def start_bundle(self):
transform = self._applied_ptransform.transform
self._tagged_receivers = _TaggedReceivers(self._evaluation_context)
for output_tag in self._applied_ptransform.outputs:
output_pcollection = pvalue.PCollection(None, tag=output_tag)
output_pcollection.producer = self._applied_ptransform
self._tagged_receivers[output_tag] = (
self._evaluation_context.create_bundle(output_pcollection))
self._tagged_receivers[output_tag].tag = output_tag
self._counter_factory = counters.CounterFactory()
# TODO(aaltay): Consider storing the serialized form as an optimization.
dofn = (
pickler.loads(pickler.dumps(transform.dofn))
if self._perform_dofn_pickle_test else transform.dofn)
args = transform.args if hasattr(transform, 'args') else []
kwargs = transform.kwargs if hasattr(transform, 'kwargs') else {}
self.user_state_context = None
self.user_timer_map = {}
if is_stateful_dofn(dofn):
kv_type_hint = self._applied_ptransform.inputs[0].element_type
if kv_type_hint and kv_type_hint != Any:
coder = coders.registry.get_coder(kv_type_hint)
self.key_coder = coder.key_coder()
else:
self.key_coder = coders.registry.get_coder(Any)
self.user_state_context = DirectUserStateContext(
self._step_context, dofn, self.key_coder)
_, all_timer_specs = get_dofn_specs(dofn)
for timer_spec in all_timer_specs:
self.user_timer_map['user/%s' % timer_spec.name] = timer_spec
self.runner = DoFnRunner(
dofn,
args,
kwargs,
self._side_inputs,
self._applied_ptransform.inputs[0].windowing,
tagged_receivers=self._tagged_receivers,
step_name=self._applied_ptransform.full_label,
state=DoFnState(self._counter_factory),
user_state_context=self.user_state_context)
self.runner.setup()
self.runner.start()
def start_bundle(self):
transform = self._applied_ptransform.transform
self._tagged_receivers = _TaggedReceivers(self._evaluation_context)
for output_tag in self._applied_ptransform.outputs:
output_pcollection = pvalue.PCollection(None, tag=output_tag)
output_pcollection.producer = self._applied_ptransform
self._tagged_receivers[output_tag] = (
self._evaluation_context.create_bundle(output_pcollection))
self._tagged_receivers[output_tag].tag = output_tag
self._counter_factory = counters.CounterFactory()
# TODO(aaltay): Consider storing the serialized form as an optimization.
dofn = (pickler.loads(pickler.dumps(transform.dofn))
if self._perform_dofn_pickle_test else transform.dofn)
args = transform.args if hasattr(transform, 'args') else []
kwargs = transform.kwargs if hasattr(transform, 'kwargs') else {}
self.user_state_context = None
self.user_timer_map = {}
if is_stateful_dofn(dofn):
kv_type_hint = self._applied_ptransform.inputs[0].element_type
if kv_type_hint and kv_type_hint != typehints.Any:
coder = coders.registry.get_coder(kv_type_hint)
self.key_coder = coder.key_coder()
else:
self.key_coder = coders.registry.get_coder(typehints.Any)
self.user_state_context = DirectUserStateContext(
self._step_context, dofn, self.key_coder)
_, all_timer_specs = get_dofn_specs(dofn)
for timer_spec in all_timer_specs:
self.user_timer_map['user/%s' % timer_spec.name] = timer_spec
self.runner = DoFnRunner(
dofn, args, kwargs,
self._side_inputs,
self._applied_ptransform.inputs[0].windowing,
tagged_receivers=self._tagged_receivers,
step_name=self._applied_ptransform.full_label,
state=DoFnState(self._counter_factory),
user_state_context=self.user_state_context)
self.runner.start()
class _ParDoEvaluator(_TransformEvaluator):
"""TransformEvaluator for ParDo transform."""
def __init__(
self,
evaluation_context, # type: EvaluationContext
applied_ptransform, # type: AppliedPTransform
input_committed_bundle,
side_inputs,
perform_dofn_pickle_test=True):
super(_ParDoEvaluator,
self).__init__(evaluation_context, applied_ptransform,
input_committed_bundle, side_inputs)
# This is a workaround for SDF implementation. SDF implementation adds state
# to the SDF that is not picklable.
self._perform_dofn_pickle_test = perform_dofn_pickle_test
def start_bundle(self):
transform = self._applied_ptransform.transform
self._tagged_receivers = _TaggedReceivers(self._evaluation_context)
for output_tag in self._applied_ptransform.outputs:
output_pcollection = pvalue.PCollection(None, tag=output_tag)
output_pcollection.producer = self._applied_ptransform
self._tagged_receivers[output_tag] = (
self._evaluation_context.create_bundle(output_pcollection))
self._tagged_receivers[output_tag].tag = output_tag
self._counter_factory = counters.CounterFactory()
# TODO(aaltay): Consider storing the serialized form as an optimization.
dofn = (pickler.loads(pickler.dumps(transform.dofn))
if self._perform_dofn_pickle_test else transform.dofn)
args = transform.args if hasattr(transform, 'args') else []
kwargs = transform.kwargs if hasattr(transform, 'kwargs') else {}
self.user_state_context = None
self.user_timer_map = {}
if is_stateful_dofn(dofn):
kv_type_hint = self._applied_ptransform.inputs[0].element_type
if kv_type_hint and kv_type_hint != Any:
coder = coders.registry.get_coder(kv_type_hint)
self.key_coder = coder.key_coder()
else:
self.key_coder = coders.registry.get_coder(Any)
self.user_state_context = DirectUserStateContext(
self._step_context, dofn, self.key_coder)
_, all_timer_specs = get_dofn_specs(dofn)
for timer_spec in all_timer_specs:
self.user_timer_map['user/%s' % timer_spec.name] = timer_spec
self.runner = DoFnRunner(dofn,
args,
kwargs,
self._side_inputs,
self._applied_ptransform.inputs[0].windowing,
tagged_receivers=self._tagged_receivers,
step_name=self._applied_ptransform.full_label,
state=DoFnState(self._counter_factory),
user_state_context=self.user_state_context)
self.runner.start()
def process_timer(self, timer_firing):
if timer_firing.name not in self.user_timer_map:
_LOGGER.warning('Unknown timer fired: %s', timer_firing)
timer_spec = self.user_timer_map[timer_firing.name]
self.runner.process_user_timer(
timer_spec, self.key_coder.decode(timer_firing.encoded_key),
timer_firing.window, timer_firing.timestamp)
def process_element(self, element):
self.runner.process(element)
def finish_bundle(self):
self.runner.finish()
bundles = list(self._tagged_receivers.values())
result_counters = self._counter_factory.get_counters()
if self.user_state_context:
self.user_state_context.commit()
return TransformResult(self, bundles, [], result_counters, None)
class _ParDoEvaluator(_TransformEvaluator):
"""TransformEvaluator for ParDo transform."""
def __init__(self, evaluation_context, applied_ptransform,
input_committed_bundle, side_inputs,
perform_dofn_pickle_test=True):
super(_ParDoEvaluator, self).__init__(
evaluation_context, applied_ptransform, input_committed_bundle,
side_inputs)
# This is a workaround for SDF implementation. SDF implementation adds state
# to the SDF that is not picklable.
self._perform_dofn_pickle_test = perform_dofn_pickle_test
def start_bundle(self):
transform = self._applied_ptransform.transform
self._tagged_receivers = _TaggedReceivers(self._evaluation_context)
for output_tag in self._applied_ptransform.outputs:
output_pcollection = pvalue.PCollection(None, tag=output_tag)
output_pcollection.producer = self._applied_ptransform
self._tagged_receivers[output_tag] = (
self._evaluation_context.create_bundle(output_pcollection))
self._tagged_receivers[output_tag].tag = output_tag
self._counter_factory = counters.CounterFactory()
# TODO(aaltay): Consider storing the serialized form as an optimization.
dofn = (pickler.loads(pickler.dumps(transform.dofn))
if self._perform_dofn_pickle_test else transform.dofn)
args = transform.args if hasattr(transform, 'args') else []
kwargs = transform.kwargs if hasattr(transform, 'kwargs') else {}
self.user_state_context = None
self.user_timer_map = {}
if is_stateful_dofn(dofn):
kv_type_hint = self._applied_ptransform.inputs[0].element_type
if kv_type_hint and kv_type_hint != typehints.Any:
coder = coders.registry.get_coder(kv_type_hint)
self.key_coder = coder.key_coder()
else:
self.key_coder = coders.registry.get_coder(typehints.Any)
self.user_state_context = DirectUserStateContext(
self._step_context, dofn, self.key_coder)
_, all_timer_specs = get_dofn_specs(dofn)
for timer_spec in all_timer_specs:
self.user_timer_map['user/%s' % timer_spec.name] = timer_spec
self.runner = DoFnRunner(
dofn, args, kwargs,
self._side_inputs,
self._applied_ptransform.inputs[0].windowing,
tagged_receivers=self._tagged_receivers,
step_name=self._applied_ptransform.full_label,
state=DoFnState(self._counter_factory),
user_state_context=self.user_state_context)
self.runner.start()
def process_timer(self, timer_firing):
if timer_firing.name not in self.user_timer_map:
logging.warning('Unknown timer fired: %s', timer_firing)
timer_spec = self.user_timer_map[timer_firing.name]
self.runner.process_user_timer(
timer_spec, self.key_coder.decode(timer_firing.encoded_key),
timer_firing.window, timer_firing.timestamp)
def process_element(self, element):
self.runner.process(element)
def finish_bundle(self):
self.runner.finish()
bundles = list(self._tagged_receivers.values())
result_counters = self._counter_factory.get_counters()
if self.user_state_context:
self.user_state_context.commit()
return TransformResult(
self, bundles, [], result_counters, None)
