...(...) ... SKIP (0.000s) ... ======================================================================== ... ``` Closes #24927 from HyukjinKwon/SPARK-28130. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2019-06-23 20:58:17 -04:00
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
[SPARK-26032][PYTHON] Break large sql/tests.py files into smaller files ## What changes were proposed in this pull request? This is the official first attempt to break huge single `tests.py` file - I did it locally before few times and gave up for some reasons. Now, currently it really makes the unittests super hard to read and difficult to check. To me, it even bothers me to to scroll down the big file. It's one single 7000 lines file! This is not only readability issue. Since one big test takes most of tests time, the tests don't run in parallel fully - although it will costs to start and stop the context. We could pick up one example and follow. Given my investigation, the current style looks closer to NumPy structure and looks easier to follow. Please see https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/sql/tests.py` into ...: ```bash pyspark ... ├── sql ... │   ├── tests # Includes all tests broken down from 'pyspark/sql/tests.py' │ │  │ # Each matchs to module in 'pyspark/sql'. Additionally, some logical group can │ │  │ # be added. For instance, 'test_arrow.py', 'test_datasources.py' ... │   │   ├── __init__.py │   │   ├── test_appsubmit.py │   │   ├── test_arrow.py │   │   ├── test_catalog.py │   │   ├── test_column.py │   │   ├── test_conf.py │   │   ├── test_context.py │   │   ├── test_dataframe.py │   │   ├── test_datasources.py │   │   ├── test_functions.py │   │   ├── test_group.py │   │   ├── test_pandas_udf.py │   │   ├── test_pandas_udf_grouped_agg.py │   │   ├── test_pandas_udf_grouped_map.py │   │   ├── test_pandas_udf_scalar.py │   │   ├── test_pandas_udf_window.py │   │   ├── test_readwriter.py │   │   ├── test_serde.py │   │   ├── test_session.py │   │   ├── test_streaming.py │   │   ├── test_types.py │   │   ├── test_udf.py │   │   └── test_utils.py ... ├── testing # Includes testing utils that can be used in unittests. │   ├── __init__.py │   └── sqlutils.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and `./run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ``` SPARK_TESTING=1 ./bin/pyspark pyspark.sql.tests.test_pandas_udf_scalar ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23021 from HyukjinKwon/SPARK-25344. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-14 01:51:11 -05:00
except ImportError:
2018-11-14 23:30:52 -05:00
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)