def setUp(self):
super().setUp()
self._test_dir = tempfile.mkdtemp()
self._executor_invocation = pipeline_pb2.ExecutorInput()
self._executor_invocation.outputs.output_file = _TEST_OUTPUT_METADATA_JSON
self._executor_invocation.inputs.parameters[
'input_base_uri'].string_value = _TEST_INPUT_DIR
self._executor_invocation.inputs.parameters[
'input_config'].string_value = json_format.MessageToJson(
example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(name='s1',
pattern='span{SPAN}/split1/*'),
example_gen_pb2.Input.Split(name='s2',
pattern='span{SPAN}/split2/*')
]))
self._executor_invocation.outputs.artifacts[
'examples'].artifacts.append(
pipeline_pb2.RuntimeArtifact(
type=pipeline_pb2.ArtifactTypeSchema(
instance_schema=compiler_utils.get_artifact_schema(
standard_artifacts.Examples()))))
self._executor_invocation_from_file = fileio.open(
os.path.join(os.path.dirname(__file__), 'testdata',
'executor_invocation.json'), 'r').read()
self._expected_result_from_file = fileio.open(
os.path.join(os.path.dirname(__file__), 'testdata',
'expected_output_metadata.json'), 'r').read()
self._olddir = os.getcwd()
os.chdir(self._test_dir)
fileio.makedirs(os.path.dirname(_TEST_OUTPUT_METADATA_JSON))
fileio.makedirs(os.path.dirname(_TEST_INPUT_DIR))
def _build_importer_spec(self) -> ImporterSpec:
"""Builds ImporterSpec."""
assert isinstance(self._node, importer.Importer)
output_channel = self._node.outputs[importer.IMPORT_RESULT_KEY]
result = ImporterSpec()
# Importer's output channel contains one artifact instance with
# additional properties.
artifact_instance = list(output_channel.get())[0]
struct_proto = compiler_utils.pack_artifact_properties(
artifact_instance)
if struct_proto:
result.metadata.CopyFrom(struct_proto)
result.reimport = bool(
self._exec_properties[importer.REIMPORT_OPTION_KEY])
result.artifact_uri.CopyFrom(
compiler_utils.value_converter(
self._exec_properties[importer.SOURCE_URI_KEY]))
single_artifact = artifact_utils.get_single_instance(
list(output_channel.get()))
result.type_schema.CopyFrom(
pipeline_pb2.ArtifactTypeSchema(
instance_schema=compiler_utils.get_artifact_schema(
single_artifact)))
return result
def build_input_artifact_spec(
channel_spec: channel.Channel
) -> pipeline_pb2.ComponentInputsSpec.ArtifactSpec:
"""Builds artifact type spec for an input channel."""
artifact_instance = channel_spec.type()
result = pipeline_pb2.ComponentInputsSpec.ArtifactSpec()
result.artifact_type.CopyFrom(
pipeline_pb2.ArtifactTypeSchema(
instance_schema=get_artifact_schema(artifact_instance)))
_validate_properties_schema(
instance_schema=result.artifact_type.instance_schema,
properties=channel_spec.type.PROPERTIES)
return result
def build_output_artifact_spec(
channel_spec: channel.Channel
) -> pipeline_pb2.TaskOutputsSpec.OutputArtifactSpec:
"""Builds the Kubeflow pipeline output artifact spec from TFX channel spec."""
artifact_instance = channel_spec.type()
result = pipeline_pb2.TaskOutputsSpec.OutputArtifactSpec()
result.artifact_type.CopyFrom(
pipeline_pb2.ArtifactTypeSchema(
instance_schema=get_artifact_schema(artifact_instance)))
for k, v in convert_from_tfx_properties(
artifact_instance.mlmd_artifact.properties).items():
result.properties[k].CopyFrom(v)
for k, v in convert_from_tfx_properties(
artifact_instance.mlmd_artifact.custom_properties).items():
result.custom_properties[k].CopyFrom(v)
return result
def _build_importer_spec(self) -> ImporterSpec:
"""Builds ImporterSpec."""
assert isinstance(self._node, importer_node.ImporterNode)
result = ImporterSpec(
properties=compiler_utils.convert_from_tfx_properties(
self._exec_properties[importer_node.PROPERTIES_KEY]),
custom_properties=compiler_utils.convert_from_tfx_properties(
self._exec_properties[importer_node.CUSTOM_PROPERTIES_KEY]))
result.reimport = bool(
self._exec_properties[importer_node.REIMPORT_OPTION_KEY])
result.artifact_uri.CopyFrom(
compiler_utils.value_converter(
self._exec_properties[importer_node.SOURCE_URI_KEY]))
single_artifact = artifact_utils.get_single_instance(
list(self._node.outputs[importer_node.IMPORT_RESULT_KEY].get()))
result.type_schema.CopyFrom(
pipeline_pb2.ArtifactTypeSchema(
instance_schema=compiler_utils.get_artifact_schema(
single_artifact)))
return result
def setUp(self):
self._executor_invocation = pipeline_pb2.ExecutorInput()
self._executor_invocation.outputs.output_file = _TEST_OUTPUT_METADATA_JSON
self._executor_invocation.inputs.parameters[
'input_base_uri'].string_value = _TEST_INPUT_DIR
self._executor_invocation.inputs.parameters[
'input_config'].string_value = json_format.MessageToJson(
example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(
name='s1', pattern='span{SPAN}/split1/*'),
example_gen_pb2.Input.Split(
name='s2', pattern='span{SPAN}/split2/*')
]))
self._executor_invocation.outputs.artifacts['examples'].artifacts.append(
pipeline_pb2.RuntimeArtifact(
type=pipeline_pb2.ArtifactTypeSchema(
instance_schema=compiler_utils.get_artifact_schema(
standard_artifacts.Examples()))))
self._executor_invocation_from_file = fileio.open(
os.path.join(
os.path.dirname(__file__), 'testdata', 'executor_invocation.json'),
'r').read()
logging.debug('Executor invocation under test: %s',
self._executor_invocation_from_file)
self._expected_result_from_file = fileio.open(
os.path.join(
os.path.dirname(__file__), 'testdata',
'expected_output_metadata.json'), 'r').read()
logging.debug('Expecting output metadata JSON: %s',
self._expected_result_from_file)
# The initialization of TempWorkingDirTestCase has to be called after all
# the testdata files have been read. Otherwise the original testdata files
# are not accessible after cwd is changed.
super().setUp()
fileio.makedirs(os.path.dirname(_TEST_OUTPUT_METADATA_JSON))
fileio.makedirs(os.path.dirname(_TEST_INPUT_DIR))
def setUp(self):
super().setUp()
self._executor_invocation = pipeline_pb2.ExecutorInput()
self._executor_invocation.outputs.output_file = _TEST_OUTPUT_METADATA_JSON
self._executor_invocation.inputs.parameters[
'input_base_uri'].string_value = _TEST_INPUT_DIR
self._executor_invocation.inputs.parameters[
'input_config'].string_value = json_format.MessageToJson(
example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(
name='s1', pattern='span{SPAN}/split1/*'),
example_gen_pb2.Input.Split(
name='s2', pattern='span{SPAN}/split2/*')
]))
self._executor_invocation.outputs.artifacts['examples'].artifacts.append(
pipeline_pb2.RuntimeArtifact(
type=pipeline_pb2.ArtifactTypeSchema(
instance_schema=compiler_utils.get_artifact_schema(
standard_artifacts.Examples()))))
self._executor_invocation_from_file = fileio.open(
os.path.join(
os.path.dirname(__file__), 'testdata', 'executor_invocation.json'),
'r').read()
logging.debug('Executor invocation under test: %s',
self._executor_invocation_from_file)
self._expected_result_from_file = fileio.open(
os.path.join(
os.path.dirname(__file__), 'testdata',
'expected_output_metadata.json'), 'r').read()
logging.debug('Expecting output metadata JSON: %s',
self._expected_result_from_file)
# Change working directory after all the testdata files have been read.
self.enter_context(test_case_utils.change_working_dir(self.tmp_dir))
fileio.makedirs(os.path.dirname(_TEST_INPUT_DIR))
def build_output_artifact_spec(
channel_spec: channel.Channel
) -> pipeline_pb2.ComponentOutputsSpec.ArtifactSpec:
"""Builds artifact type spec for an output channel."""
# We use the first artifact instance if available from channel, otherwise
# create one.
artifacts = list(channel_spec.get())
artifact_instance = artifacts[0] if artifacts else channel_spec.type()
result = pipeline_pb2.ComponentOutputsSpec.ArtifactSpec()
result.artifact_type.CopyFrom(
pipeline_pb2.ArtifactTypeSchema(
instance_schema=get_artifact_schema(artifact_instance)))
_validate_properties_schema(
instance_schema=result.artifact_type.instance_schema,
properties=channel_spec.type.PROPERTIES)
struct_proto = pack_artifact_properties(artifact_instance)
if struct_proto:
result.metadata.CopyFrom(struct_proto)
return result
