def test_basic_array_type_info(self):
ds = self.env.from_collection(
[(1, [1.1, None, 1.30], [None, 'hi', 'flink']),
(2, [None, 2.2, 2.3], ['hello', None, 'flink']),
(3, [3.1, 3.2, None], ['hello', 'hi', None])],
type_info=Types.ROW([
Types.INT(),
Types.BASIC_ARRAY(Types.FLOAT()),
Types.BASIC_ARRAY(Types.STRING())
]))
ds.map(lambda x: x, output_type=Types.ROW([Types.INT(),
Types.BASIC_ARRAY(Types.FLOAT()),
Types.BASIC_ARRAY(Types.STRING())]))\
.add_sink(self.test_sink)
self.env.execute("test basic array type info")
results = self.test_sink.get_results()
expected = [
'1,[1.1, null, 1.3],[null, hi, flink]',
'2,[null, 2.2, 2.3],[hello, null, flink]',
'3,[3.1, 3.2, null],[hello, hi, null]'
]
results.sort()
expected.sort()
self.assertEqual(expected, results)
def test_primitive_array_type_info(self):
ds = self.env.from_collection([(1, [1.1, 1.2, 1.30]), (2, [2.1, 2.2, 2.3]),
(3, [3.1, 3.2, 3.3])],
type_info=Types.ROW([Types.INT(),
Types.PRIMITIVE_ARRAY(Types.FLOAT())]))
ds.map(lambda x: x, output_type=Types.ROW([Types.INT(),
Types.PRIMITIVE_ARRAY(Types.FLOAT())]))\
.add_sink(self.test_sink)
self.env.execute("test primitive array type info")
results = self.test_sink.get_results()
expected = ['1,[1.1, 1.2, 1.3]', '2,[2.1, 2.2, 2.3]', '3,[3.1, 3.2, 3.3]']
results.sort()
expected.sort()
self.assertEqual(expected, results)
def event_timer_timer_demo():
env = StreamExecutionEnvironment.get_execution_environment()
ds = env.from_collection(
collection=[
(1000, 'Alice', 110.1),
(4000, 'Bob', 30.2),
(3000, 'Alice', 20.0),
(2000, 'Bob', 53.1),
(5000, 'Alice', 13.1),
(3000, 'Bob', 3.1),
(7000, 'Bob', 16.1),
(10000, 'Alice', 20.1)
],
type_info=Types.TUPLE([Types.LONG(), Types.STRING(), Types.FLOAT()]))
ds = ds.assign_timestamps_and_watermarks(
WatermarkStrategy.for_bounded_out_of_orderness(Duration.of_seconds(2))
.with_timestamp_assigner(MyTimestampAssigner()))
# apply the process function onto a keyed stream
ds.key_by(lambda value: value[1]) \
.process(Sum()) \
.print()
# submit for execution
env.execute()
def pickled_bytes_to_python_converter(data, field_type):
if isinstance(field_type, RowTypeInfo):
data = zip(list(data[1:]), field_type.get_field_types())
fields = []
for d, d_type in data:
fields.append(pickled_bytes_to_python_converter(d, d_type))
return tuple(fields)
else:
data = pickle.loads(data)
if field_type == Types.SQL_TIME():
seconds, microseconds = divmod(data, 10**6)
minutes, seconds = divmod(seconds, 60)
hours, minutes = divmod(minutes, 60)
return datetime.time(hours, minutes, seconds, microseconds)
elif field_type == Types.SQL_DATE():
return field_type.from_internal_type(data)
elif field_type == Types.SQL_TIMESTAMP():
return field_type.from_internal_type(int(data.timestamp() * 10**6))
elif field_type == Types.FLOAT():
return field_type.from_internal_type(ast.literal_eval(data))
elif is_basic_array_type_info(
field_type) or is_primitive_array_type_info(field_type):
element_type = typeinfo._from_java_type(
field_type.get_java_type_info().getComponentInfo())
elements = []
for element_bytes in data:
elements.append(
pickled_bytes_to_python_converter(element_bytes,
element_type))
return elements
else:
return field_type.from_internal_type(data)
def open(self, runtime_context: RuntimeContext):
state_descriptor = ValueStateDescriptor("state", Types.FLOAT())
state_ttl_config = StateTtlConfig \
.new_builder(Time.seconds(1)) \
.set_update_type(StateTtlConfig.UpdateType.OnReadAndWrite) \
.disable_cleanup_in_background() \
.build()
state_descriptor.enable_time_to_live(state_ttl_config)
self.state = runtime_context.get_state(state_descriptor)
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)
def pickled_bytes_to_python_converter(data, field_type):
if isinstance(field_type, RowTypeInfo):
row_kind = RowKind(int.from_bytes(data[0], 'little'))
data = zip(list(data[1:]), field_type.get_field_types())
fields = []
for d, d_type in data:
fields.append(pickled_bytes_to_python_converter(d, d_type))
row = Row.of_kind(row_kind, *fields)
return row
else:
data = pickle.loads(data)
if field_type == Types.SQL_TIME():
seconds, microseconds = divmod(data, 10**6)
minutes, seconds = divmod(seconds, 60)
hours, minutes = divmod(minutes, 60)
return datetime.time(hours, minutes, seconds, microseconds)
elif field_type == Types.SQL_DATE():
return field_type.from_internal_type(data)
elif field_type == Types.SQL_TIMESTAMP():
return field_type.from_internal_type(int(data.timestamp() * 10**6))
elif field_type == Types.FLOAT():
return field_type.from_internal_type(ast.literal_eval(data))
elif isinstance(
field_type,
(BasicArrayTypeInfo, PrimitiveArrayTypeInfo, ObjectArrayTypeInfo)):
element_type = field_type._element_type
elements = []
for element_bytes in data:
elements.append(
pickled_bytes_to_python_converter(element_bytes,
element_type))
return elements
elif isinstance(field_type, MapTypeInfo):
key_type = field_type._key_type_info
value_type = field_type._value_type_info
zip_kv = zip(data[0], data[1])
return dict((pickled_bytes_to_python_converter(k, key_type),
pickled_bytes_to_python_converter(v, value_type))
for k, v in zip_kv)
elif isinstance(field_type, ListTypeInfo):
element_type = field_type.elem_type
elements = []
for element_bytes in data:
elements.append(
pickled_bytes_to_python_converter(element_bytes,
element_type))
return elements
else:
return field_type.from_internal_type(data)
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 to_java_typeinfo(type_info: TypeInformation):
if isinstance(type_info, BasicTypeInfo):
basic_type = type_info._basic_type
if basic_type == BasicType.STRING:
j_typeinfo = JTypes.STRING
elif basic_type == BasicType.BYTE:
j_typeinfo = JTypes.LONG
elif basic_type == BasicType.BOOLEAN:
j_typeinfo = JTypes.BOOLEAN
elif basic_type == BasicType.SHORT:
j_typeinfo = JTypes.LONG
elif basic_type == BasicType.INT:
j_typeinfo = JTypes.LONG
elif basic_type == BasicType.LONG:
j_typeinfo = JTypes.LONG
elif basic_type == BasicType.FLOAT:
j_typeinfo = JTypes.DOUBLE
elif basic_type == BasicType.DOUBLE:
j_typeinfo = JTypes.DOUBLE
elif basic_type == BasicType.CHAR:
j_typeinfo = JTypes.STRING
elif basic_type == BasicType.BIG_INT:
j_typeinfo = JTypes.BIG_INT
elif basic_type == BasicType.BIG_DEC:
j_typeinfo = JTypes.BIG_DEC
elif basic_type == BasicType.INSTANT:
j_typeinfo = JTypes.INSTANT
else:
raise TypeError("Invalid BasicType %s." % basic_type)
elif isinstance(type_info, PrimitiveArrayTypeInfo):
element_type = type_info._element_type
if element_type == Types.BOOLEAN():
j_typeinfo = JPrimitiveArrayTypeInfo.BOOLEAN_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.BYTE():
j_typeinfo = JPrimitiveArrayTypeInfo.BYTE_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.SHORT():
j_typeinfo = JPrimitiveArrayTypeInfo.SHORT_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.INT():
j_typeinfo = JPrimitiveArrayTypeInfo.INT_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.LONG():
j_typeinfo = JPrimitiveArrayTypeInfo.LONG_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.FLOAT():
j_typeinfo = JPrimitiveArrayTypeInfo.FLOAT_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.DOUBLE():
j_typeinfo = JPrimitiveArrayTypeInfo.DOUBLE_PRIMITIVE_ARRAY_TYPE_INFO
elif element_type == Types.CHAR():
j_typeinfo = JPrimitiveArrayTypeInfo.CHAR_PRIMITIVE_ARRAY_TYPE_INFO
else:
raise TypeError("Invalid element type for a primitive array.")
elif isinstance(type_info, BasicArrayTypeInfo):
element_type = type_info._element_type
if element_type == Types.BOOLEAN():
j_typeinfo = JBasicArrayTypeInfo.BOOLEAN_ARRAY_TYPE_INFO
elif element_type == Types.BYTE():
j_typeinfo = JBasicArrayTypeInfo.BYTE_ARRAY_TYPE_INFO
elif element_type == Types.SHORT():
j_typeinfo = JBasicArrayTypeInfo.SHORT_ARRAY_TYPE_INFO
elif element_type == Types.INT():
j_typeinfo = JBasicArrayTypeInfo.INT_ARRAY_TYPE_INFO
elif element_type == Types.LONG():
j_typeinfo = JBasicArrayTypeInfo.LONG_ARRAY_TYPE_INFO
elif element_type == Types.FLOAT():
j_typeinfo = JBasicArrayTypeInfo.FLOAT_ARRAY_TYPE_INFO
elif element_type == Types.DOUBLE():
j_typeinfo = JBasicArrayTypeInfo.DOUBLE_ARRAY_TYPE_INFO
elif element_type == Types.CHAR():
j_typeinfo = JBasicArrayTypeInfo.CHAR_ARRAY_TYPE_INFO
elif element_type == Types.STRING():
j_typeinfo = JBasicArrayTypeInfo.STRING_ARRAY_TYPE_INFO
else:
raise TypeError("Invalid element type for a basic array.")
elif isinstance(type_info, ObjectArrayTypeInfo):
element_type = type_info._element_type
j_typeinfo = JTypes.OBJECT_ARRAY(to_java_typeinfo(element_type))
elif isinstance(type_info, MapTypeInfo):
j_key_typeinfo = to_java_typeinfo(type_info._key_type_info)
j_value_typeinfo = to_java_typeinfo(type_info._value_type_info)
j_typeinfo = JMapTypeInfo(j_key_typeinfo, j_value_typeinfo)
else:
j_typeinfo = JPickledByteArrayTypeInfo.PICKLED_BYTE_ARRAY_TYPE_INFO
return j_typeinfo
