7c05f61514
## What changes were proposed in this pull request?
Currently, pretty skipped message added by f7435bec6a
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>
70 lines
2.8 KiB
Python
70 lines
2.8 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.testing.utils import ReusedPySparkTestCase
|
|
|
|
|
|
class JoinTests(ReusedPySparkTestCase):
|
|
|
|
def test_narrow_dependency_in_join(self):
|
|
rdd = self.sc.parallelize(range(10)).map(lambda x: (x, x))
|
|
parted = rdd.partitionBy(2)
|
|
self.assertEqual(2, parted.union(parted).getNumPartitions())
|
|
self.assertEqual(rdd.getNumPartitions() + 2, parted.union(rdd).getNumPartitions())
|
|
self.assertEqual(rdd.getNumPartitions() + 2, rdd.union(parted).getNumPartitions())
|
|
|
|
tracker = self.sc.statusTracker()
|
|
|
|
self.sc.setJobGroup("test1", "test", True)
|
|
d = sorted(parted.join(parted).collect())
|
|
self.assertEqual(10, len(d))
|
|
self.assertEqual((0, (0, 0)), d[0])
|
|
jobId = tracker.getJobIdsForGroup("test1")[0]
|
|
self.assertEqual(2, len(tracker.getJobInfo(jobId).stageIds))
|
|
|
|
self.sc.setJobGroup("test2", "test", True)
|
|
d = sorted(parted.join(rdd).collect())
|
|
self.assertEqual(10, len(d))
|
|
self.assertEqual((0, (0, 0)), d[0])
|
|
jobId = tracker.getJobIdsForGroup("test2")[0]
|
|
self.assertEqual(3, len(tracker.getJobInfo(jobId).stageIds))
|
|
|
|
self.sc.setJobGroup("test3", "test", True)
|
|
d = sorted(parted.cogroup(parted).collect())
|
|
self.assertEqual(10, len(d))
|
|
self.assertEqual([[0], [0]], list(map(list, d[0][1])))
|
|
jobId = tracker.getJobIdsForGroup("test3")[0]
|
|
self.assertEqual(2, len(tracker.getJobInfo(jobId).stageIds))
|
|
|
|
self.sc.setJobGroup("test4", "test", True)
|
|
d = sorted(parted.cogroup(rdd).collect())
|
|
self.assertEqual(10, len(d))
|
|
self.assertEqual([[0], [0]], list(map(list, d[0][1])))
|
|
jobId = tracker.getJobIdsForGroup("test4")[0]
|
|
self.assertEqual(3, len(tracker.getJobInfo(jobId).stageIds))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.tests.test_join import *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|