def create_operation(operation_name,
spec,
counter_factory,
step_name,
state_sampler,
test_shuffle_source=None,
test_shuffle_sink=None,
is_streaming=False):
"""Create Operation object for given operation specification."""
if isinstance(spec, operation_specs.WorkerRead):
if isinstance(spec.source, iobase.SourceBundle):
op = ReadOperation(operation_name, spec, counter_factory,
state_sampler)
else:
from dataflow_worker.native_operations import NativeReadOperation
op = NativeReadOperation(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerWrite):
from dataflow_worker.native_operations import NativeWriteOperation
op = NativeWriteOperation(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerCombineFn):
op = CombineOperation(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerPartialGroupByKey):
op = create_pgbk_op(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerDoFn):
op = DoOperation(operation_name, spec, counter_factory, state_sampler)
elif isinstance(spec, operation_specs.WorkerGroupingShuffleRead):
from dataflow_worker.shuffle_operations import GroupedShuffleReadOperation
op = GroupedShuffleReadOperation(operation_name,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerUngroupedShuffleRead):
from dataflow_worker.shuffle_operations import UngroupedShuffleReadOperation
op = UngroupedShuffleReadOperation(operation_name,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerInMemoryWrite):
op = InMemoryWriteOperation(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerShuffleWrite):
from dataflow_worker.shuffle_operations import ShuffleWriteOperation
op = ShuffleWriteOperation(operation_name,
spec,
counter_factory,
state_sampler,
shuffle_sink=test_shuffle_sink)
elif isinstance(spec, operation_specs.WorkerFlatten):
op = FlattenOperation(operation_name, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerMergeWindows):
from dataflow_worker.shuffle_operations import BatchGroupAlsoByWindowsOperation
from dataflow_worker.shuffle_operations import StreamingGroupAlsoByWindowsOperation
if is_streaming:
op = StreamingGroupAlsoByWindowsOperation(operation_name, spec,
counter_factory,
state_sampler)
else:
op = BatchGroupAlsoByWindowsOperation(operation_name, spec,
counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerReifyTimestampAndWindows):
from dataflow_worker.shuffle_operations import ReifyTimestampAndWindowsOperation
op = ReifyTimestampAndWindowsOperation(operation_name, spec,
counter_factory, state_sampler)
else:
raise TypeError(
'Expected an instance of operation_specs.Worker* class '
'instead of %s' % (spec, ))
op.step_name = step_name
op.metrics_container = MetricsContainer(step_name)
op.scoped_metrics_container = ScopedMetricsContainer(op.metrics_container)
return op
def create_operation(name_context,
spec,
counter_factory,
step_name,
state_sampler,
test_shuffle_source=None,
test_shuffle_sink=None,
is_streaming=False):
"""Create Operation object for given operation specification."""
if not isinstance(name_context, common.NameContext):
# TODO(BEAM-4028): Remove ad-hoc NameContext once all has been migrated.
name_context = common.DataflowNameContext(step_name=name_context,
user_name=step_name,
system_name=None)
if isinstance(spec, operation_specs.WorkerRead):
if isinstance(spec.source, iobase.SourceBundle):
op = ReadOperation(name_context, spec, counter_factory,
state_sampler)
else:
from dataflow_worker.native_operations import NativeReadOperation
op = NativeReadOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerWrite):
from dataflow_worker.native_operations import NativeWriteOperation
op = NativeWriteOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerCombineFn):
op = CombineOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerPartialGroupByKey):
op = create_pgbk_op(name_context, spec, counter_factory, state_sampler)
elif isinstance(spec, operation_specs.WorkerDoFn):
op = DoOperation(name_context, spec, counter_factory, state_sampler)
elif isinstance(spec, operation_specs.WorkerGroupingShuffleRead):
from dataflow_worker.shuffle_operations import GroupedShuffleReadOperation
op = GroupedShuffleReadOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerUngroupedShuffleRead):
from dataflow_worker.shuffle_operations import UngroupedShuffleReadOperation
op = UngroupedShuffleReadOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerInMemoryWrite):
op = InMemoryWriteOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerShuffleWrite):
from dataflow_worker.shuffle_operations import ShuffleWriteOperation
op = ShuffleWriteOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_sink=test_shuffle_sink)
elif isinstance(spec, operation_specs.WorkerFlatten):
op = FlattenOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerMergeWindows):
from dataflow_worker.shuffle_operations import BatchGroupAlsoByWindowsOperation
from dataflow_worker.shuffle_operations import StreamingGroupAlsoByWindowsOperation
if is_streaming:
op = StreamingGroupAlsoByWindowsOperation(name_context, spec,
counter_factory,
state_sampler)
else:
op = BatchGroupAlsoByWindowsOperation(name_context, spec,
counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerReifyTimestampAndWindows):
from dataflow_worker.shuffle_operations import ReifyTimestampAndWindowsOperation
op = ReifyTimestampAndWindowsOperation(name_context, spec,
counter_factory, state_sampler)
else:
raise TypeError(
'Expected an instance of operation_specs.Worker* class '
'instead of %s' % (spec, ))
return op
def create_operation(name_context,
spec,
counter_factory,
step_name=None,
state_sampler=None,
test_shuffle_source=None,
test_shuffle_sink=None,
is_streaming=False):
# type: (...) -> Operation
"""Create Operation object for given operation specification."""
# TODO(pabloem): Document arguments to this function call.
if not isinstance(name_context, common.NameContext):
name_context = common.NameContext(step_name=name_context)
if isinstance(spec, operation_specs.WorkerRead):
if isinstance(spec.source, iobase.SourceBundle):
op = ReadOperation(name_context, spec, counter_factory,
state_sampler) # type: Operation
else:
from dataflow_worker.native_operations import NativeReadOperation
op = NativeReadOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerWrite):
from dataflow_worker.native_operations import NativeWriteOperation
op = NativeWriteOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerCombineFn):
op = CombineOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerPartialGroupByKey):
op = create_pgbk_op(name_context, spec, counter_factory, state_sampler)
elif isinstance(spec, operation_specs.WorkerDoFn):
op = DoOperation(name_context, spec, counter_factory, state_sampler)
elif isinstance(spec, operation_specs.WorkerGroupingShuffleRead):
from dataflow_worker.shuffle_operations import GroupedShuffleReadOperation
op = GroupedShuffleReadOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerUngroupedShuffleRead):
from dataflow_worker.shuffle_operations import UngroupedShuffleReadOperation
op = UngroupedShuffleReadOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_source=test_shuffle_source)
elif isinstance(spec, operation_specs.WorkerInMemoryWrite):
op = InMemoryWriteOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerShuffleWrite):
from dataflow_worker.shuffle_operations import ShuffleWriteOperation
op = ShuffleWriteOperation(name_context,
spec,
counter_factory,
state_sampler,
shuffle_sink=test_shuffle_sink)
elif isinstance(spec, operation_specs.WorkerFlatten):
op = FlattenOperation(name_context, spec, counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerMergeWindows):
from dataflow_worker.shuffle_operations import BatchGroupAlsoByWindowsOperation
from dataflow_worker.shuffle_operations import StreamingGroupAlsoByWindowsOperation
if is_streaming:
op = StreamingGroupAlsoByWindowsOperation(name_context, spec,
counter_factory,
state_sampler)
else:
op = BatchGroupAlsoByWindowsOperation(name_context, spec,
counter_factory,
state_sampler)
elif isinstance(spec, operation_specs.WorkerReifyTimestampAndWindows):
from dataflow_worker.shuffle_operations import ReifyTimestampAndWindowsOperation
op = ReifyTimestampAndWindowsOperation(name_context, spec,
counter_factory, state_sampler)
else:
raise TypeError(
'Expected an instance of operation_specs.Worker* class '
'instead of %s' % (spec, ))
return op
