def test_handle_parsing_predicates(self):
component_text = '''\
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
task 2:
componentRef: {name: Comp 2}
arguments:
in2 1: 21
in2 2: {taskOutput: {taskId: task 1, outputName: out1 1}}
isEnabled:
not:
and:
op1:
'>':
op1: {taskOutput: {taskId: task 1, outputName: out1 1}}
op2: 0
op2:
'==':
op1: {taskOutput: {taskId: task 1, outputName: out1 2}}
op2: 'head'
'''
struct = load_yaml(component_text)
ComponentSpec.from_dict(struct)
def test_handle_parsing_graph_component(self):
component_text = '''\
inputs:
- {name: graph in 1}
- {name: graph in 2}
outputs:
- {name: graph out 1}
- {name: graph out 2}
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
arguments:
in1 1: 11
task 2:
componentRef: {name: Comp 2}
arguments:
in2 1: 21
in2 2: {taskOutput: {taskId: task 1, outputName: out1 1}}
task 3:
componentRef: {name: Comp 3}
arguments:
in3 1: {taskOutput: {taskId: task 2, outputName: out2 1}}
in3 2: {graphInput: {inputName: graph in 1}}
outputValues:
graph out 1: {taskOutput: {taskId: task 3, outputName: out3 1}}
graph out 2: {taskOutput: {taskId: task 1, outputName: out1 2}}
'''
struct = load_yaml(component_text)
ComponentSpec.from_dict(struct)
def test_handle_constructing_graph_component(self):
task1 = TaskSpec(component_ref=ComponentReference(name='comp 1'), arguments={'in1 1': 11})
task2 = TaskSpec(component_ref=ComponentReference(name='comp 2'), arguments={'in2 1': 21, 'in2 2': TaskOutputArgument.construct(task_id='task 1', output_name='out1 1')})
task3 = TaskSpec(component_ref=ComponentReference(name='comp 3'), arguments={'in3 1': TaskOutputArgument.construct(task_id='task 2', output_name='out2 1'), 'in3 2': GraphInputReference(input_name='graph in 1').as_argument()})
graph_component1 = ComponentSpec(
inputs=[
InputSpec(name='graph in 1'),
InputSpec(name='graph in 2'),
],
outputs=[
OutputSpec(name='graph out 1'),
OutputSpec(name='graph out 2'),
],
implementation=GraphImplementation(graph=GraphSpec(
tasks={
'task 1': task1,
'task 2': task2,
'task 3': task3,
},
output_values={
'graph out 1': TaskOutputArgument.construct(task_id='task 3', output_name='out3 1'),
'graph out 2': TaskOutputArgument.construct(task_id='task 1', output_name='out1 2'),
}
))
)
def test_fail_on_cyclic_references(self):
component_text = '''\
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
arguments:
in1 1: {taskOutput: {taskId: task 2, outputName: out2 1}}
task 2:
componentRef: {name: Comp 2}
arguments:
in2 1: {taskOutput: {taskId: task 1, outputName: out1 1}}
'''
struct = load_yaml(component_text)
ComponentSpec.from_dict(struct)
def test_handle_parsing_task_volumes_and_mounts(self):
component_text = '''\
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
executionOptions:
kubernetesOptions:
mainContainer:
volumeMounts:
- name: workdir
mountPath: /mnt/vol
podSpec:
volumes:
- name: workdir
emptyDir: {}
'''
struct = load_yaml(component_text)
component_spec = ComponentSpec.from_dict(struct)
self.assertEqual(
component_spec.implementation.graph.tasks['task 1'].
execution_options.kubernetes_options.pod_spec.volumes[0].name,
'workdir')
self.assertIsNotNone(
component_spec.implementation.graph.tasks['task 1'].
execution_options.kubernetes_options.pod_spec.volumes[0].empty_dir)
def test_decorator_metadata(self):
"""Test @pipeline decorator with metadata."""
@pipeline(name='p1', description='description1')
def my_pipeline1(a: {'Schema':
{
'file_type': 'csv'
}} = 'good',
b: Integer() = 12):
pass
golden_meta = ComponentSpec(name='p1',
description='description1',
inputs=[])
golden_meta.inputs.append(
InputSpec(name='a',
type={'Schema': {
'file_type': 'csv'
}},
default='good'))
golden_meta.inputs.append(
InputSpec(name='b',
type={
'Integer': {
'openapi_schema_validator': {
"type": "integer"
}
}
},
default=12))
pipeline_meta = _extract_pipeline_metadata(my_pipeline1)
self.assertEqual(pipeline_meta, golden_meta)
def test_component_metadata(self):
"""Test component decorator metadata."""
class MockContainerOp:
def _set_metadata(self, component_meta):
self._metadata = component_meta
@component
def componentA(
a: {'ArtifactA': {
'file_type': 'csv'
}},
b: Integer() = 12,
c: {'ArtifactB': {
'path_type': 'file',
'file_type': 'tsv'
}} = 'gs://hello/world'
) -> {
'model': Integer()
}:
return MockContainerOp()
containerOp = componentA(1, 2, c=3)
golden_meta = ComponentSpec(name='ComponentA', inputs=[], outputs=[])
golden_meta.inputs.append(
InputSpec(name='a', type={'ArtifactA': {
'file_type': 'csv'
}}))
golden_meta.inputs.append(
InputSpec(name='b',
type={
'Integer': {
'openapi_schema_validator': {
"type": "integer"
}
}
},
default="12",
optional=True))
golden_meta.inputs.append(
InputSpec(
name='c',
type={'ArtifactB': {
'path_type': 'file',
'file_type': 'tsv'
}},
default='gs://hello/world',
optional=True))
golden_meta.outputs.append(
OutputSpec(name='model',
type={
'Integer': {
'openapi_schema_validator': {
"type": "integer"
}
}
}))
self.assertEqual(containerOp._metadata, golden_meta)
def test_handle_parsing_task_container_spec_options(self):
component_text = '''\
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
k8sContainerOptions:
resources:
requests:
memory: 1024Mi
cpu: 200m
'''
struct = load_yaml(component_text)
component_spec = ComponentSpec.from_dict(struct)
self.assertEqual(component_spec.implementation.graph.tasks['task 1'].k8s_container_options.resources.requests['memory'], '1024Mi')
def test_handle_parsing_task_volumes_and_mounts(self):
component_text = '''\
implementation:
graph:
tasks:
task 1:
componentRef: {name: Comp 1}
k8sContainerOptions:
volumeMounts:
- name: workdir
mountPath: /mnt/vol
k8sPodOptions:
spec:
volumes:
- name: workdir
emptyDir: {}
'''
struct = load_yaml(component_text)
component_spec = ComponentSpec.from_dict(struct)
self.assertEqual(component_spec.implementation.graph.tasks['task 1'].k8s_pod_options.spec.volumes[0].name, 'workdir')
self.assertTrue(component_spec.implementation.graph.tasks['task 1'].k8s_pod_options.spec.volumes[0].empty_dir is not None)
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_to_dict(self):
component_meta = ComponentSpec(
name='foobar',
description='foobar example',
inputs=[
InputSpec(name='input1',
description='input1 desc',
type={
'GCSPath': {
'bucket_type': 'directory',
'file_type': 'csv'
}
},
default='default1'),
InputSpec(name='input2',
description='input2 desc',
type={
'TFModel': {
'input_data': 'tensor',
'version': '1.8.0'
}
},
default='default2'),
InputSpec(name='input3',
description='input3 desc',
type='Integer',
default='default3'),
],
outputs=[
OutputSpec(
name='output1',
description='output1 desc',
type={'Schema': {
'file_type': 'tsv'
}},
)
])
golden_meta = {
'name':
'foobar',
'description':
'foobar example',
'inputs': [{
'name': 'input1',
'description': 'input1 desc',
'type': {
'GCSPath': {
'bucket_type': 'directory',
'file_type': 'csv'
}
},
'default': 'default1'
}, {
'name': 'input2',
'description': 'input2 desc',
'type': {
'TFModel': {
'input_data': 'tensor',
'version': '1.8.0'
}
},
'default': 'default2'
}, {
'name': 'input3',
'description': 'input3 desc',
'type': 'Integer',
'default': 'default3'
}],
'outputs': [{
'name': 'output1',
'description': 'output1 desc',
'type': {
'Schema': {
'file_type': 'tsv'
}
},
}]
}
self.assertEqual(component_meta.to_dict(), golden_meta)
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
