def test_decimal_type(self):
t1 = DataTypes.DECIMAL()
t2 = DataTypes.DECIMAL(10, 2)
self.assertTrue(t2 is not t1)
self.assertNotEqual(t1, t2)
t3 = DataTypes.DECIMAL(8)
self.assertNotEqual(t2, t3)
def test_atomic_type_with_data_type_with_parameters(self):
gateway = get_gateway()
JDataTypes = gateway.jvm.DataTypes
java_types = [
JDataTypes.TIME(3).notNull(),
JDataTypes.TIMESTAMP(3).notNull(),
JDataTypes.VARBINARY(100).notNull(),
JDataTypes.BINARY(2).notNull(),
JDataTypes.VARCHAR(30).notNull(),
JDataTypes.CHAR(50).notNull(),
JDataTypes.DECIMAL(20, 10).notNull()
]
converted_python_types = [
_from_java_data_type(item) for item in java_types
]
expected = [
DataTypes.TIME(3, False),
DataTypes.TIMESTAMP(3).not_null(),
DataTypes.VARBINARY(100, False),
DataTypes.BINARY(2, False),
DataTypes.VARCHAR(30, False),
DataTypes.CHAR(50, False),
DataTypes.DECIMAL(20, 10, False)
]
self.assertEqual(converted_python_types, expected)
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 test_csv_primitive_column(self):
schema = CsvSchema.builder() \
.add_number_column('tinyint', DataTypes.TINYINT()) \
.add_number_column('smallint', DataTypes.SMALLINT()) \
.add_number_column('int', DataTypes.INT()) \
.add_number_column('bigint', DataTypes.BIGINT()) \
.add_number_column('float', DataTypes.FLOAT()) \
.add_number_column('double', DataTypes.DOUBLE()) \
.add_number_column('decimal', DataTypes.DECIMAL(2, 0)) \
.add_boolean_column('boolean') \
.add_string_column('string') \
.build()
with open(self.csv_file_name, 'w') as f:
f.write('127,')
f.write('-32767,')
f.write('2147483647,')
f.write('-9223372036854775808,')
f.write('3e38,')
f.write('2e-308,')
f.write('1.5,')
f.write('true,')
f.write('string\n')
self._build_csv_job(schema)
self.env.execute('test_csv_primitive_column')
row = self.test_sink.get_results(True, False)[0]
self.assertEqual(row['tinyint'], 127)
self.assertEqual(row['smallint'], -32767)
self.assertEqual(row['int'], 2147483647)
self.assertEqual(row['bigint'], -9223372036854775808)
self.assertAlmostEqual(row['float'], 3e38, delta=1e31)
self.assertAlmostEqual(row['double'], 2e-308, delta=2e-301)
self.assertAlmostEqual(row['decimal'], 2)
self.assertEqual(row['boolean'], True)
self.assertEqual(row['string'], 'string')
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_atomic_type_with_data_type_with_parameters(self):
gateway = get_gateway()
JDataTypes = gateway.jvm.DataTypes
java_types = [
JDataTypes.TIME(3).notNull(),
JDataTypes.TIMESTAMP(3).notNull(),
JDataTypes.VARBINARY(100).notNull(),
JDataTypes.BINARY(2).notNull(),
JDataTypes.VARCHAR(30).notNull(),
JDataTypes.CHAR(50).notNull(),
JDataTypes.DECIMAL(20, 10).notNull()
]
converted_python_types = [_from_java_type(item) for item in java_types]
expected = [
DataTypes.TIME(3, False),
DataTypes.TIMESTAMP(3).not_null(),
DataTypes.VARBINARY(100, False),
DataTypes.BINARY(2, False),
DataTypes.VARCHAR(30, False),
DataTypes.CHAR(50, False),
DataTypes.DECIMAL(20, 10, False)
]
self.assertEqual(converted_python_types, expected)
# Legacy type tests
Types = gateway.jvm.org.apache.flink.table.api.Types
InternalBigDecimalTypeInfo = \
gateway.jvm.org.apache.flink.table.runtime.typeutils.BigDecimalTypeInfo
java_types = [
Types.STRING(),
Types.DECIMAL(),
InternalBigDecimalTypeInfo(12, 5)
]
converted_python_types = [_from_java_type(item) for item in java_types]
expected = [
DataTypes.VARCHAR(2147483647),
DataTypes.DECIMAL(38, 18),
DataTypes.DECIMAL(12, 5)
]
self.assertEqual(converted_python_types, expected)
def _create_parquet_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('binary', DataTypes.BINARY(10)),
DataTypes.FIELD('varbinary', DataTypes.VARBINARY(10)),
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('time', DataTypes.TIME().bridged_to('java.sql.Time')),
DataTypes.FIELD('timestamp', DataTypes.TIMESTAMP(3).bridged_to('java.sql.Timestamp')),
DataTypes.FIELD('timestamp_ltz', DataTypes.TIMESTAMP_LTZ(3)),
])
row_type_info = Types.ROW_NAMED(
['char', 'varchar', 'binary', 'varbinary', 'boolean', 'decimal', 'int', 'bigint', 'double',
'date', 'time', 'timestamp', 'timestamp_ltz'],
[Types.STRING(), Types.STRING(), Types.PRIMITIVE_ARRAY(Types.BYTE()),
Types.PRIMITIVE_ARRAY(Types.BYTE()), Types.BOOLEAN(), Types.BIG_DEC(), Types.INT(),
Types.LONG(), Types.DOUBLE(), Types.SQL_DATE(), Types.SQL_TIME(), Types.SQL_TIMESTAMP(),
Types.INSTANT()]
)
datetime_ltz = datetime.datetime(1970, 2, 3, 4, 5, 6, 700000, tzinfo=pytz.timezone('UTC'))
timestamp_ltz = Instant.of_epoch_milli(
(
calendar.timegm(datetime_ltz.utctimetuple()) +
calendar.timegm(time.localtime(0))
) * 1000 + datetime_ltz.microsecond // 1000
)
data = [Row(
char='char',
varchar='varchar',
binary=b'binary',
varbinary=b'varbinary',
boolean=True,
decimal=Decimal(1.5),
int=2147483647,
bigint=-9223372036854775808,
double=2e-308,
date=datetime.date(1970, 1, 1),
time=datetime.time(1, 1, 1),
timestamp=datetime.datetime(1970, 1, 2, 3, 4, 5, 600000),
timestamp_ltz=timestamp_ltz
)]
return row_type, row_type_info, data
def test_verify_type_not_nullable(self):
import array
import datetime
import decimal
schema = DataTypes.ROW([
DataTypes.FIELD('s', DataTypes.STRING(nullable=False)),
DataTypes.FIELD('i', DataTypes.INT(True))
])
class MyObj:
def __init__(self, **kwargs):
for k, v in kwargs.items():
setattr(self, k, v)
# obj, data_type
success_spec = [
# String
("", DataTypes.STRING()),
(u"", DataTypes.STRING()),
# UDT
(ExamplePoint(1.0, 2.0), ExamplePointUDT()),
# Boolean
(True, DataTypes.BOOLEAN()),
# TinyInt
(-(2**7), DataTypes.TINYINT()),
(2**7 - 1, DataTypes.TINYINT()),
# SmallInt
(-(2**15), DataTypes.SMALLINT()),
(2**15 - 1, DataTypes.SMALLINT()),
# Int
(-(2**31), DataTypes.INT()),
(2**31 - 1, DataTypes.INT()),
# BigInt
(2**64, DataTypes.BIGINT()),
# Float & Double
(1.0, DataTypes.FLOAT()),
(1.0, DataTypes.DOUBLE()),
# Decimal
(decimal.Decimal("1.0"), DataTypes.DECIMAL(10, 0)),
# Binary
(bytearray([1]), DataTypes.BINARY(1)),
# Date/Time/Timestamp
(datetime.date(2000, 1, 2), DataTypes.DATE()),
(datetime.datetime(2000, 1, 2, 3, 4), DataTypes.DATE()),
(datetime.time(1, 1, 2), DataTypes.TIME()),
(datetime.datetime(2000, 1, 2, 3, 4), DataTypes.TIMESTAMP()),
# Array
([], DataTypes.ARRAY(DataTypes.INT())),
(["1", None], DataTypes.ARRAY(DataTypes.STRING(nullable=True))),
([1, 2], DataTypes.ARRAY(DataTypes.INT())),
((1, 2), DataTypes.ARRAY(DataTypes.INT())),
(array.array('h', [1, 2]), DataTypes.ARRAY(DataTypes.INT())),
# Map
({}, DataTypes.MAP(DataTypes.STRING(), DataTypes.INT())),
({
"a": 1
}, DataTypes.MAP(DataTypes.STRING(), DataTypes.INT())),
({
"a": None
},
DataTypes.MAP(DataTypes.STRING(nullable=False),
DataTypes.INT(True))),
# Struct
({
"s": "a",
"i": 1
}, schema),
({
"s": "a",
"i": None
}, schema),
({
"s": "a"
}, schema),
({
"s": "a",
"f": 1.0
}, schema),
(Row(s="a", i=1), schema),
(Row(s="a", i=None), schema),
(Row(s="a", i=1, f=1.0), schema),
(["a", 1], schema),
(["a", None], schema),
(("a", 1), schema),
(MyObj(s="a", i=1), schema),
(MyObj(s="a", i=None), schema),
(MyObj(s="a"), schema),
]
# obj, data_type, exception class
failure_spec = [
# Char/VarChar (match anything but None)
(None, DataTypes.VARCHAR(1), ValueError),
(None, DataTypes.CHAR(1), ValueError),
# VarChar (length exceeds maximum length)
("abc", DataTypes.VARCHAR(1), ValueError),
# Char (length exceeds length)
("abc", DataTypes.CHAR(1), ValueError),
# UDT
(ExamplePoint(1.0, 2.0), PythonOnlyUDT(), ValueError),
# Boolean
(1, DataTypes.BOOLEAN(), TypeError),
("True", DataTypes.BOOLEAN(), TypeError),
([1], DataTypes.BOOLEAN(), TypeError),
# TinyInt
(-(2**7) - 1, DataTypes.TINYINT(), ValueError),
(2**7, DataTypes.TINYINT(), ValueError),
("1", DataTypes.TINYINT(), TypeError),
(1.0, DataTypes.TINYINT(), TypeError),
# SmallInt
(-(2**15) - 1, DataTypes.SMALLINT(), ValueError),
(2**15, DataTypes.SMALLINT(), ValueError),
# Int
(-(2**31) - 1, DataTypes.INT(), ValueError),
(2**31, DataTypes.INT(), ValueError),
# Float & Double
(1, DataTypes.FLOAT(), TypeError),
(1, DataTypes.DOUBLE(), TypeError),
# Decimal
(1.0, DataTypes.DECIMAL(10, 0), TypeError),
(1, DataTypes.DECIMAL(10, 0), TypeError),
("1.0", DataTypes.DECIMAL(10, 0), TypeError),
# Binary
(1, DataTypes.BINARY(1), TypeError),
# VarBinary (length exceeds maximum length)
(bytearray([1, 2]), DataTypes.VARBINARY(1), ValueError),
# Char (length exceeds length)
(bytearray([1, 2]), DataTypes.BINARY(1), ValueError),
# Date/Time/Timestamp
("2000-01-02", DataTypes.DATE(), TypeError),
("10:01:02", DataTypes.TIME(), TypeError),
(946811040, DataTypes.TIMESTAMP(), TypeError),
# Array
(["1", None], DataTypes.ARRAY(DataTypes.VARCHAR(1,
nullable=False)),
ValueError),
([1, "2"], DataTypes.ARRAY(DataTypes.INT()), TypeError),
# Map
({
"a": 1
}, DataTypes.MAP(DataTypes.INT(), DataTypes.INT()), TypeError),
({
"a": "1"
}, DataTypes.MAP(DataTypes.VARCHAR(1),
DataTypes.INT()), TypeError),
({
"a": None
}, DataTypes.MAP(DataTypes.VARCHAR(1),
DataTypes.INT(False)), ValueError),
# Struct
({
"s": "a",
"i": "1"
}, schema, TypeError),
(Row(s="a"), schema, ValueError), # Row can't have missing field
(Row(s="a", i="1"), schema, TypeError),
(["a"], schema, ValueError),
(["a", "1"], schema, TypeError),
(MyObj(s="a", i="1"), schema, TypeError),
(MyObj(s=None, i="1"), schema, ValueError),
]
# Check success cases
for obj, data_type in success_spec:
try:
_create_type_verifier(data_type.not_null())(obj)
except (TypeError, ValueError):
self.fail("verify_type(%s, %s, nullable=False)" %
(obj, data_type))
# Check failure cases
for obj, data_type, exp in failure_spec:
msg = "verify_type(%s, %s, nullable=False) == %s" % (
obj, data_type, exp)
with self.assertRaises(exp, msg=msg):
_create_type_verifier(data_type.not_null())(obj)
