def setUpClass(cls):
super(PandasConversionTestBase, cls).setUpClass()
cls.data = [(1, 1, 1, 1, True, 1.1, 1.2, 'hello', bytearray(b"aaa"),
decimal.Decimal('1000000000000000000.01'), datetime.date(2014, 9, 13),
datetime.time(hour=1, minute=0, second=1),
datetime.datetime(1970, 1, 1, 0, 0, 0, 123000), ['hello', '中文'],
Row(a=1, b='hello', c=datetime.datetime(1970, 1, 1, 0, 0, 0, 123000),
d=[1, 2])),
(1, 2, 2, 2, False, 2.1, 2.2, 'world', bytearray(b"bbb"),
decimal.Decimal('1000000000000000000.02'), datetime.date(2014, 9, 13),
datetime.time(hour=1, minute=0, second=1),
datetime.datetime(1970, 1, 1, 0, 0, 0, 123000), ['hello', '中文'],
Row(a=1, b='hello', c=datetime.datetime(1970, 1, 1, 0, 0, 0, 123000),
d=[1, 2]))]
cls.data_type = DataTypes.ROW(
[DataTypes.FIELD("f1", DataTypes.TINYINT()),
DataTypes.FIELD("f2", DataTypes.SMALLINT()),
DataTypes.FIELD("f3", DataTypes.INT()),
DataTypes.FIELD("f4", DataTypes.BIGINT()),
DataTypes.FIELD("f5", DataTypes.BOOLEAN()),
DataTypes.FIELD("f6", DataTypes.FLOAT()),
DataTypes.FIELD("f7", DataTypes.DOUBLE()),
DataTypes.FIELD("f8", DataTypes.STRING()),
DataTypes.FIELD("f9", DataTypes.BYTES()),
DataTypes.FIELD("f10", DataTypes.DECIMAL(38, 18)),
DataTypes.FIELD("f11", DataTypes.DATE()),
DataTypes.FIELD("f12", DataTypes.TIME()),
DataTypes.FIELD("f13", DataTypes.TIMESTAMP(3)),
DataTypes.FIELD("f14", DataTypes.ARRAY(DataTypes.STRING())),
DataTypes.FIELD("f15", DataTypes.ROW(
[DataTypes.FIELD("a", DataTypes.INT()),
DataTypes.FIELD("b", DataTypes.STRING()),
DataTypes.FIELD("c", DataTypes.TIMESTAMP(3)),
DataTypes.FIELD("d", DataTypes.ARRAY(DataTypes.INT()))]))], False)
cls.pdf = cls.create_pandas_data_frame()
def _create_orc_basic_row_and_data() -> Tuple[RowType, RowTypeInfo, List[Row]]:
row_type = DataTypes.ROW([
DataTypes.FIELD('char', DataTypes.CHAR(10)),
DataTypes.FIELD('varchar', DataTypes.VARCHAR(10)),
DataTypes.FIELD('bytes', DataTypes.BYTES()),
DataTypes.FIELD('boolean', DataTypes.BOOLEAN()),
DataTypes.FIELD('decimal', DataTypes.DECIMAL(2, 0)),
DataTypes.FIELD('int', DataTypes.INT()),
DataTypes.FIELD('bigint', DataTypes.BIGINT()),
DataTypes.FIELD('double', DataTypes.DOUBLE()),
DataTypes.FIELD('date', DataTypes.DATE().bridged_to('java.sql.Date')),
DataTypes.FIELD('timestamp', DataTypes.TIMESTAMP(3).bridged_to('java.sql.Timestamp')),
])
row_type_info = Types.ROW_NAMED(
['char', 'varchar', 'bytes', 'boolean', 'decimal', 'int', 'bigint', 'double',
'date', 'timestamp'],
[Types.STRING(), Types.STRING(), Types.PRIMITIVE_ARRAY(Types.BYTE()), Types.BOOLEAN(),
Types.BIG_DEC(), Types.INT(), Types.LONG(), Types.DOUBLE(), Types.SQL_DATE(),
Types.SQL_TIMESTAMP()]
)
data = [Row(
char='char',
varchar='varchar',
bytes=b'varbinary',
boolean=True,
decimal=Decimal(1.5),
int=2147483647,
bigint=-9223372036854775808,
double=2e-308,
date=date(1970, 1, 1),
timestamp=datetime(1970, 1, 2, 3, 4, 5, 600000),
)]
return row_type, row_type_info, data
def test_basic_type(self):
test_types = [DataTypes.STRING(),
DataTypes.BOOLEAN(),
DataTypes.BYTES(),
DataTypes.TINYINT(),
DataTypes.SMALLINT(),
DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.FLOAT(),
DataTypes.DOUBLE(),
DataTypes.DATE(),
DataTypes.TIME(),
DataTypes.TIMESTAMP(3)]
java_types = [_to_java_type(item) for item in test_types]
converted_python_types = [_from_java_type(item) for item in java_types]
self.assertEqual(test_types, converted_python_types)
