def build_importer_component_spec(
importer_base_name: str,
input_name: str,
input_type_schema: str,
) -> pipeline_spec_pb2.ComponentSpec:
"""Builds an importer component spec.
Args:
importer_base_name: The base name of the importer node.
dependent_task: The task requires importer node.
input_name: The name of the input artifact needs to be imported.
input_type_schema: The type of the input artifact.
Returns:
An importer node component spec.
"""
result = pipeline_spec_pb2.ComponentSpec()
result.executor_label = dsl_utils.sanitize_executor_label(
importer_base_name)
result.input_definitions.parameters[
input_name].type = pipeline_spec_pb2.PrimitiveType.STRING
result.output_definitions.artifacts[
OUTPUT_KEY].artifact_type.instance_schema = input_type_schema
return result
def build_component_spec_from_structure(
component_spec: structures.ComponentSpec,
) -> pipeline_spec_pb2.ComponentSpec:
"""Builds an IR ComponentSpec instance from structures.ComponentSpec.
Args:
component_spec: The structure component spec.
Returns:
An instance of IR ComponentSpec.
"""
result = pipeline_spec_pb2.ComponentSpec()
result.executor_label = dsl_utils.sanitize_executor_label(component_spec.name)
for input_spec in component_spec.inputs or []:
if type_utils.is_parameter_type(input_spec.type):
result.input_definitions.parameters[
input_spec.name].type = type_utils.get_parameter_type(input_spec.type)
else:
result.input_definitions.artifacts[
input_spec.name].artifact_type.instance_schema = (
type_utils.get_artifact_type_schema(input_spec.type))
for output_spec in component_spec.outputs or []:
if type_utils.is_parameter_type(output_spec.type):
result.output_definitions.parameters[
output_spec.name].type = type_utils.get_parameter_type(
output_spec.type)
else:
result.output_definitions.artifacts[
output_spec.name].artifact_type.instance_schema = (
type_utils.get_artifact_type_schema(output_spec.type))
return result
def _build_importer_component_spec(
importer_base_name: str,
artifact_type_schema: pipeline_spec_pb2.ArtifactTypeSchema,
) -> pipeline_spec_pb2.ComponentSpec:
"""Builds an importer component spec.
Args:
importer_base_name: The base name of the importer node.
artifact_type_schema: The user specified artifact type schema of the
artifact to be imported.
Returns:
An importer node component spec.
"""
result = pipeline_spec_pb2.ComponentSpec()
result.executor_label = dsl_utils.sanitize_executor_label(
importer_base_name)
result.input_definitions.parameters[
INPUT_KEY].type = pipeline_spec_pb2.PrimitiveType.STRING
result.output_definitions.artifacts[OUTPUT_KEY].artifact_type.CopyFrom(
artifact_type_schema)
return result
def _attach_v2_specs(
task: _container_op.ContainerOp,
component_spec: _structures.ComponentSpec,
arguments: Mapping[str, Any],
) -> None:
"""Attaches v2 specs to a ContainerOp object.
Attach v2_specs to the ContainerOp object regardless whether the pipeline is
being compiled to v1 (Argo yaml) or v2 (IR json).
However, there're different behaviors for the two cases. Namely, resolved
commands and arguments, error handling, etc.
Regarding the difference in error handling, v2 has a stricter requirement on
input type annotation. For instance, an input without any type annotation is
viewed as an artifact, and if it's paired with InputValuePlaceholder, an
error will be thrown at compile time. However, we cannot raise such an error
in v1, as it wouldn't break existing pipelines.
Args:
task: The ContainerOp object to attach IR specs.
component_spec: The component spec object.
arguments: The dictionary of component arguments.
"""
def _resolve_commands_and_args_v2(
component_spec: _structures.ComponentSpec,
arguments: Mapping[str, Any],
) -> _components._ResolvedCommandLineAndPaths:
"""Resolves the command line argument placeholders for v2 (IR).
Args:
component_spec: The component spec object.
arguments: The dictionary of component arguments.
Returns:
A named tuple: _components._ResolvedCommandLineAndPaths.
"""
inputs_dict = {
input_spec.name: input_spec
for input_spec in component_spec.inputs or []
}
outputs_dict = {
output_spec.name: output_spec
for output_spec in component_spec.outputs or []
}
def _input_artifact_uri_placeholder(input_key: str) -> str:
if kfp.COMPILING_FOR_V2 and type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError('Input "{}" with type "{}" cannot be paired with '
'InputUriPlaceholder.'.format(
input_key, inputs_dict[input_key].type))
else:
return _generate_input_uri_placeholder(input_key)
def _input_artifact_path_placeholder(input_key: str) -> str:
if kfp.COMPILING_FOR_V2 and type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError('Input "{}" with type "{}" cannot be paired with '
'InputPathPlaceholder.'.format(
input_key, inputs_dict[input_key].type))
else:
return "{{{{$.inputs.artifacts['{}'].path}}}}".format(input_key)
def _input_parameter_placeholder(input_key: str) -> str:
if kfp.COMPILING_FOR_V2 and not type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError('Input "{}" with type "{}" cannot be paired with '
'InputValuePlaceholder.'.format(
input_key, inputs_dict[input_key].type))
else:
return "{{{{$.inputs.parameters['{}']}}}}".format(input_key)
def _output_artifact_uri_placeholder(output_key: str) -> str:
if kfp.COMPILING_FOR_V2 and type_utils.is_parameter_type(
outputs_dict[output_key].type):
raise TypeError('Output "{}" with type "{}" cannot be paired with '
'OutputUriPlaceholder.'.format(
output_key, outputs_dict[output_key].type))
else:
return _generate_output_uri_placeholder(output_key)
def _output_artifact_path_placeholder(output_key: str) -> str:
return "{{{{$.outputs.artifacts['{}'].path}}}}".format(output_key)
def _output_parameter_path_placeholder(output_key: str) -> str:
return "{{{{$.outputs.parameters['{}'].output_file}}}}".format(output_key)
def _resolve_output_path_placeholder(output_key: str) -> str:
if type_utils.is_parameter_type(outputs_dict[output_key].type):
return _output_parameter_path_placeholder(output_key)
else:
return _output_artifact_path_placeholder(output_key)
placeholder_resolver = ExtraPlaceholderResolver()
def _resolve_ir_placeholders_v2(
arg,
component_spec: _structures.ComponentSpec,
arguments: dict,
) -> str:
inputs_dict = {input_spec.name: input_spec for input_spec in component_spec.inputs or []}
if isinstance(arg, _structures.InputValuePlaceholder):
input_name = arg.input_name
input_value = arguments.get(input_name, None)
if input_value is not None:
return _input_parameter_placeholder(input_name)
else:
input_spec = inputs_dict[input_name]
if input_spec.optional:
return None
else:
raise ValueError('No value provided for input {}'.format(input_name))
elif isinstance(arg, _structures.InputUriPlaceholder):
input_name = arg.input_name
if input_name in arguments:
input_uri = _input_artifact_uri_placeholder(input_name)
return input_uri
else:
input_spec = inputs_dict[input_name]
if input_spec.optional:
return None
else:
raise ValueError('No value provided for input {}'.format(input_name))
elif isinstance(arg, _structures.OutputUriPlaceholder):
output_name = arg.output_name
output_uri = _output_artifact_uri_placeholder(output_name)
return output_uri
return placeholder_resolver.resolve_placeholder(
arg=arg,
component_spec=component_spec,
arguments=arguments,
)
resolved_cmd = _components._resolve_command_line_and_paths(
component_spec=component_spec,
arguments=arguments,
input_path_generator=_input_artifact_path_placeholder,
output_path_generator=_resolve_output_path_placeholder,
placeholder_resolver=_resolve_ir_placeholders_v2,
)
return resolved_cmd
pipeline_task_spec = pipeline_spec_pb2.PipelineTaskSpec()
# Check types of the reference arguments and serialize PipelineParams
arguments = arguments.copy()
# Preserve input params for ContainerOp.inputs
input_params_set = set([
param for param in arguments.values()
if isinstance(param, _pipeline_param.PipelineParam)
])
for input_name, argument_value in arguments.items():
input_type = component_spec._inputs_dict[input_name].type
argument_type = None
if isinstance(argument_value, _pipeline_param.PipelineParam):
argument_type = argument_value.param_type
types.verify_type_compatibility(
argument_type, input_type,
'Incompatible argument passed to the input "{}" of component "{}": '
.format(input_name, component_spec.name))
# Loop arguments defaults to 'String' type if type is unknown.
# This has to be done after the type compatiblity check.
if argument_type is None and isinstance(
argument_value, (_for_loop.LoopArguments,
_for_loop.LoopArgumentVariable)):
argument_type = 'String'
arguments[input_name] = str(argument_value)
if type_utils.is_parameter_type(input_type):
if argument_value.op_name:
pipeline_task_spec.inputs.parameters[
input_name].task_output_parameter.producer_task = (
dsl_utils.sanitize_task_name(argument_value.op_name))
pipeline_task_spec.inputs.parameters[
input_name].task_output_parameter.output_parameter_key = (
argument_value.name)
else:
pipeline_task_spec.inputs.parameters[
input_name].component_input_parameter = argument_value.name
else:
if argument_value.op_name:
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.producer_task = (
dsl_utils.sanitize_task_name(argument_value.op_name))
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.output_artifact_key = (
argument_value.name)
elif isinstance(argument_value, str):
argument_type = 'String'
pipeline_params = _pipeline_param.extract_pipelineparams_from_any(
argument_value)
if pipeline_params and kfp.COMPILING_FOR_V2:
# argument_value contains PipelineParam placeholders which needs to be
# replaced. And the input needs to be added to the task spec.
for param in pipeline_params:
# Form the name for the compiler injected input, and make sure it
# doesn't collide with any existing input names.
additional_input_name = (
dsl_component_spec.additional_input_name_for_pipelineparam(param))
for existing_input_name, _ in arguments.items():
if existing_input_name == additional_input_name:
raise ValueError('Name collision between existing input name '
'{} and compiler injected input name {}'.format(
existing_input_name, additional_input_name))
# Add the additional param to the input params set. Otherwise, it will
# not be included when the params set is not empty.
input_params_set.add(param)
additional_input_placeholder = (
"{{{{$.inputs.parameters['{}']}}}}".format(additional_input_name))
argument_value = argument_value.replace(param.pattern,
additional_input_placeholder)
# The output references are subject to change -- the producer task may
# not be whitin the same DAG.
if param.op_name:
pipeline_task_spec.inputs.parameters[
additional_input_name].task_output_parameter.producer_task = (
dsl_utils.sanitize_task_name(param.op_name))
pipeline_task_spec.inputs.parameters[
additional_input_name].task_output_parameter.output_parameter_key = param.name
else:
pipeline_task_spec.inputs.parameters[
additional_input_name].component_input_parameter = param.full_name
input_type = component_spec._inputs_dict[input_name].type
if type_utils.is_parameter_type(input_type):
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.string_value = (
argument_value)
elif isinstance(argument_value, int):
argument_type = 'Integer'
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.int_value = argument_value
elif isinstance(argument_value, float):
argument_type = 'Float'
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.double_value = argument_value
elif isinstance(argument_value, _container_op.ContainerOp):
raise TypeError(
'ContainerOp object {} was passed to component as an input argument. '
'Pass a single output instead.'.format(input_name))
else:
if kfp.COMPILING_FOR_V2:
raise NotImplementedError(
'Input argument supports only the following types: PipelineParam'
', str, int, float. Got: "{}".'.format(argument_value))
argument_is_parameter_type = type_utils.is_parameter_type(argument_type)
input_is_parameter_type = type_utils.is_parameter_type(input_type)
if kfp.COMPILING_FOR_V2 and (argument_is_parameter_type !=
input_is_parameter_type):
if isinstance(argument_value, dsl.PipelineParam):
param_or_value_msg = 'PipelineParam "{}"'.format(
argument_value.full_name)
else:
param_or_value_msg = 'value "{}"'.format(argument_value)
raise TypeError(
'Passing '
'{param_or_value} with type "{arg_type}" (as "{arg_category}") to '
'component input '
'"{input_name}" with type "{input_type}" (as "{input_category}") is '
'incompatible. Please fix the type of the component input.'.format(
param_or_value=param_or_value_msg,
arg_type=argument_type,
arg_category='Parameter'
if argument_is_parameter_type else 'Artifact',
input_name=input_name,
input_type=input_type,
input_category='Paramter'
if input_is_parameter_type else 'Artifact',
))
if not component_spec.name:
component_spec.name = _components._default_component_name
# task.name is unique at this point.
pipeline_task_spec.task_info.name = (dsl_utils.sanitize_task_name(task.name))
resolved_cmd = _resolve_commands_and_args_v2(
component_spec=component_spec, arguments=arguments)
task.container_spec = (
pipeline_spec_pb2.PipelineDeploymentConfig.PipelineContainerSpec(
image=component_spec.implementation.container.image,
command=resolved_cmd.command,
args=resolved_cmd.args))
# TODO(chensun): dedupe IR component_spec and contaienr_spec
pipeline_task_spec.component_ref.name = (
dsl_utils.sanitize_component_name(task.name))
executor_label = dsl_utils.sanitize_executor_label(task.name)
task.component_spec = dsl_component_spec.build_component_spec_from_structure(
component_spec, executor_label, arguments.keys())
task.task_spec = pipeline_task_spec
# Override command and arguments if compiling to v2.
if kfp.COMPILING_FOR_V2:
task.command = resolved_cmd.command
task.arguments = resolved_cmd.args
# limit this to v2 compiling only to avoid possible behavior change in v1.
task.inputs = list(input_params_set)
def test_sanitize_executor_label(self):
self.assertEqual('exec-my-component',
dsl_utils.sanitize_executor_label('My component'))
def _get_custom_job_op(
task_name: str,
job_spec: Dict[str, Any],
input_artifacts: Optional[Dict[str, dsl.PipelineParam]] = None,
input_parameters: Optional[Dict[str, _ValueOrPipelineParam]] = None,
output_artifacts: Optional[Dict[str, Type[artifact.Artifact]]] = None,
output_parameters: Optional[Dict[str, Any]] = None,
) -> AiPlatformCustomJobOp:
"""Gets an AiPlatformCustomJobOp from job spec and I/O definition."""
pipeline_task_spec = pipeline_spec_pb2.PipelineTaskSpec()
pipeline_component_spec = pipeline_spec_pb2.ComponentSpec()
pipeline_task_spec.task_info.CopyFrom(
pipeline_spec_pb2.PipelineTaskInfo(name=dsl_utils.sanitize_task_name(task_name)))
# Iterate through the inputs/outputs declaration to get pipeline component
# spec.
for input_name, param in input_parameters.items():
if isinstance(param, dsl.PipelineParam):
pipeline_component_spec.input_definitions.parameters[
input_name].type = type_utils.get_parameter_type(param.param_type)
else:
pipeline_component_spec.input_definitions.parameters[
input_name].type = type_utils.get_parameter_type(type(param))
for input_name, art in input_artifacts.items():
if not isinstance(art, dsl.PipelineParam):
raise RuntimeError(
'Get unresolved input artifact for input %s. Input '
'artifacts must be connected to a producer task.' % input_name)
pipeline_component_spec.input_definitions.artifacts[
input_name].artifact_type.CopyFrom(
type_utils.get_artifact_type_schema_message(art.param_type))
for output_name, param_type in output_parameters.items():
pipeline_component_spec.output_definitions.parameters[
output_name].type = type_utils.get_parameter_type(param_type)
for output_name, artifact_type in output_artifacts.items():
pipeline_component_spec.output_definitions.artifacts[
output_name].artifact_type.CopyFrom(artifact_type.get_ir_type())
pipeline_component_spec.executor_label = dsl_utils.sanitize_executor_label(
task_name)
# Iterate through the inputs/outputs specs to get pipeline task spec.
for input_name, param in input_parameters.items():
if isinstance(param, dsl.PipelineParam) and param.op_name:
# If the param has a valid op_name, this should be a pipeline parameter
# produced by an upstream task.
pipeline_task_spec.inputs.parameters[input_name].CopyFrom(
pipeline_spec_pb2.TaskInputsSpec.InputParameterSpec(
task_output_parameter=pipeline_spec_pb2.TaskInputsSpec.InputParameterSpec.TaskOutputParameterSpec(
producer_task=dsl_utils.sanitize_task_name(param.op_name),
output_parameter_key=param.name
)))
elif isinstance(param, dsl.PipelineParam) and not param.op_name:
# If a valid op_name is missing, this should be a pipeline parameter.
pipeline_task_spec.inputs.parameters[input_name].CopyFrom(
pipeline_spec_pb2.TaskInputsSpec.InputParameterSpec(
component_input_parameter=param.name))
else:
# If this is not a pipeline param, then it should be a value.
pipeline_task_spec.inputs.parameters[input_name].CopyFrom(
pipeline_spec_pb2.TaskInputsSpec.InputParameterSpec(
runtime_value=pipeline_spec_pb2.ValueOrRuntimeParameter(
constant_value=dsl_utils.get_value(param))))
for input_name, art in input_artifacts.items():
if art.op_name:
# If the param has a valid op_name, this should be an artifact produced
# by an upstream task.
pipeline_task_spec.inputs.artifacts[input_name].CopyFrom(
pipeline_spec_pb2.TaskInputsSpec.InputArtifactSpec(
task_output_artifact=pipeline_spec_pb2.TaskInputsSpec.InputArtifactSpec.TaskOutputArtifactSpec(
producer_task=dsl_utils.sanitize_task_name(art.op_name),
output_artifact_key=art.name)))
else:
# Otherwise, this should be from the input of the subdag.
pipeline_task_spec.inputs.artifacts[input_name].CopyFrom(
pipeline_spec_pb2.TaskInputsSpec.InputArtifactSpec(
component_input_artifact=art.name
))
# TODO: Add task dependencies/trigger policies/caching/iterator
pipeline_task_spec.component_ref.name = dsl_utils.sanitize_component_name(
task_name)
# Construct dummy I/O declaration for the op.
# TODO: resolve name conflict instead of raising errors.
dummy_outputs = collections.OrderedDict()
for output_name, _ in output_artifacts.items():
dummy_outputs[output_name] = _DUMMY_PATH
for output_name, _ in output_parameters.items():
if output_name in dummy_outputs:
raise KeyError('Got name collision for output key %s. Consider renaming '
'either output parameters or output '
'artifacts.' % output_name)
dummy_outputs[output_name] = _DUMMY_PATH
dummy_inputs = collections.OrderedDict()
for input_name, art in input_artifacts.items():
dummy_inputs[input_name] = _DUMMY_PATH
for input_name, param in input_parameters.items():
if input_name in dummy_inputs:
raise KeyError('Got name collision for input key %s. Consider renaming '
'either input parameters or input '
'artifacts.' % input_name)
dummy_inputs[input_name] = _DUMMY_PATH
# Construct the AIP (Unified) custom job op.
return AiPlatformCustomJobOp(
name=task_name,
custom_job_spec=job_spec,
component_spec=pipeline_component_spec,
task_spec=pipeline_task_spec,
task_inputs=[
dsl.InputArgumentPath(
argument=dummy_inputs[input_name],
input=input_name,
path=path,
) for input_name, path in dummy_inputs.items()
],
task_outputs=dummy_outputs
)
def _attach_v2_specs(
task: _container_op.ContainerOp,
component_spec: _structures.ComponentSpec,
arguments: Mapping[str, Any],
) -> None:
"""Attaches v2 specs to a ContainerOp object.
Args:
task: The ContainerOp object to attach IR specs.
component_spec: The component spec object.
arguments: The dictionary of component arguments.
"""
# Attach v2_specs to the ContainerOp object regardless whether the pipeline is
# being compiled to v1 (Argo yaml) or v2 (IR json).
# However, there're different behaviors for the two cases. Namely, resolved
# commands and arguments, error handling, etc.
# Regarding the difference in error handling, v2 has a stricter requirement on
# input type annotation. For instance, an input without any type annotation is
# viewed as an artifact, and if it's paired with InputValuePlaceholder, an
# error will be thrown at compile time. However, we cannot raise such an error
# in v1, as it wouldn't break existing pipelines.
is_compiling_for_v2 = False
for frame in inspect.stack():
if '_create_pipeline_v2' in frame:
is_compiling_for_v2 = True
break
def _resolve_commands_and_args_v2(
component_spec: _structures.ComponentSpec,
arguments: Mapping[str, Any],
) -> _components._ResolvedCommandLineAndPaths:
"""Resolves the command line argument placeholders for v2 (IR).
Args:
component_spec: The component spec object.
arguments: The dictionary of component arguments.
Returns:
A named tuple: _components._ResolvedCommandLineAndPaths.
"""
inputs_dict = {
input_spec.name: input_spec
for input_spec in component_spec.inputs or []
}
outputs_dict = {
output_spec.name: output_spec
for output_spec in component_spec.outputs or []
}
def _input_artifact_uri_placeholder(input_key: str) -> str:
if is_compiling_for_v2 and type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError(
'Input "{}" with type "{}" cannot be paired with '
'InputUriPlaceholder.'.format(input_key,
inputs_dict[input_key].type))
else:
return "{{{{$.inputs.artifacts['{}'].uri}}}}".format(input_key)
def _input_artifact_path_placeholder(input_key: str) -> str:
if is_compiling_for_v2 and type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError(
'Input "{}" with type "{}" cannot be paired with '
'InputPathPlaceholder.'.format(
input_key, inputs_dict[input_key].type))
elif is_compiling_for_v2 and input_key in importer_specs:
raise TypeError(
'Input "{}" with type "{}" is not connected to any upstream output. '
'However it is used with InputPathPlaceholder. '
'If you want to import an existing artifact using a system-connected'
' importer node, use InputUriPlaceholder instead. '
'Or if you just want to pass a string parameter, use string type and'
' InputValuePlaceholder instead.'.format(
input_key, inputs_dict[input_key].type))
else:
return "{{{{$.inputs.artifacts['{}'].path}}}}".format(
input_key)
def _input_parameter_placeholder(input_key: str) -> str:
if is_compiling_for_v2 and not type_utils.is_parameter_type(
inputs_dict[input_key].type):
raise TypeError(
'Input "{}" with type "{}" cannot be paired with '
'InputValuePlaceholder.'.format(
input_key, inputs_dict[input_key].type))
else:
return "{{{{$.inputs.parameters['{}']}}}}".format(input_key)
def _output_artifact_uri_placeholder(output_key: str) -> str:
if is_compiling_for_v2 and type_utils.is_parameter_type(
outputs_dict[output_key].type):
raise TypeError(
'Output "{}" with type "{}" cannot be paired with '
'OutputUriPlaceholder.'.format(
output_key, outputs_dict[output_key].type))
else:
return "{{{{$.outputs.artifacts['{}'].uri}}}}".format(
output_key)
def _output_artifact_path_placeholder(output_key: str) -> str:
return "{{{{$.outputs.artifacts['{}'].path}}}}".format(output_key)
def _output_parameter_path_placeholder(output_key: str) -> str:
return "{{{{$.outputs.parameters['{}'].output_file}}}}".format(
output_key)
def _resolve_output_path_placeholder(output_key: str) -> str:
if type_utils.is_parameter_type(outputs_dict[output_key].type):
return _output_parameter_path_placeholder(output_key)
else:
return _output_artifact_path_placeholder(output_key)
placeholder_resolver = ExtraPlaceholderResolver()
def _resolve_ir_placeholders_v2(
arg,
component_spec: _structures.ComponentSpec,
arguments: dict,
) -> str:
inputs_dict = {
input_spec.name: input_spec
for input_spec in component_spec.inputs or []
}
if isinstance(arg, _structures.InputValuePlaceholder):
input_name = arg.input_name
input_value = arguments.get(input_name, None)
if input_value is not None:
return _input_parameter_placeholder(input_name)
else:
input_spec = inputs_dict[input_name]
if input_spec.optional:
return None
else:
raise ValueError(
'No value provided for input {}'.format(
input_name))
elif isinstance(arg, _structures.InputUriPlaceholder):
input_name = arg.input_name
if input_name in arguments:
input_uri = _input_artifact_uri_placeholder(input_name)
return input_uri
else:
input_spec = inputs_dict[input_name]
if input_spec.optional:
return None
else:
raise ValueError(
'No value provided for input {}'.format(
input_name))
elif isinstance(arg, _structures.OutputUriPlaceholder):
output_name = arg.output_name
output_uri = _output_artifact_uri_placeholder(output_name)
return output_uri
return placeholder_resolver.resolve_placeholder(
arg=arg,
component_spec=component_spec,
arguments=arguments,
)
resolved_cmd = _components._resolve_command_line_and_paths(
component_spec=component_spec,
arguments=arguments,
input_path_generator=_input_artifact_path_placeholder,
output_path_generator=_resolve_output_path_placeholder,
placeholder_resolver=_resolve_ir_placeholders_v2,
)
return resolved_cmd
pipeline_task_spec = pipeline_spec_pb2.PipelineTaskSpec()
# Keep track of auto-injected importer spec.
importer_specs = {}
# Check types of the reference arguments and serialize PipelineParams
original_arguments = arguments
arguments = arguments.copy()
# Preserver input params for ContainerOp.inputs
input_params = list(
set([
param for param in arguments.values()
if isinstance(param, _pipeline_param.PipelineParam)
]))
for input_name, argument_value in arguments.items():
if isinstance(argument_value, _pipeline_param.PipelineParam):
input_type = component_spec._inputs_dict[input_name].type
reference_type = argument_value.param_type
types.verify_type_compatibility(
reference_type, input_type,
'Incompatible argument passed to the input "{}" of component "{}": '
.format(input_name, component_spec.name))
arguments[input_name] = str(argument_value)
if type_utils.is_parameter_type(input_type):
if argument_value.op_name:
pipeline_task_spec.inputs.parameters[
input_name].task_output_parameter.producer_task = (
dsl_utils.sanitize_task_name(
argument_value.op_name))
pipeline_task_spec.inputs.parameters[
input_name].task_output_parameter.output_parameter_key = (
argument_value.name)
else:
pipeline_task_spec.inputs.parameters[
input_name].component_input_parameter = argument_value.name
else:
if argument_value.op_name:
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.producer_task = (
dsl_utils.sanitize_task_name(
argument_value.op_name))
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.output_artifact_key = (
argument_value.name)
elif is_compiling_for_v2:
# argument_value.op_name could be none, in which case an importer node
# will be inserted later.
# Importer node is only applicable for v2 engine.
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.producer_task = ''
type_schema = type_utils.get_input_artifact_type_schema(
input_name, component_spec.inputs)
importer_specs[
input_name] = importer_node.build_importer_spec(
input_type_schema=type_schema,
pipeline_param_name=argument_value.name)
elif isinstance(argument_value, str):
pipeline_params = _pipeline_param.extract_pipelineparams_from_any(
argument_value)
if pipeline_params and is_compiling_for_v2:
# argument_value contains PipelineParam placeholders which needs to be
# replaced. And the input needs to be added to the task spec.
for param in pipeline_params:
# Form the name for the compiler injected input, and make sure it
# doesn't collide with any existing input names.
additional_input_name = (
dsl_component_spec.
additional_input_name_for_pipelineparam(param))
for existing_input_name, _ in arguments.items():
if existing_input_name == additional_input_name:
raise ValueError(
'Name collision between existing input name '
'{} and compiler injected input name {}'.
format(existing_input_name,
additional_input_name))
additional_input_placeholder = (
"{{{{$.inputs.parameters['{}']}}}}".format(
additional_input_name))
argument_value = argument_value.replace(
param.pattern, additional_input_placeholder)
# The output references are subject to change -- the producer task may
# not be whitin the same DAG.
if param.op_name:
pipeline_task_spec.inputs.parameters[
additional_input_name].task_output_parameter.producer_task = (
dsl_utils.sanitize_task_name(param.op_name))
pipeline_task_spec.inputs.parameters[
additional_input_name].task_output_parameter.output_parameter_key = param.name
else:
pipeline_task_spec.inputs.parameters[
additional_input_name].component_input_parameter = param.full_name
input_type = component_spec._inputs_dict[input_name].type
if type_utils.is_parameter_type(input_type):
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.string_value = (
argument_value)
elif is_compiling_for_v2:
# An importer node with constant value artifact_uri will be inserted.
# Importer node is only applicable for v2 engine.
pipeline_task_spec.inputs.artifacts[
input_name].task_output_artifact.producer_task = ''
type_schema = type_utils.get_input_artifact_type_schema(
input_name, component_spec.inputs)
importer_specs[input_name] = importer_node.build_importer_spec(
input_type_schema=type_schema,
constant_value=argument_value)
elif isinstance(argument_value, int):
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.int_value = argument_value
elif isinstance(argument_value, float):
pipeline_task_spec.inputs.parameters[
input_name].runtime_value.constant_value.double_value = argument_value
elif isinstance(argument_value, _container_op.ContainerOp):
raise TypeError(
'ContainerOp object {} was passed to component as an input argument. '
'Pass a single output instead.'.format(input_name))
else:
if is_compiling_for_v2:
raise NotImplementedError(
'Input argument supports only the following types: PipelineParam'
', str, int, float. Got: "{}".'.format(argument_value))
if not component_spec.name:
component_spec.name = _components._default_component_name
# task.name is unique at this point.
pipeline_task_spec.task_info.name = (dsl_utils.sanitize_task_name(
task.name))
resolved_cmd = _resolve_commands_and_args_v2(component_spec=component_spec,
arguments=original_arguments)
task.container_spec = (
pipeline_spec_pb2.PipelineDeploymentConfig.PipelineContainerSpec(
image=component_spec.implementation.container.image,
command=resolved_cmd.command,
args=resolved_cmd.args))
# TODO(chensun): dedupe IR component_spec and contaienr_spec
pipeline_task_spec.component_ref.name = (dsl_utils.sanitize_component_name(
task.name))
executor_label = dsl_utils.sanitize_executor_label(task.name)
task.component_spec = dsl_component_spec.build_component_spec_from_structure(
component_spec, executor_label, arguments.keys())
task.task_spec = pipeline_task_spec
task.importer_specs = importer_specs
# Override command and arguments if compiling to v2.
if is_compiling_for_v2:
task.command = resolved_cmd.command
task.arguments = resolved_cmd.args
# limit this to v2 compiling only to avoid possible behavior change in v1.
task.inputs = input_params
