def test_construct_log_string_for_event():
step_output_event = DagsterEvent(
event_type_value="STEP_OUTPUT",
pipeline_name="my_pipeline",
step_key="solid2",
solid_handle=NodeHandle("solid2", None),
step_kind_value="COMPUTE",
logging_tags={},
event_specific_data=StepOutputData(
step_output_handle=StepOutputHandle("solid2", "result")),
message=
'Yielded output "result" of type "Any" for step "solid2". (Type check passed).',
pid=54348,
)
logging_metadata = DagsterLoggingMetadata(
run_id="f79a8a93-27f1-41b5-b465-b35d0809b26d",
pipeline_name="my_pipeline")
dagster_message_props = DagsterMessageProps(
orig_message=step_output_event.message,
dagster_event=step_output_event,
)
assert (
construct_log_string(logging_metadata=logging_metadata,
message_props=dagster_message_props) ==
'my_pipeline - f79a8a93-27f1-41b5-b465-b35d0809b26d - 54348 - STEP_OUTPUT - Yielded output "result" of type "Any" for step "solid2". (Type check passed).'
)
def test_construct_log_string_for_event():
step_output_event = DagsterEvent(
event_type_value="STEP_OUTPUT",
pipeline_name="my_pipeline",
step_key="solid2",
solid_handle=SolidHandle("solid2", None),
step_kind_value="COMPUTE",
logging_tags={},
event_specific_data=StepOutputData(
step_output_handle=StepOutputHandle("solid2", "result")),
message=
'Yielded output "result" of type "Any" for step "solid2". (Type check passed).',
pid=54348,
)
message_props = {
"dagster_event": step_output_event,
"pipeline_name": "my_pipeline"
}
synth_props = {
"orig_message": step_output_event.message,
"run_id": "f79a8a93-27f1-41b5-b465-b35d0809b26d",
}
assert (
construct_log_string(message_props=message_props,
logging_tags={},
synth_props=synth_props) ==
'my_pipeline - f79a8a93-27f1-41b5-b465-b35d0809b26d - 54348 - STEP_OUTPUT - Yielded output "result" of type "Any" for step "solid2". (Type check passed).'
)
def _type_check_output(
step_context: SystemStepExecutionContext,
step_output_handle: StepOutputHandle,
output: Any,
version: Optional[str],
) -> Iterator[DagsterEvent]:
check.inst_param(step_context, "step_context", SystemStepExecutionContext)
check.inst_param(output, "output", (Output, DynamicOutput))
step_output = step_context.step.step_output_named(output.output_name)
step_output_def = step_context.solid_def.output_def_named(step_output.name)
dagster_type = step_output_def.dagster_type
with user_code_error_boundary(
DagsterTypeCheckError,
lambda: ('In solid "{handle}" the output "{output_name}" received '
"value {output_value} of Python type {output_type} which "
"does not pass the typecheck for Dagster type "
"{dagster_type_name}. Step {step_key}.").format(
handle=str(step_context.step.solid_handle),
output_name=output.output_name,
output_value=output.value,
output_type=type(output.value),
dagster_type_name=dagster_type.display_name,
step_key=step_context.step.key,
),
):
type_check = _do_type_check(step_context.for_type(dagster_type),
dagster_type, output.value)
yield DagsterEvent.step_output_event(
step_context=step_context,
step_output_data=StepOutputData(
step_output_handle=step_output_handle,
type_check_data=TypeCheckData(
success=type_check.success,
label=step_output_handle.output_name,
description=type_check.description if type_check else None,
metadata_entries=type_check.metadata_entries
if type_check else [],
),
version=version,
),
)
if not type_check.success:
raise DagsterTypeCheckDidNotPass(
description=
'Type check failed for step output "{output_name}" - expected type "{dagster_type}".'
.format(
output_name=output.output_name,
dagster_type=dagster_type.display_name,
),
metadata_entries=type_check.metadata_entries,
dagster_type=dagster_type,
)
def _type_check_output(
step_context: StepExecutionContext,
step_output_handle: StepOutputHandle,
output: Any,
version: Optional[str],
) -> Iterator[DagsterEvent]:
check.inst_param(step_context, "step_context", StepExecutionContext)
check.inst_param(output, "output", (Output, DynamicOutput))
step_output = step_context.step.step_output_named(output.output_name)
step_output_def = step_context.solid_def.output_def_named(step_output.name)
dagster_type = step_output_def.dagster_type
type_check_context = step_context.for_type(dagster_type)
op_label = step_context.describe_op()
output_type = type(output.value)
with user_code_error_boundary(
DagsterTypeCheckError,
lambda:
(f'Error occurred while type-checking output "{output.output_name}" of {op_label}, with '
f"Python type {output_type} and Dagster type {dagster_type.display_name}"
),
log_manager=type_check_context.log,
):
type_check = do_type_check(type_check_context, dagster_type,
output.value)
yield DagsterEvent.step_output_event(
step_context=step_context,
step_output_data=StepOutputData(
step_output_handle=step_output_handle,
type_check_data=TypeCheckData(
success=type_check.success,
label=step_output_handle.output_name,
description=type_check.description if type_check else None,
metadata_entries=type_check.metadata_entries
if type_check else [],
),
version=version,
metadata_entries=[
entry for entry in output.metadata_entries
if isinstance(entry, MetadataEntry)
],
),
)
if not type_check.success:
raise DagsterTypeCheckDidNotPass(
description=(
f'Type check failed for step output "{output.output_name}" - '
f'expected type "{dagster_type.display_name}". '
f"Description: {type_check.description}"),
metadata_entries=type_check.metadata_entries,
dagster_type=dagster_type,
)
def _create_step_output_event(step_context, step_output_handle, type_check, success, version):
return DagsterEvent.step_output_event(
step_context=step_context,
step_output_data=StepOutputData(
step_output_handle=step_output_handle,
type_check_data=TypeCheckData(
success=success,
label=step_output_handle.output_name,
description=type_check.description if type_check else None,
metadata_entries=type_check.metadata_entries if type_check else [],
),
version=version,
),
)
def _type_check_output(
step_context: SystemStepExecutionContext,
step_output_handle: StepOutputHandle,
output: Any,
version: Optional[str],
) -> Iterator[DagsterEvent]:
check.inst_param(step_context, "step_context", SystemStepExecutionContext)
check.inst_param(output, "output", (Output, DynamicOutput))
step_output = step_context.step.step_output_named(output.output_name)
step_output_def = step_context.solid_def.output_def_named(step_output.name)
dagster_type = step_output_def.dagster_type
with user_code_error_boundary(
DagsterTypeCheckError,
lambda: (
f'Error occurred while type-checking output "{output.output_name}" of solid '
f'"{str(step_context.step.solid_handle)}", with Python type {type(output.value)} and '
f"Dagster type {dagster_type.display_name}"
),
):
type_check = _do_type_check(step_context.for_type(dagster_type), dagster_type, output.value)
yield DagsterEvent.step_output_event(
step_context=step_context,
step_output_data=StepOutputData(
step_output_handle=step_output_handle,
type_check_data=TypeCheckData(
success=type_check.success,
label=step_output_handle.output_name,
description=type_check.description if type_check else None,
metadata_entries=type_check.metadata_entries if type_check else [],
),
version=version,
),
)
if not type_check.success:
raise DagsterTypeCheckDidNotPass(
description='Type check failed for step output "{output_name}" - expected type "{dagster_type}".'.format(
output_name=output.output_name,
dagster_type=dagster_type.display_name,
),
metadata_entries=type_check.metadata_entries,
dagster_type=dagster_type,
)
def _create_step_output_event(
step_context: SystemStepExecutionContext,
step_output_handle: StepOutputHandle,
type_check: TypeCheck,
success: bool,
version: Optional[str],
) -> DagsterEvent:
return DagsterEvent.step_output_event(
step_context=step_context,
step_output_data=StepOutputData(
step_output_handle=step_output_handle,
type_check_data=TypeCheckData(
success=success,
label=step_output_handle.output_name,
description=type_check.description if type_check else None,
metadata_entries=type_check.metadata_entries
if type_check else [],
),
version=version,
),
)
def test_recover_in_between_steps():
two_op_job = define_two_op_job()
events = [
DagsterEvent(
DagsterEventType.STEP_START.value,
pipeline_name=two_op_job.name,
step_key="foo_op",
),
DagsterEvent(
DagsterEventType.STEP_OUTPUT.value,
pipeline_name=two_op_job.name,
event_specific_data=StepOutputData(
StepOutputHandle(step_key="foo_op", output_name="result")
),
step_key="foo_op",
),
DagsterEvent(
DagsterEventType.STEP_SUCCESS.value,
pipeline_name=two_op_job.name,
event_specific_data=StepSuccessData(duration_ms=10.0),
step_key="foo_op",
),
]
with pytest.raises(
DagsterInvariantViolationError,
match="Execution finished without completing the execution plan",
):
with create_execution_plan(two_op_job).start(RetryMode.DISABLED) as active_execution:
steps = active_execution.get_steps_to_execute()
assert len(steps) == 1
step_1 = steps[0]
assert step_1.key == "foo_op"
active_execution.handle_event(events[0])
active_execution.handle_event(events[1])
active_execution.handle_event(events[2])
# CRASH!- we've closed the active execution. Now we recover, spinning up a new one
with create_execution_plan(two_op_job).start(RetryMode.DISABLED) as active_execution:
possibly_in_flight_steps = active_execution.rebuild_from_events(events)
assert len(possibly_in_flight_steps) == 1
step_2 = possibly_in_flight_steps[0]
assert step_2.key == "bar_op"
assert not active_execution.get_steps_to_execute()
active_execution.handle_event(
DagsterEvent(
DagsterEventType.STEP_START.value,
pipeline_name=two_op_job.name,
step_key="bar_op",
)
)
active_execution.handle_event(
DagsterEvent(
DagsterEventType.STEP_SUCCESS.value,
pipeline_name=two_op_job.name,
event_specific_data=StepSuccessData(duration_ms=10.0),
step_key="bar_op",
)
)
