Riza Suminto created IMPALA-12898:
-------------------------------------
Summary: Tidy up test matrix of test_scanner.py
Key: IMPALA-12898
URL: https://issues.apache.org/jira/browse/IMPALA-12898
Project: IMPALA
Issue Type: Test
Components: Infrastructure
Reporter: Riza Suminto
Several tests in test_scanner.py seemingly declared with tests dimensions that
is ignored by its tests.
For example, TestScannersAllTableFormats
{code:python}
class TestScannersAllTableFormats(ImpalaTestSuite):
BATCH_SIZES = [0, 1, 16]
@classmethod
def get_workload(cls):
return 'functional-query'
@classmethod
def add_test_dimensions(cls):
super(TestScannersAllTableFormats, cls).add_test_dimensions()
if cls.exploration_strategy() == 'core':
# The purpose of this test is to get some base coverage of all the file
formats.
# Even in 'core', we'll test each format by using the pairwise strategy.
cls.ImpalaTestMatrix.add_dimension(cls.create_table_info_dimension('pairwise'))
cls.ImpalaTestMatrix.add_dimension(
ImpalaTestDimension('batch_size',
*TestScannersAllTableFormats.BATCH_SIZES))
cls.ImpalaTestMatrix.add_dimension(
ImpalaTestDimension('debug_action', *DEBUG_ACTION_DIMS))
cls.ImpalaTestMatrix.add_dimension(ImpalaTestDimension('mt_dop',
*MT_DOP_VALUES))
def test_scanners(self, vector):
new_vector = deepcopy(vector)
# Copy over test dimensions to the matching query options.
new_vector.get_value('exec_option')['batch_size'] =
vector.get_value('batch_size')
new_vector.get_value('exec_option')['debug_action'] =
vector.get_value('debug_action')
new_vector.get_value('exec_option')['mt_dop'] = vector.get_value('mt_dop')
self.run_test_case('QueryTest/scanners', new_vector)
def test_many_nulls(self, vector):
if vector.get_value('table_format').file_format == 'hbase':
# manynulls table not loaded for HBase
pytest.skip()
# Copy over test dimensions to the matching query options.
new_vector = deepcopy(vector)
new_vector.get_value('exec_option')['batch_size'] =
vector.get_value('batch_size')
new_vector.get_value('exec_option')['debug_action'] =
vector.get_value('debug_action')
new_vector.get_value('exec_option')['mt_dop'] = vector.get_value('mt_dop')
self.run_test_case('QueryTest/scanners-many-nulls', new_vector)
def test_hdfs_scanner_profile(self, vector):
if vector.get_value('table_format').file_format in ('kudu', 'hbase') or \
vector.get_value('exec_option')['num_nodes'] != 0:
pytest.skip()
self.run_test_case('QueryTest/hdfs_scanner_profile', vector)
def test_string_escaping(self, vector):
"""Test handling of string escape sequences."""
if vector.get_value('table_format').file_format == 'rc':
# IMPALA-7778: RCFile scanner incorrectly ignores escapes for now.
self.run_test_case('QueryTest/string-escaping-rcfile-bug', vector)
else:
self.run_test_case('QueryTest/string-escaping', vector)
{code}
test_scanners and test_many_nulls correctly copy exec_option values from test
vector. But test_hdfs_scanner_profile and test_string_escaping is not, and
unnecessary run multiple times even though it does not permuting its
exec_option. This and other test classes inside test_scanner.py can benefit
from refactoring and dimension reduction.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
