[SPARK-28130][PYTHON] Print pretty messages for skipped tests when xm…

…lrunner is available in PySpark

## What changes were proposed in this pull request?

Currently, pretty skipped message added by f7435be 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>

python/pyspark/ml/tests/test_algorithms.py

@@ -334,7 +334,7 @@ def test_linear_regression_with_huber_loss(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_base.py

@@ -71,7 +71,7 @@ def testDefaultFitMultiple(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_evaluation.py

@@ -57,7 +57,7 @@ def test_clustering_evaluator_with_cosine_distance(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_feature.py

@@ -307,7 +307,7 @@ def test_apply_binary_term_freqs(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_image.py

@@ -104,7 +104,7 @@ def test_read_images_multiple_times(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_linalg.py

@@ -382,7 +382,7 @@ def test_infer_schema(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_param.py

@@ -360,7 +360,7 @@ def test_java_params(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_persistence.py

@@ -392,7 +392,7 @@ def test_default_read_write_default_params(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_pipeline.py

@@ -63,7 +63,7 @@ def doTransform(pipeline):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_stat.py

@@ -44,7 +44,7 @@ def test_chisquaretest(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_training_summary.py

@@ -245,7 +245,7 @@ def test_kmeans_summary(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_tuning.py

@@ -538,7 +538,7 @@ def test_copy(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/ml/tests/test_wrapper.py

@@ -112,7 +112,7 @@ def test_new_java_array(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_algorithms.py

@@ -296,7 +296,7 @@ def test_fpgrowth(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_feature.py

@@ -186,7 +186,7 @@ def test_pca(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_linalg.py

@@ -623,7 +623,7 @@ def test_regression(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_stat.py

@@ -182,7 +182,7 @@ def test_R_implementation_equivalence(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_streaming_algorithms.py

@@ -508,7 +508,7 @@ def condition():
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/mllib/tests/test_util.py

@@ -98,7 +98,7 @@ def test_to_java_object_rdd(self):  # SPARK-6660
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_appsubmit.py

@@ -91,7 +91,7 @@ def test_hivecontext(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_arrow.py

@@ -424,7 +424,7 @@ def conf(cls):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_catalog.py

@@ -194,7 +194,7 @@ def test_list_columns(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_column.py

@@ -152,7 +152,7 @@ def test_bitwise_operations(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_conf.py

@@ -50,7 +50,7 @@ def test_conf(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_context.py

@@ -256,7 +256,7 @@ def range_frame_match():
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_dataframe.py

@@ -774,7 +774,7 @@ def test_query_execution_listener_on_collect_with_arrow(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_datasources.py

@@ -165,7 +165,7 @@ def test_ignore_column_of_all_nulls(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_functions.py

@@ -301,7 +301,7 @@ def test_input_file_name_reset_for_rdd(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_group.py

@@ -40,7 +40,7 @@ def test_aggregator(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_pandas_udf.py

@@ -247,7 +247,7 @@ def udf(column):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_pandas_udf_grouped_agg.py

@@ -480,7 +480,7 @@ def test_grouped_with_empty_partition(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_pandas_udf_grouped_map.py

@@ -522,7 +522,7 @@ def test_grouped_with_empty_partition(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_pandas_udf_scalar.py

@@ -1105,7 +1105,7 @@ def test_datasource_with_udf(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_pandas_udf_window.py

@@ -356,7 +356,7 @@ def test_bounded_mixed(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_readwriter.py

@@ -148,7 +148,7 @@ def count_bucketed_cols(names, table="pyspark_bucket"):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_serde.py

@@ -143,7 +143,7 @@ def test_int_array_serialization(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_session.py

@@ -316,7 +316,7 @@ def test_use_custom_class_for_extensions(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_streaming.py

@@ -571,7 +571,7 @@ def collectBatch(df, id):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_types.py

@@ -957,7 +957,7 @@ def __init__(self, **kwargs):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_udf.py

@@ -633,7 +633,7 @@ def test_udf_init_shouldnt_initialize_context(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/sql/tests/test_utils.py

@@ -49,7 +49,7 @@ def test_capture_illegalargument_exception(self):
 
     try:
         import xmlrunner
-        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
         testRunner = None
     unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/streaming/tests/test_context.py

@@ -179,6 +179,7 @@ def test_await_termination_or_timeout(self):
 
     try:
         import xmlrunner
-        unittest.main(testRunner=xmlrunner.XMLTestRunner(output='target/test-reports'), verbosity=2)
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
-        unittest.main(verbosity=2)
+        testRunner = None
+    unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/streaming/tests/test_dstream.py

@@ -645,6 +645,7 @@ def check_output(n):
 
     try:
         import xmlrunner
-        unittest.main(testRunner=xmlrunner.XMLTestRunner(output='target/test-reports'), verbosity=2)
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
-        unittest.main(verbosity=2)
+        testRunner = None
+    unittest.main(testRunner=testRunner, verbosity=2)

python/pyspark/streaming/tests/test_kinesis.py

@@ -84,6 +84,7 @@ def get_output(_, rdd):
 
     try:
         import xmlrunner
-        unittest.main(testRunner=xmlrunner.XMLTestRunner(output='target/test-reports'), verbosity=2)
+        testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
     except ImportError:
-        unittest.main(verbosity=2)
+        testRunner = None
+    unittest.main(testRunner=testRunner, verbosity=2)