def test_cython_row_coder(self):
from pyflink.common import Row, RowKind
field_count = 15
field_names = ['f{}'.format(i) for i in range(field_count)]
row = Row(**{
field_names[i]: None if i % 2 == 0 else i
for i in range(field_count)
})
data = [row]
python_field_coders = [
coder_impl.RowCoderImpl(
[coder_impl.BigIntCoderImpl() for _ in range(field_count)],
row._fields)
]
cython_field_coders = [
coder_impl_fast.RowCoderImpl([
coder_impl_fast.BigIntCoderImpl() for _ in range(field_count)
], row._fields)
]
row.set_row_kind(RowKind.INSERT)
self.check_cython_coder(python_field_coders, cython_field_coders, data)
row.set_row_kind(RowKind.UPDATE_BEFORE)
self.check_cython_coder(python_field_coders, cython_field_coders, data)
row.set_row_kind(RowKind.UPDATE_AFTER)
self.check_cython_coder(python_field_coders, cython_field_coders, data)
row.set_row_kind(RowKind.DELETE)
self.check_cython_coder(python_field_coders, cython_field_coders, data)
def test_cython_array_coder(self):
data = [[1, 2, 3, None]]
python_field_coders = [coder_impl.ArrayCoderImpl(coder_impl.BigIntCoderImpl())
for _ in range(len(data))]
cython_field_coders = [coder_impl_fast.ArrayCoderImpl(coder_impl_fast.BigIntCoderImpl())
for _ in range(len(data))]
self.check_cython_coder(python_field_coders, cython_field_coders, [data])
def test_cython_row_coder(self):
from pyflink.common import Row, RowKind
field_count = 2
row = Row(*[None if i % 2 == 0 else i for i in range(field_count)])
data = [row]
python_field_coders = [
coder_impl.RowCoderImpl(
[coder_impl.BigIntCoderImpl() for _ in range(field_count)])
]
cython_field_coders = [
coder_impl_fast.RowCoderImpl([
coder_impl_fast.BigIntCoderImpl() for _ in range(field_count)
])
]
row.set_row_kind(RowKind.INSERT)
self.check_cython_coder(python_field_coders, cython_field_coders,
[data])
row.set_row_kind(RowKind.UPDATE_BEFORE)
self.check_cython_coder(python_field_coders, cython_field_coders,
[data])
row.set_row_kind(RowKind.UPDATE_AFTER)
self.check_cython_coder(python_field_coders, cython_field_coders,
[data])
row.set_row_kind(RowKind.DELETE)
self.check_cython_coder(python_field_coders, cython_field_coders,
[data])
def test_cython_bigint_coder(self):
data = [1, 100, -100, -1000]
python_field_coders = [
coder_impl.BigIntCoderImpl() for _ in range(len(data))
]
cython_field_coders = [
coder_impl_fast.BigIntCoderImpl() for _ in range(len(data))
]
self.check_cython_coder(python_field_coders, cython_field_coders, data)
def test_cython_map_coder(self):
data = [{'flink': 1, 'pyflink': 2, 'coder': None}]
python_field_coders = [coder_impl.MapCoderImpl(coder_impl.CharCoderImpl(),
coder_impl.BigIntCoderImpl())
for _ in range(len(data))]
cython_field_coders = [coder_impl_fast.MapCoderImpl(coder_impl_fast.CharCoderImpl(),
coder_impl_fast.BigIntCoderImpl())
for _ in range(len(data))]
self.check_cython_coder(python_field_coders, cython_field_coders, [data])
def test_cython_row_coder(self):
from pyflink.table import Row
field_count = 2
data = [Row(*[None if i % 2 == 0 else i for i in range(field_count)])]
python_field_coders = [coder_impl.RowCoderImpl([coder_impl.BigIntCoderImpl()
for _ in range(field_count)])]
cython_field_coders = [coder_impl_fast.RowCoderImpl([coder_impl_fast.BigIntCoderImpl()
for _ in range(field_count)])]
self.check_cython_coder(python_field_coders, cython_field_coders, [data])
def test_cython_primitive_array_coder(self):
data = [[1, 2, 3, 4]]
python_field_coders = [
coder_impl.PrimitiveArrayCoderImpl(coder_impl.BigIntCoderImpl())
for _ in range(len(data))
]
cython_field_coders = [
coder_impl_fast.PrimitiveArrayCoderImpl(
coder_impl_fast.BigIntCoderImpl()) for _ in range(len(data))
]
self.check_cython_coder(python_field_coders, cython_field_coders, data)
def test_cython_coder_with_wrong_result_type(self):
from apache_beam.coders.coder_impl import create_OutputStream
from pyflink.fn_execution.beam.beam_stream import BeamOutputStream
data = ['1']
cython_field_coders = [
coder_impl_fast.BigIntCoderImpl() for _ in range(len(data))
]
cy_flatten_row_coder = coder_impl_fast.FlattenRowCoderImpl(
cython_field_coders)
beam_output_stream = create_OutputStream()
output_stream = BeamOutputStream(beam_output_stream)
with self.assertRaises(TypeError) as context:
cy_flatten_row_coder.encode_to_stream(data, output_stream)
self.assertIn('an integer is required', str(context.exception))
def get_impl(self):
return coder_impl.BigIntCoderImpl()
