def test_map_function_without_data_types(self): self.env.set_parallelism(1) ds = self.env.from_collection([('ab', decimal.Decimal(1)), ('bdc', decimal.Decimal(2)), ('cfgs', decimal.Decimal(3)), ('deeefg', decimal.Decimal(4))], type_info=Types.ROW( [Types.STRING(), Types.BIG_DEC()])) ds.map(MyMapFunction()).add_sink(self.test_sink) self.env.execute('map_function_test') results = self.test_sink.get_results(True) expected = [ "<Row('ab', 2, Decimal('1'))>", "<Row('bdc', 3, Decimal('2'))>", "<Row('cfgs', 4, Decimal('3'))>", "<Row('deeefg', 6, Decimal('4'))>" ] expected.sort() results.sort() self.assertEqual(expected, results)
def test_map_function_without_data_types(self): self.env.set_parallelism(1) ds = self.env.from_collection([('ab', decimal.Decimal(1)), ('bdc', decimal.Decimal(2)), ('cfgs', decimal.Decimal(3)), ('deeefg', decimal.Decimal(4))], type_info=Types.ROW( [Types.STRING(), Types.BIG_DEC()])) mapped_stream = ds.map(MyMapFunction()) collect_util = DataStreamCollectUtil() collect_util.collect(mapped_stream) self.env.execute('map_function_test') results = collect_util.results() expected = [ "('ab', 2, Decimal('1'))", "('bdc', 3, Decimal('2'))", "('cfgs', 4, Decimal('3'))", "('deeefg', 6, Decimal('4'))" ] expected.sort() results.sort() self.assertEqual(expected, results)
def test_from_java_type(self): basic_int_type_info = Types.INT() self.assertEqual(basic_int_type_info, _from_java_type(basic_int_type_info.get_java_type_info())) basic_short_type_info = Types.SHORT() self.assertEqual(basic_short_type_info, _from_java_type(basic_short_type_info.get_java_type_info())) basic_long_type_info = Types.LONG() self.assertEqual(basic_long_type_info, _from_java_type(basic_long_type_info.get_java_type_info())) basic_float_type_info = Types.FLOAT() self.assertEqual(basic_float_type_info, _from_java_type(basic_float_type_info.get_java_type_info())) basic_double_type_info = Types.DOUBLE() self.assertEqual(basic_double_type_info, _from_java_type(basic_double_type_info.get_java_type_info())) basic_char_type_info = Types.CHAR() self.assertEqual(basic_char_type_info, _from_java_type(basic_char_type_info.get_java_type_info())) basic_byte_type_info = Types.BYTE() self.assertEqual(basic_byte_type_info, _from_java_type(basic_byte_type_info.get_java_type_info())) basic_big_int_type_info = Types.BIG_INT() self.assertEqual(basic_big_int_type_info, _from_java_type(basic_big_int_type_info.get_java_type_info())) basic_big_dec_type_info = Types.BIG_DEC() self.assertEqual(basic_big_dec_type_info, _from_java_type(basic_big_dec_type_info.get_java_type_info())) basic_sql_date_type_info = Types.SQL_DATE() self.assertEqual(basic_sql_date_type_info, _from_java_type(basic_sql_date_type_info.get_java_type_info())) basic_sql_time_type_info = Types.SQL_TIME() self.assertEqual(basic_sql_time_type_info, _from_java_type(basic_sql_time_type_info.get_java_type_info())) basic_sql_timestamp_type_info = Types.SQL_TIMESTAMP() self.assertEqual(basic_sql_timestamp_type_info, _from_java_type(basic_sql_timestamp_type_info.get_java_type_info())) row_type_info = Types.ROW([Types.INT(), Types.STRING()]) self.assertEqual(row_type_info, _from_java_type(row_type_info.get_java_type_info())) tuple_type_info = Types.TUPLE([Types.CHAR(), Types.INT()]) self.assertEqual(tuple_type_info, _from_java_type(tuple_type_info.get_java_type_info())) primitive_int_array_type_info = Types.PRIMITIVE_ARRAY(Types.INT()) self.assertEqual(primitive_int_array_type_info, _from_java_type(primitive_int_array_type_info.get_java_type_info())) object_array_type_info = Types.OBJECT_ARRAY(Types.SQL_DATE()) self.assertEqual(object_array_type_info, _from_java_type(object_array_type_info.get_java_type_info())) pickled_byte_array_type_info = Types.PICKLED_BYTE_ARRAY() self.assertEqual(pickled_byte_array_type_info, _from_java_type(pickled_byte_array_type_info.get_java_type_info())) sql_date_type_info = Types.SQL_DATE() self.assertEqual(sql_date_type_info, _from_java_type(sql_date_type_info.get_java_type_info())) map_type_info = Types.MAP(Types.INT(), Types.STRING()) self.assertEqual(map_type_info, _from_java_type(map_type_info.get_java_type_info())) list_type_info = Types.LIST(Types.INT()) self.assertEqual(list_type_info, _from_java_type(list_type_info.get_java_type_info()))
def test_from_collection_with_data_types(self): # verify from_collection for the collection with single object. ds = self.env.from_collection(['Hi', 'Hello'], type_info=Types.STRING()) ds.add_sink(self.test_sink) self.env.execute("test from collection with single object") results = self.test_sink.get_results(False) expected = ['Hello', 'Hi'] results.sort() expected.sort() self.assertEqual(expected, results) # verify from_collection for the collection with multiple objects like tuple. ds = self.env.from_collection( [(1, None, 1, True, 32767, -2147483648, 1.23, 1.98932, bytearray(b'flink'), 'pyflink', datetime.date(2014, 9, 13), datetime.time(hour=12, minute=0, second=0, microsecond=123000), datetime.datetime(2018, 3, 11, 3, 0, 0, 123000), [1, 2, 3], decimal.Decimal('1000000000000000000.05'), decimal.Decimal('1000000000000000000.0599999999999' '9999899999999999')), (2, None, 2, True, 43878, 9147483648, 9.87, 2.98936, bytearray(b'flink'), 'pyflink', datetime.date(2015, 10, 14), datetime.time(hour=11, minute=2, second=2, microsecond=234500), datetime.datetime(2020, 4, 15, 8, 2, 6, 235000), [2, 4, 6], decimal.Decimal('2000000000000000000.74'), decimal.Decimal('2000000000000000000.061111111111111' '11111111111111'))], type_info=Types.ROW([ Types.LONG(), Types.LONG(), Types.SHORT(), Types.BOOLEAN(), Types.SHORT(), Types.INT(), Types.FLOAT(), Types.DOUBLE(), Types.PICKLED_BYTE_ARRAY(), Types.STRING(), Types.SQL_DATE(), Types.SQL_TIME(), Types.SQL_TIMESTAMP(), Types.BASIC_ARRAY(Types.LONG()), Types.BIG_DEC(), Types.BIG_DEC() ])) ds.add_sink(self.test_sink) self.env.execute("test from collection with tuple object") results = self.test_sink.get_results(False) # if user specifies data types of input data, the collected result should be in row format. expected = [ '+I[1, null, 1, true, 32767, -2147483648, 1.23, 1.98932, [102, 108, 105, 110, 107], ' 'pyflink, 2014-09-13, 12:00:00, 2018-03-11 03:00:00.123, [1, 2, 3], ' '1000000000000000000.05, 1000000000000000000.05999999999999999899999999999]', '+I[2, null, 2, true, -21658, 557549056, 9.87, 2.98936, [102, 108, 105, 110, 107], ' 'pyflink, 2015-10-14, 11:02:02, 2020-04-15 08:02:06.235, [2, 4, 6], ' '2000000000000000000.74, 2000000000000000000.06111111111111111111111111111]' ] results.sort() expected.sort() self.assertEqual(expected, results)