def test_fuzz_nested_types(self, vector, unique_database):
table_format = vector.get_value('table_format')
table_name = "complextypestbl"
src_db = QueryTestSectionReader.get_db_name(table_format)
if table_format.file_format not in ['parquet', 'orc']: pytest.skip()
# Additional queries to scan the nested values.
custom_queries = [
"select count(*) from ("
" select distinct t.id, a.pos, a.item, aa.pos, aa.item, m.key, m.value,"
" ma.key, ma.value, t.nested_struct.* "
" from complextypestbl t, t.int_array a, t.int_array_array.item aa, "
" t.int_map m, t.int_map_array.item ma) q",
"select count(*) from ("
" select t.id, t.nested_struct.a, b.pos, b.item, i.e, i.f, m.key,"
" arr.pos, arr.item "
" from complextypestbl t, t.nested_struct.b, t.nested_struct.c.d.item i,"
" t.nested_struct.g m, m.value.h.i arr) q",
]
self.run_fuzz_test(vector,
src_db,
table_name,
unique_database,
table_name,
10,
custom_queries=custom_queries)
def test_wide_table(self, vector):
if vector.get_value('table_format').file_format == 'kudu':
pytest.xfail("IMPALA-3718: Extend Kudu functional test support")
NUM_COLS = vector.get_value('num_cols')
# Due to the way HBase handles duplicate row keys, we have different number of
# rows in HBase tables compared to HDFS tables.
NUM_ROWS = 10 if vector.get_value('table_format').file_format != 'hbase' else 2
DB_NAME = QueryTestSectionReader.get_db_name(vector.get_value('table_format'))
TABLE_NAME = "%s.widetable_%s_cols" % (DB_NAME, NUM_COLS)
result = self.client.execute("select count(*) from %s " % TABLE_NAME)
assert result.data == [str(NUM_ROWS)]
expected_result = widetable.get_data(NUM_COLS, NUM_ROWS, quote_strings=True)
result = self.client.execute("select * from %s" % TABLE_NAME)
if vector.get_value('table_format').file_format == 'hbase':
assert len(result.data) == NUM_ROWS
return
types = parse_column_types(result.schema)
labels = parse_column_labels(result.schema)
expected = QueryTestResult(expected_result, types, labels, order_matters=False)
actual = QueryTestResult(parse_result_rows(result), types, labels,
order_matters=False)
assert expected == actual
def test_fuzz_nested_types(self, vector, unique_database):
table_format = vector.get_value('table_format')
table_name = "complextypestbl"
src_db = QueryTestSectionReader.get_db_name(table_format)
if table_format.file_format != 'parquet': pytest.skip()
self.run_fuzz_test(vector, src_db, table_name, unique_database, table_name, 10)
def __build_query(self):
"""Populates db, query_str, table_format_str"""
self.db = QueryTestSectionReader.get_db_name(self.test_vector, self.scale_factor)
self.query_str = QueryTestSectionReader.build_query(self.query_str.strip())
self.table_format_str = '%s/%s/%s' % (self.test_vector.file_format,
self.test_vector.compression_codec,
self.test_vector.compression_type)
def test_fuzz_nested_types(self, vector, unique_database):
table_format = vector.get_value('table_format')
table_name = "complextypestbl"
src_db = QueryTestSectionReader.get_db_name(table_format)
if table_format.file_format != 'parquet': pytest.skip()
self.run_fuzz_test(vector, src_db, table_name, unique_database, table_name, 10)
def _build_query(self):
"""Populates db, query_str, table_format_str"""
self.db = QueryTestSectionReader.get_db_name(self.test_vector,
self.scale_factor)
self.query_str = QueryTestSectionReader.build_query(
self.query_str.strip())
self.table_format_str = '%s/%s/%s' % (
self.test_vector.file_format, self.test_vector.compression_codec,
self.test_vector.compression_type)
def change_database(cls, impala_client, table_format=None,
db_name=None, scale_factor=None):
if db_name == None:
assert table_format != None
db_name = QueryTestSectionReader.get_db_name(table_format,
scale_factor if scale_factor else '')
query = 'use %s' % db_name
# Clear the exec_options before executing a USE statement.
# The USE statement should not fail for negative exec_option tests.
impala_client.clear_configuration()
impala_client.execute(query)
def change_database(cls, impala_client, table_format=None,
db_name=None, scale_factor=None):
if db_name == None:
assert table_format != None
db_name = QueryTestSectionReader.get_db_name(table_format,
scale_factor if scale_factor else '')
query = 'use %s' % db_name
# Clear the exec_options before executing a USE statement.
# The USE statement should not fail for negative exec_option tests.
impala_client.clear_configuration()
impala_client.execute(query)
def test_exprs(self, vector):
# TODO: Enable some of these tests for Avro if possible
# Don't attempt to evaluate timestamp expressions with Avro tables (which)
# don't support a timestamp type)"
table_format = vector.get_value('table_format')
if table_format.file_format == 'avro':
pytest.skip()
if table_format.file_format == 'hbase':
pytest.xfail("A lot of queries check for NULLs, which hbase does not recognize")
self.run_test_case('QueryTest/exprs', vector)
# This will change the current database to matching table format and then execute
# select current_database(). An error will be thrown if multiple values are returned.
current_db = self.execute_scalar('select current_database()', vector=vector)
assert current_db == QueryTestSectionReader.get_db_name(table_format)
def test_exprs(self, vector):
# TODO: Enable some of these tests for Avro if possible
# Don't attempt to evaluate timestamp expressions with Avro tables (which)
# don't support a timestamp type)"
table_format = vector.get_value('table_format')
if table_format.file_format == 'avro':
pytest.skip()
if table_format.file_format == 'hbase':
pytest.xfail("A lot of queries check for NULLs, which hbase does not recognize")
self.run_test_case('QueryTest/exprs', vector)
# This will change the current database to matching table format and then execute
# select current_database(). An error will be thrown if multiple values are returned.
current_db = self.execute_scalar('select current_database()', vector=vector)
assert current_db == QueryTestSectionReader.get_db_name(table_format)
def test_fuzz_decimal_tbl(self, vector, unique_database):
table_format = vector.get_value('table_format')
table_name = "decimal_tbl"
if table_format.file_format == 'avro':
table_name = "avro_decimal_tbl"
if table_format.compression_codec != 'snap' or \
table_format.compression_type != 'block':
pytest.skip()
elif table_format.file_format == 'text' and \
table_format.compression_codec != 'none':
# decimal_tbl is not present for these file formats
pytest.skip()
src_db = QueryTestSectionReader.get_db_name(table_format)
self.run_fuzz_test(vector, src_db, table_name, unique_database, table_name, 10)
def test_fuzz_decimal_tbl(self, vector, unique_database):
table_format = vector.get_value('table_format')
table_name = "decimal_tbl"
if table_format.file_format == 'avro':
table_name = "avro_decimal_tbl"
if table_format.compression_codec != 'snap' or \
table_format.compression_type != 'block':
pytest.skip()
elif table_format.file_format == 'rc' or \
table_format.file_format == 'seq':
pytest.skip()
elif table_format.file_format == 'text' and \
table_format.compression_codec != 'none':
# decimal_tbl is not present for these file formats
pytest.skip()
src_db = QueryTestSectionReader.get_db_name(table_format)
self.run_fuzz_test(vector, src_db, table_name, unique_database, table_name, 10)
def test_exprs(self, vector):
vector.get_value('exec_option')['enable_expr_rewrites'] = \
vector.get_value('enable_expr_rewrites')
# TODO: Enable some of these tests for Avro if possible
# Don't attempt to evaluate timestamp expressions with Avro tables (which don't
# support a timestamp type)"
table_format = vector.get_value('table_format')
if table_format.file_format == 'avro':
pytest.skip()
if table_format.file_format == 'hbase':
pytest.xfail("A lot of queries check for NULLs, which hbase does not recognize")
if table_format.file_format == 'kudu':
# Can't load LikeTbl without KUDU-1570.
pytest.xfail("Need support for Kudu tables with nullable PKs (KUDU-1570)")
self.run_test_case('QueryTest/exprs', vector)
# This will change the current database to matching table format and then execute
# select current_database(). An error will be thrown if multiple values are returned.
current_db = self.execute_scalar('select current_database()', vector=vector)
assert current_db == QueryTestSectionReader.get_db_name(table_format)
def test_wide_table(self, vector):
NUM_COLS = vector.get_value('num_cols')
# Due to the way HBase handles duplicate row keys, we have different number of
# rows in HBase tables compared to HDFS tables.
NUM_ROWS = 10 if vector.get_value('table_format').file_format != 'hbase' else 2
DB_NAME = QueryTestSectionReader.get_db_name(vector.get_value('table_format'))
TABLE_NAME = "%s.widetable_%s_cols" % (DB_NAME, NUM_COLS)
result = self.client.execute("select count(*) from %s " % TABLE_NAME)
assert result.data == [str(NUM_ROWS)]
expected_result = widetable.get_data(NUM_COLS, NUM_ROWS, quote_strings=True)
result = self.client.execute("select * from %s" % TABLE_NAME)
if vector.get_value('table_format').file_format == 'hbase':
assert len(result.data) == NUM_ROWS
return
types = parse_column_types(result.schema)
labels = parse_column_labels(result.schema)
expected = QueryTestResult(expected_result, types, labels, order_matters=False)
actual = QueryTestResult(parse_result_rows(result), types, labels,
order_matters=False)
assert expected == actual
def test_fuzz_alltypes(self, vector, unique_database):
table_format = vector.get_value('table_format')
src_db = QueryTestSectionReader.get_db_name(table_format)
table_name = "alltypes"
self.run_fuzz_test(vector, src_db, table_name, unique_database,
table_name)
def test_fuzz_alltypes(self, vector, unique_database):
table_format = vector.get_value('table_format')
src_db = QueryTestSectionReader.get_db_name(table_format)
table_name = "alltypes"
self.run_fuzz_test(vector, src_db, table_name, unique_database, table_name)
