def execute(self, context):
"""Execute the python dataflow job."""
bucket_helper = GoogleCloudBucketHelper(self.gcp_conn_id,
self.delegate_to)
self.py_file = bucket_helper.google_cloud_to_local(self.py_file)
hook = DataflowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
dataflow_options = self.dataflow_default_options.copy()
dataflow_options.update(self.options)
# Convert argument names from lowerCamelCase to snake case.
camel_to_snake = lambda name: re.sub(
r'[A-Z]', lambda x: '_' + x.group(0).lower(), name)
formatted_options = {
camel_to_snake(key): dataflow_options[key]
for key in dataflow_options
}
hook.start_python_dataflow(
job_name=self.job_name,
variables=formatted_options,
dataflow=self.py_file,
py_options=self.py_options,
py_interpreter=self.py_interpreter,
py_requirements=self.py_requirements,
py_system_site_packages=self.py_system_site_packages,
)
class DataflowCreatePythonJobOperator(BaseOperator):
"""
Launching Cloud Dataflow jobs written in python. Note that both
dataflow_default_options and options will be merged to specify pipeline
execution parameter, and dataflow_default_options is expected to save
high-level options, for instances, project and zone information, which
apply to all dataflow operators in the DAG.
.. seealso::
For more detail on job submission have a look at the reference:
https://cloud.google.com/dataflow/pipelines/specifying-exec-params
:param py_file: Reference to the python dataflow pipeline file.py, e.g.,
/some/local/file/path/to/your/python/pipeline/file. (templated)
:type py_file: str
:param job_name: The 'job_name' to use when executing the DataFlow job
(templated). This ends up being set in the pipeline options, so any entry
with key ``'jobName'`` or ``'job_name'`` in ``options`` will be overwritten.
:type job_name: str
:param py_options: Additional python options, e.g., ["-m", "-v"].
:type py_options: list[str]
:param dataflow_default_options: Map of default job options.
:type dataflow_default_options: dict
:param options: Map of job specific options.The key must be a dictionary.
The value can contain different types:
* If the value is None, the single option - ``--key`` (without value) will be added.
* If the value is False, this option will be skipped
* If the value is True, the single option - ``--key`` (without value) will be added.
* If the value is list, the many options will be added for each key.
If the value is ``['A', 'B']`` and the key is ``key`` then the ``--key=A --key-B`` options
will be left
* Other value types will be replaced with the Python textual representation.
When defining labels (``labels`` option), you can also provide a dictionary.
:type options: dict
:param py_interpreter: Python version of the beam pipeline.
If None, this defaults to the python3.
To track python versions supported by beam and related
issues check: https://issues.apache.org/jira/browse/BEAM-1251
:type py_interpreter: str
:param py_requirements: Additional python package(s) to install.
If a value is passed to this parameter, a new virtual environment has been created with
additional packages installed.
You could also install the apache_beam package if it is not installed on your system or you want
to use a different version.
:type py_requirements: List[str]
:param py_system_site_packages: Whether to include system_site_packages in your virtualenv.
See virtualenv documentation for more information.
This option is only relevant if the ``py_requirements`` parameter is not None.
:param gcp_conn_id: The connection ID to use connecting to Google Cloud.
:type gcp_conn_id: str
:param project_id: Optional, the Google Cloud project ID in which to start a job.
If set to None or missing, the default project_id from the Google Cloud connection is used.
:type project_id: str
:param location: Job location.
:type location: str
:param delegate_to: The account to impersonate using domain-wide delegation of authority,
if any. For this to work, the service account making the request must have
domain-wide delegation enabled.
:type delegate_to: str
:param poll_sleep: The time in seconds to sleep between polling Google
Cloud Platform for the dataflow job status while the job is in the
JOB_STATE_RUNNING state.
:type poll_sleep: int
"""
template_fields = [
'options', 'dataflow_default_options', 'job_name', 'py_file'
]
@apply_defaults
def __init__( # pylint: disable=too-many-arguments
self,
*,
py_file: str,
job_name: str = '{{task.task_id}}',
dataflow_default_options: Optional[dict] = None,
options: Optional[dict] = None,
py_interpreter: str = "python3",
py_options: Optional[List[str]] = None,
py_requirements: Optional[List[str]] = None,
py_system_site_packages: bool = False,
project_id: Optional[str] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
gcp_conn_id: str = 'google_cloud_default',
delegate_to: Optional[str] = None,
poll_sleep: int = 10,
**kwargs,
) -> None:
super().__init__(**kwargs)
self.py_file = py_file
self.job_name = job_name
self.py_options = py_options or []
self.dataflow_default_options = dataflow_default_options or {}
self.options = options or {}
self.options.setdefault('labels', {}).update({
'airflow-version':
'v' + version.replace('.', '-').replace('+', '-')
})
self.py_interpreter = py_interpreter
self.py_requirements = py_requirements
self.py_system_site_packages = py_system_site_packages
self.project_id = project_id
self.location = location
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.poll_sleep = poll_sleep
self.job_id = None
self.hook = None
def execute(self, context):
"""Execute the python dataflow job."""
with ExitStack() as exit_stack:
if self.py_file.lower().startswith('gs://'):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
tmp_gcs_file = exit_stack.enter_context( # pylint: disable=no-member
gcs_hook.provide_file(object_url=self.py_file))
self.py_file = tmp_gcs_file.name
self.hook = DataflowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
dataflow_options = self.dataflow_default_options.copy()
dataflow_options.update(self.options)
# Convert argument names from lowerCamelCase to snake case.
camel_to_snake = lambda name: re.sub(
r'[A-Z]', lambda x: '_' + x.group(0).lower(), name)
formatted_options = {
camel_to_snake(key): dataflow_options[key]
for key in dataflow_options
}
def set_current_job_id(job_id):
self.job_id = job_id
self.hook.start_python_dataflow(
job_name=self.job_name,
variables=formatted_options,
dataflow=self.py_file,
py_options=self.py_options,
py_interpreter=self.py_interpreter,
py_requirements=self.py_requirements,
py_system_site_packages=self.py_system_site_packages,
on_new_job_id_callback=set_current_job_id,
project_id=self.project_id,
location=self.location,
)
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job_id:
self.hook.cancel_job(job_id=self.job_id,
project_id=self.project_id)
class DataflowCreatePythonJobOperator(BaseOperator):
"""
Launching Cloud Dataflow jobs written in python. Note that both
dataflow_default_options and options will be merged to specify pipeline
execution parameter, and dataflow_default_options is expected to save
high-level options, for instances, project and zone information, which
apply to all dataflow operators in the DAG.
.. seealso::
For more detail on job submission have a look at the reference:
https://cloud.google.com/dataflow/pipelines/specifying-exec-params
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:DataflowCreatePythonJobOperator`
:param py_file: Reference to the python dataflow pipeline file.py, e.g.,
/some/local/file/path/to/your/python/pipeline/file. (templated)
:type py_file: str
:param job_name: The 'job_name' to use when executing the DataFlow job
(templated). This ends up being set in the pipeline options, so any entry
with key ``'jobName'`` or ``'job_name'`` in ``options`` will be overwritten.
:type job_name: str
:param py_options: Additional python options, e.g., ["-m", "-v"].
:type py_options: list[str]
:param dataflow_default_options: Map of default job options.
:type dataflow_default_options: dict
:param options: Map of job specific options.The key must be a dictionary.
The value can contain different types:
* If the value is None, the single option - ``--key`` (without value) will be added.
* If the value is False, this option will be skipped
* If the value is True, the single option - ``--key`` (without value) will be added.
* If the value is list, the many options will be added for each key.
If the value is ``['A', 'B']`` and the key is ``key`` then the ``--key=A --key-B`` options
will be left
* Other value types will be replaced with the Python textual representation.
When defining labels (``labels`` option), you can also provide a dictionary.
:type options: dict
:param py_interpreter: Python version of the beam pipeline.
If None, this defaults to the python3.
To track python versions supported by beam and related
issues check: https://issues.apache.org/jira/browse/BEAM-1251
:type py_interpreter: str
:param py_requirements: Additional python package(s) to install.
If a value is passed to this parameter, a new virtual environment has been created with
additional packages installed.
You could also install the apache_beam package if it is not installed on your system or you want
to use a different version.
:type py_requirements: List[str]
:param py_system_site_packages: Whether to include system_site_packages in your virtualenv.
See virtualenv documentation for more information.
This option is only relevant if the ``py_requirements`` parameter is not None.
:param gcp_conn_id: The connection ID to use connecting to Google Cloud.
:type gcp_conn_id: str
:param project_id: Optional, the Google Cloud project ID in which to start a job.
If set to None or missing, the default project_id from the Google Cloud connection is used.
:type project_id: str
:param location: Job location.
:type location: str
:param delegate_to: The account to impersonate using domain-wide delegation of authority,
if any. For this to work, the service account making the request must have
domain-wide delegation enabled.
:type delegate_to: str
:param poll_sleep: The time in seconds to sleep between polling Google
Cloud Platform for the dataflow job status while the job is in the
JOB_STATE_RUNNING state.
:type poll_sleep: int
:param drain_pipeline: Optional, set to True if want to stop streaming job by draining it
instead of canceling during during killing task instance. See:
https://cloud.google.com/dataflow/docs/guides/stopping-a-pipeline
:type drain_pipeline: bool
:param cancel_timeout: How long (in seconds) operator should wait for the pipeline to be
successfully cancelled when task is being killed.
:type cancel_timeout: Optional[int]
:param wait_until_finished: (Optional)
If True, wait for the end of pipeline execution before exiting.
If False, only submits job.
If None, default behavior.
The default behavior depends on the type of pipeline:
* for the streaming pipeline, wait for jobs to start,
* for the batch pipeline, wait for the jobs to complete.
.. warning::
You cannot call ``PipelineResult.wait_until_finish`` method in your pipeline code for the operator
to work properly. i. e. you must use asynchronous execution. Otherwise, your pipeline will
always wait until finished. For more information, look at:
`Asynchronous execution
<https://cloud.google.com/dataflow/docs/guides/specifying-exec-params#python_10>`__
The process of starting the Dataflow job in Airflow consists of two steps:
* running a subprocess and reading the stderr/stderr log for the job id.
* loop waiting for the end of the job ID from the previous step.
This loop checks the status of the job.
Step two is started just after step one has finished, so if you have wait_until_finished in your
pipeline code, step two will not start until the process stops. When this process stops,
steps two will run, but it will only execute one iteration as the job will be in a terminal state.
If you in your pipeline do not call the wait_for_pipeline method but pass wait_until_finish=True
to the operator, the second loop will wait for the job's terminal state.
If you in your pipeline do not call the wait_for_pipeline method, and pass wait_until_finish=False
to the operator, the second loop will check once is job not in terminal state and exit the loop.
:type wait_until_finished: Optional[bool]
"""
template_fields = [
"options", "dataflow_default_options", "job_name", "py_file"
]
@apply_defaults
def __init__( # pylint: disable=too-many-arguments
self,
*,
py_file: str,
job_name: str = "{{task.task_id}}",
dataflow_default_options: Optional[dict] = None,
options: Optional[dict] = None,
py_interpreter: str = "python3",
py_options: Optional[List[str]] = None,
py_requirements: Optional[List[str]] = None,
py_system_site_packages: bool = False,
project_id: Optional[str] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
poll_sleep: int = 10,
drain_pipeline: bool = False,
cancel_timeout: Optional[int] = 10 * 60,
wait_until_finished: Optional[bool] = None,
**kwargs,
) -> None:
super().__init__(**kwargs)
self.py_file = py_file
self.job_name = job_name
self.py_options = py_options or []
self.dataflow_default_options = dataflow_default_options or {}
self.options = options or {}
self.options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
self.py_interpreter = py_interpreter
self.py_requirements = py_requirements
self.py_system_site_packages = py_system_site_packages
self.project_id = project_id
self.location = location
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.poll_sleep = poll_sleep
self.drain_pipeline = drain_pipeline
self.cancel_timeout = cancel_timeout
self.wait_until_finished = wait_until_finished
self.job_id = None
self.hook: Optional[DataflowHook] = None
def execute(self, context):
"""Execute the python dataflow job."""
with ExitStack() as exit_stack:
if self.py_file.lower().startswith("gs://"):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
tmp_gcs_file = exit_stack.enter_context( # pylint: disable=no-member
gcs_hook.provide_file(object_url=self.py_file))
self.py_file = tmp_gcs_file.name
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep,
drain_pipeline=self.drain_pipeline,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
dataflow_options = self.dataflow_default_options.copy()
dataflow_options.update(self.options)
# Convert argument names from lowerCamelCase to snake case.
camel_to_snake = lambda name: re.sub(
r"[A-Z]", lambda x: "_" + x.group(0).lower(), name)
formatted_options = {
camel_to_snake(key): dataflow_options[key]
for key in dataflow_options
}
def set_current_job_id(job_id):
self.job_id = job_id
self.hook.start_python_dataflow( # type: ignore[attr-defined]
job_name=self.job_name,
variables=formatted_options,
dataflow=self.py_file,
py_options=self.py_options,
py_interpreter=self.py_interpreter,
py_requirements=self.py_requirements,
py_system_site_packages=self.py_system_site_packages,
on_new_job_id_callback=set_current_job_id,
project_id=self.project_id,
location=self.location,
)
return {"job_id": self.job_id}
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job_id:
self.hook.cancel_job(job_id=self.job_id,
project_id=self.project_id)
class TestDataflowHook(unittest.TestCase):
def setUp(self):
with mock.patch(BASE_STRING.format('CloudBaseHook.__init__'),
new=mock_init):
self.dataflow_hook = DataflowHook(gcp_conn_id='test')
@mock.patch(
"airflow.providers.google.cloud.hooks.dataflow.DataflowHook._authorize"
)
@mock.patch("airflow.providers.google.cloud.hooks.dataflow.build")
def test_dataflow_client_creation(self, mock_build, mock_authorize):
result = self.dataflow_hook.get_conn()
mock_build.assert_called_once_with('dataflow',
'v1b3',
http=mock_authorize.return_value,
cache_discovery=False)
self.assertEqual(mock_build.return_value, result)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_python_dataflow(job_name=JOB_NAME,
variables=DATAFLOW_OPTIONS_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS)
expected_cmd = [
"python3", '-m', PY_FILE, '--region=us-central1',
'--runner=DataflowRunner', '--project=test', '--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID)
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@parameterized.expand([('default_to_python3', 'python3'),
('major_version_2', 'python2'),
('major_version_3', 'python3'),
('minor_version', 'python3.6')])
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_custom_interpreter(
self, name, py_interpreter, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
del name # unused variable
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_python_dataflow(job_name=JOB_NAME,
variables=DATAFLOW_OPTIONS_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
py_interpreter=py_interpreter)
expected_cmd = [
py_interpreter, '-m', PY_FILE, '--region=us-central1',
'--runner=DataflowRunner', '--project=test', '--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID)
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_java_dataflow(job_name=JOB_NAME,
variables=DATAFLOW_OPTIONS_JAVA,
jar=JAR_FILE)
expected_cmd = [
'java', '-jar', JAR_FILE, '--region=us-central1',
'--runner=DataflowRunner', '--project=test',
'--stagingLocation=gs://test/staging', '--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID)
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow_with_job_class(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_java_dataflow(job_name=JOB_NAME,
variables=DATAFLOW_OPTIONS_JAVA,
jar=JAR_FILE,
job_class=JOB_CLASS)
expected_cmd = [
'java', '-cp', JAR_FILE, JOB_CLASS, '--region=us-central1',
'--runner=DataflowRunner', '--project=test',
'--stagingLocation=gs://test/staging', '--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID)
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@parameterized.expand([
(JOB_NAME, JOB_NAME, False),
('test-example', 'test_example', False),
('test-dataflow-pipeline-12345678', JOB_NAME, True),
('test-example-12345678', 'test_example', True),
('df-job-1', 'df-job-1', False),
('df-job', 'df-job', False),
('dfjob', 'dfjob', False),
('dfjob1', 'dfjob1', False),
])
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
def test_valid_dataflow_job_name(self, expected_result, job_name,
append_job_name, mock_uuid4):
job_name = self.dataflow_hook._build_dataflow_job_name(
job_name=job_name, append_job_name=append_job_name)
self.assertEqual(expected_result, job_name)
@parameterized.expand([("1dfjob@", ), ("dfjob@", ), ("df^jo", )])
def test_build_dataflow_job_name_with_invalid_value(self, job_name):
self.assertRaises(ValueError,
self.dataflow_hook._build_dataflow_job_name,
job_name=job_name,
append_job_name=False)
class TestDataflowHook(unittest.TestCase):
def setUp(self):
with mock.patch(BASE_STRING.format('GoogleBaseHook.__init__'),
new=mock_init):
self.dataflow_hook = DataflowHook(gcp_conn_id='test')
@mock.patch(
"airflow.providers.google.cloud.hooks.dataflow.DataflowHook._authorize"
)
@mock.patch("airflow.providers.google.cloud.hooks.dataflow.build")
def test_dataflow_client_creation(self, mock_build, mock_authorize):
result = self.dataflow_hook.get_conn()
mock_build.assert_called_once_with('dataflow',
'v1b3',
http=mock_authorize.return_value,
cache_discovery=False)
self.assertEqual(mock_build.return_value, result)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
)
expected_cmd = [
"python3",
'-m',
PY_FILE,
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_custom_region_as_variable(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
variables = copy.deepcopy(DATAFLOW_VARIABLES_PY)
variables['region'] = TEST_LOCATION
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=variables,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
)
expected_cmd = [
"python3",
'-m',
PY_FILE,
f'--region={TEST_LOCATION}',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_custom_region_as_paramater(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
location=TEST_LOCATION,
)
expected_cmd = [
"python3",
'-m',
PY_FILE,
f'--region={TEST_LOCATION}',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_multiple_extra_packages(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
variables: Dict[str, Any] = copy.deepcopy(DATAFLOW_VARIABLES_PY)
variables['extra-package'] = ['a.whl', 'b.whl']
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=variables,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
)
expected_cmd = [
"python3",
'-m',
PY_FILE,
'--extra-package=a.whl',
'--extra-package=b.whl',
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@parameterized.expand([
('default_to_python3', 'python3'),
('major_version_2', 'python2'),
('major_version_3', 'python3'),
('minor_version', 'python3.6'),
])
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_custom_interpreter(
self,
name,
py_interpreter,
mock_conn,
mock_dataflow,
mock_dataflowjob,
mock_uuid,
):
del name # unused variable
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
py_interpreter=py_interpreter,
)
expected_cmd = [
py_interpreter,
'-m',
PY_FILE,
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@parameterized.expand([
(['foo-bar'], False),
(['foo-bar'], True),
([], True),
])
@mock.patch(DATAFLOW_STRING.format('prepare_virtualenv'))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_non_empty_py_requirements_and_without_system_packages(
self,
current_py_requirements,
current_py_system_site_packages,
mock_conn,
mock_dataflow,
mock_dataflowjob,
mock_uuid,
mock_virtualenv,
):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
mock_virtualenv.return_value = '/dummy_dir/bin/python'
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
py_requirements=current_py_requirements,
py_system_site_packages=current_py_system_site_packages,
)
expected_cmd = [
'/dummy_dir/bin/python',
'-m',
PY_FILE,
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--labels=foo=bar',
'--staging_location=gs://test/staging',
'--job_name={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_python_dataflow_with_empty_py_requirements_and_without_system_packages(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
with self.assertRaisesRegex(AirflowException,
"Invalid method invocation."):
self.dataflow_hook.start_python_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_PY,
dataflow=PY_FILE,
py_options=PY_OPTIONS,
py_requirements=[],
)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_java_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_JAVA,
jar=JAR_FILE)
expected_cmd = [
'java',
'-jar',
JAR_FILE,
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--stagingLocation=gs://test/staging',
'--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(
sorted(expected_cmd),
sorted(mock_dataflow.call_args[1]["cmd"]),
)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow_with_multiple_values_in_variables(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
variables: Dict[str, Any] = copy.deepcopy(DATAFLOW_VARIABLES_JAVA)
variables['mock-option'] = ['a.whl', 'b.whl']
self.dataflow_hook.start_java_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=variables,
jar=JAR_FILE)
expected_cmd = [
'java',
'-jar',
JAR_FILE,
'--mock-option=a.whl',
'--mock-option=b.whl',
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--stagingLocation=gs://test/staging',
'--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow_with_custom_region_as_variable(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
variables = copy.deepcopy(DATAFLOW_VARIABLES_JAVA)
variables['region'] = TEST_LOCATION
self.dataflow_hook.start_java_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=variables,
jar=JAR_FILE)
expected_cmd = [
'java',
'-jar',
JAR_FILE,
f'--region={TEST_LOCATION}',
'--runner=DataflowRunner',
'--project=test',
'--stagingLocation=gs://test/staging',
'--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(
sorted(expected_cmd),
sorted(mock_dataflow.call_args[1]["cmd"]),
)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow_with_custom_region_as_parameter(
self, mock_conn, mock_dataflow, mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
variables = copy.deepcopy(DATAFLOW_VARIABLES_JAVA)
variables['region'] = TEST_LOCATION
self.dataflow_hook.start_java_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=variables,
jar=JAR_FILE)
expected_cmd = [
'java',
'-jar',
JAR_FILE,
f'--region={TEST_LOCATION}',
'--runner=DataflowRunner',
'--project=test',
'--stagingLocation=gs://test/staging',
'--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(
sorted(expected_cmd),
sorted(mock_dataflow.call_args[1]["cmd"]),
)
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'))
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('_DataflowRunner'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_java_dataflow_with_job_class(self, mock_conn, mock_dataflow,
mock_dataflowjob, mock_uuid):
mock_uuid.return_value = MOCK_UUID
mock_conn.return_value = None
dataflow_instance = mock_dataflow.return_value
dataflow_instance.wait_for_done.return_value = None
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
self.dataflow_hook.start_java_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=DATAFLOW_VARIABLES_JAVA,
jar=JAR_FILE,
job_class=JOB_CLASS)
expected_cmd = [
'java',
'-cp',
JAR_FILE,
JOB_CLASS,
'--region=us-central1',
'--runner=DataflowRunner',
'--project=test',
'--stagingLocation=gs://test/staging',
'--labels={"foo":"bar"}',
'--jobName={}-{}'.format(JOB_NAME, MOCK_UUID),
]
self.assertListEqual(sorted(mock_dataflow.call_args[1]["cmd"]),
sorted(expected_cmd))
@parameterized.expand([
(JOB_NAME, JOB_NAME, False),
('test-example', 'test_example', False),
('test-dataflow-pipeline-12345678', JOB_NAME, True),
('test-example-12345678', 'test_example', True),
('df-job-1', 'df-job-1', False),
('df-job', 'df-job', False),
('dfjob', 'dfjob', False),
('dfjob1', 'dfjob1', False),
])
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
def test_valid_dataflow_job_name(self, expected_result, job_name,
append_job_name, mock_uuid4):
job_name = self.dataflow_hook._build_dataflow_job_name(
job_name=job_name, append_job_name=append_job_name)
self.assertEqual(expected_result, job_name)
@parameterized.expand([("1dfjob@", ), ("dfjob@", ), ("df^jo", )])
def test_build_dataflow_job_name_with_invalid_value(self, job_name):
self.assertRaises(ValueError,
self.dataflow_hook._build_dataflow_job_name,
job_name=job_name,
append_job_name=False)
