def test_wide_table(self, vector):
NUM_COLS = vector.get_value('num_cols')
NUM_ROWS = 10
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)
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_insert_wide_table(self, vector):
table_format = vector.get_value('table_format')
# Text can't handle as many columns as Parquet (codegen takes forever)
num_cols = 1000 if table_format.file_format == 'text' else 2000
db_name = QueryTestSectionReader.get_db_name(vector.get_value('table_format'))
table_name = db_name + ".insert_widetable"
if vector.get_value('exec_option')['disable_codegen']:
table_name += "_codegen_disabled"
self.client.execute("drop table if exists " + table_name)
col_descs = widetable.get_columns(num_cols)
create_stmt = "CREATE TABLE " + table_name + "(" + ','.join(col_descs) + ")"
if vector.get_value('table_format').file_format == 'parquet':
create_stmt += " stored as parquet"
self.client.execute(create_stmt)
# Get a single row of data
col_vals = widetable.get_data(num_cols, 1, quote_strings=True)[0]
insert_stmt = "INSERT INTO " + table_name + " VALUES(" + col_vals + ")"
self.client.execute(insert_stmt)
result = self.client.execute("select count(*) from " + table_name)
assert result.data == ["1"]
result = self.client.execute("select * from " + table_name)
types = parse_column_types(result.schema)
labels = parse_column_labels(result.schema)
expected = QueryTestResult([col_vals], types, labels, order_matters=False)
actual = QueryTestResult(parse_result_rows(result), types, labels, order_matters=False)
assert expected == actual
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_many_grouping_columns(self, vector):
"""Test that an aggregate with many grouping columns works"""
table_format = vector.get_value('table_format')
exec_option = vector.get_value('exec_option')
query = "select distinct * from widetable_1000_cols"
# Ensure codegen is enabled.
result = self.execute_query(query,
exec_option,
table_format=table_format)
# All rows should be distinct.
expected_result = widetable.get_data(1000, 10, quote_strings=True)
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_insert_wide_table(self, vector, unique_database):
table_format = vector.get_value('table_format')
# Text can't handle as many columns as Parquet (codegen takes forever)
num_cols = 1000 if table_format.file_format == 'text' else 2000
table_name = unique_database + ".insert_widetable"
if vector.get_value('exec_option')['disable_codegen']:
table_name += "_codegen_disabled"
col_descs = widetable.get_columns(num_cols)
create_stmt = "CREATE TABLE " + table_name + "(" + ','.join(col_descs) + ")"
if vector.get_value('table_format').file_format == 'parquet':
create_stmt += " stored as parquet"
self.client.execute(create_stmt)
# Get a single row of data
col_vals = widetable.get_data(num_cols, 1, quote_strings=True)[0]
insert_stmt = "INSERT INTO " + table_name + " VALUES(" + col_vals + ")"
self.client.execute(insert_stmt)
result = self.client.execute("select count(*) from " + table_name)
assert result.data == ["1"]
result = self.client.execute("select * from " + table_name)
types = result.column_types
labels = result.column_labels
expected = QueryTestResult([col_vals], types, labels, order_matters=False)
actual = QueryTestResult(parse_result_rows(result), types, labels, order_matters=False)
assert expected == actual
def test_wide_table(self, vector):
NUM_COLS = vector.get_value("num_cols")
NUM_ROWS = 10
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)
types = parse_column_types(result.schema)
expected = QueryTestResult(expected_result, types, order_matters=False)
actual = QueryTestResult(parse_result_rows(result), types, order_matters=False)
assert expected == actual
def test_many_grouping_columns(self, vector):
"""Test that an aggregate with many grouping columns works"""
table_format = vector.get_value('table_format')
exec_option = vector.get_value('exec_option')
query = "select distinct * from widetable_1000_cols"
# Ensure codegen is enabled.
result = self.execute_query(query, exec_option, table_format=table_format)
# All rows should be distinct.
expected_result = widetable.get_data(1000, 10, quote_strings=True)
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_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