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>
98 lines
3.6 KiB
Python
98 lines
3.6 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.
|
|
#
|
|
|
|
import os
|
|
import subprocess
|
|
import tempfile
|
|
|
|
import py4j
|
|
|
|
from pyspark import SparkContext
|
|
from pyspark.tests.test_appsubmit import SparkSubmitTests
|
|
|
|
|
|
class HiveSparkSubmitTests(SparkSubmitTests):
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
# get a SparkContext to check for availability of Hive
|
|
sc = SparkContext('local[4]', cls.__name__)
|
|
cls.hive_available = True
|
|
try:
|
|
sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
|
|
except py4j.protocol.Py4JError:
|
|
cls.hive_available = False
|
|
except TypeError:
|
|
cls.hive_available = False
|
|
finally:
|
|
# we don't need this SparkContext for the test
|
|
sc.stop()
|
|
|
|
def setUp(self):
|
|
super(HiveSparkSubmitTests, self).setUp()
|
|
if not self.hive_available:
|
|
self.skipTest("Hive is not available.")
|
|
|
|
def test_hivecontext(self):
|
|
# This test checks that HiveContext is using Hive metastore (SPARK-16224).
|
|
# It sets a metastore url and checks if there is a derby dir created by
|
|
# Hive metastore. If this derby dir exists, HiveContext is using
|
|
# Hive metastore.
|
|
metastore_path = os.path.join(tempfile.mkdtemp(), "spark16224_metastore_db")
|
|
metastore_URL = "jdbc:derby:;databaseName=" + metastore_path + ";create=true"
|
|
hive_site_dir = os.path.join(self.programDir, "conf")
|
|
hive_site_file = self.createTempFile("hive-site.xml", ("""
|
|
|<configuration>
|
|
| <property>
|
|
| <name>javax.jdo.option.ConnectionURL</name>
|
|
| <value>%s</value>
|
|
| </property>
|
|
|</configuration>
|
|
""" % metastore_URL).lstrip(), "conf")
|
|
script = self.createTempFile("test.py", """
|
|
|import os
|
|
|
|
|
|from pyspark.conf import SparkConf
|
|
|from pyspark.context import SparkContext
|
|
|from pyspark.sql import HiveContext
|
|
|
|
|
|conf = SparkConf()
|
|
|sc = SparkContext(conf=conf)
|
|
|hive_context = HiveContext(sc)
|
|
|print(hive_context.sql("show databases").collect())
|
|
""")
|
|
proc = subprocess.Popen(
|
|
self.sparkSubmit + ["--master", "local-cluster[1,1,1024]",
|
|
"--driver-class-path", hive_site_dir, script],
|
|
stdout=subprocess.PIPE)
|
|
out, err = proc.communicate()
|
|
self.assertEqual(0, proc.returncode)
|
|
self.assertIn("default", out.decode('utf-8'))
|
|
self.assertTrue(os.path.exists(metastore_path))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.sql.tests.test_appsubmit import *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|