def test_start_java_pipeline(self, mock_runner):
hook = BeamHook(runner=DEFAULT_RUNNER)
wait_for_done = mock_runner.return_value.wait_for_done
process_line_callback = MagicMock()
hook.start_java_pipeline( # pylint: disable=no-value-for-parameter
jar=JAR_FILE,
variables=copy.deepcopy(BEAM_VARIABLES_JAVA),
process_line_callback=process_line_callback,
)
expected_cmd = [
'java',
'-jar',
JAR_FILE,
f'--runner={DEFAULT_RUNNER}',
'--output=gs://test/output',
'--labels={"foo":"bar"}',
]
mock_runner.assert_called_once_with(cmd=expected_cmd, process_line_callback=process_line_callback)
wait_for_done.assert_called_once_with()
class DataflowHook(GoogleBaseHook):
"""
Hook for Google Dataflow.
All the methods in the hook where project_id is used must be called with
keyword arguments rather than positional.
"""
def __init__(
self,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
poll_sleep: int = 10,
impersonation_chain: Optional[Union[str, Sequence[str]]] = None,
drain_pipeline: bool = False,
cancel_timeout: Optional[int] = 5 * 60,
wait_until_finished: Optional[bool] = None,
) -> None:
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: Optional[str] = None
self.beam_hook = BeamHook(BeamRunnerType.DataflowRunner)
super().__init__(
gcp_conn_id=gcp_conn_id,
delegate_to=delegate_to,
impersonation_chain=impersonation_chain,
)
def get_conn(self) -> build:
"""Returns a Google Cloud Dataflow service object."""
http_authorized = self._authorize()
return build("dataflow",
"v1b3",
http=http_authorized,
cache_discovery=False)
@_fallback_to_location_from_variables
@_fallback_to_project_id_from_variables
@GoogleBaseHook.fallback_to_default_project_id
def start_java_dataflow(
self,
job_name: str,
variables: dict,
jar: str,
project_id: str,
job_class: Optional[str] = None,
append_job_name: bool = True,
multiple_jobs: bool = False,
on_new_job_id_callback: Optional[Callable[[str], None]] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> None:
"""
Starts Dataflow java job.
:param job_name: The name of the job.
:type job_name: str
:param variables: Variables passed to the job.
:type variables: dict
: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.
:param jar: Name of the jar for the job
:type job_class: str
:param job_class: Name of the java class for the job.
:type job_class: str
:param append_job_name: True if unique suffix has to be appended to job name.
:type append_job_name: bool
:param multiple_jobs: True if to check for multiple job in dataflow
:type multiple_jobs: bool
:param on_new_job_id_callback: Callback called when the job ID is known.
:type on_new_job_id_callback: callable
:param location: Job location.
:type location: str
"""
warnings.warn(
""""This method is deprecated.
Please use `airflow.providers.apache.beam.hooks.beam.start.start_java_pipeline`
to start pipeline and `providers.google.cloud.hooks.dataflow.DataflowHook.wait_for_done`
to wait for the required pipeline state.
""",
DeprecationWarning,
stacklevel=3,
)
name = self.build_dataflow_job_name(job_name, append_job_name)
variables["jobName"] = name
variables["region"] = location
variables["project"] = project_id
if "labels" in variables:
variables["labels"] = json.dumps(variables["labels"],
separators=(",", ":"))
self.beam_hook.start_java_pipeline(
variables=variables,
jar=jar,
job_class=job_class,
process_line_callback=
process_line_and_extract_dataflow_job_id_callback(
on_new_job_id_callback),
)
self.wait_for_done(
job_name=name,
location=location,
job_id=self.job_id,
multiple_jobs=multiple_jobs,
)
@_fallback_to_location_from_variables
@_fallback_to_project_id_from_variables
@GoogleBaseHook.fallback_to_default_project_id
def start_template_dataflow(
self,
job_name: str,
variables: dict,
parameters: dict,
dataflow_template: str,
project_id: str,
append_job_name: bool = True,
on_new_job_id_callback: Optional[Callable[[str], None]] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
environment: Optional[dict] = None,
) -> dict:
"""
Starts Dataflow template job.
:param job_name: The name of the job.
:type job_name: str
:param variables: Map of job runtime environment options.
It will update environment argument if passed.
.. seealso::
For more information on possible configurations, look at the API documentation
`https://cloud.google.com/dataflow/pipelines/specifying-exec-params
<https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment>`__
:type variables: dict
:param parameters: Parameters fot the template
:type parameters: dict
:param dataflow_template: GCS path to the template.
:type dataflow_template: 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.
:param append_job_name: True if unique suffix has to be appended to job name.
:type append_job_name: bool
:param on_new_job_id_callback: Callback called when the job ID is known.
:type on_new_job_id_callback: callable
:param location: Job location.
:type location: str
:type environment: Optional, Map of job runtime environment options.
.. seealso::
For more information on possible configurations, look at the API documentation
`https://cloud.google.com/dataflow/pipelines/specifying-exec-params
<https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment>`__
:type environment: Optional[dict]
"""
name = self.build_dataflow_job_name(job_name, append_job_name)
environment = environment or {}
# available keys for runtime environment are listed here:
# https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
environment_keys = [
"numWorkers",
"maxWorkers",
"zone",
"serviceAccountEmail",
"tempLocation",
"bypassTempDirValidation",
"machineType",
"additionalExperiments",
"network",
"subnetwork",
"additionalUserLabels",
"kmsKeyName",
"ipConfiguration",
"workerRegion",
"workerZone",
]
for key in variables:
if key in environment_keys:
if key in environment:
self.log.warning(
"'%s' parameter in 'variables' will override of "
"the same one passed in 'environment'!",
key,
)
environment.update({key: variables[key]})
service = self.get_conn()
request = (service.projects().locations().templates().launch(
projectId=project_id,
location=location,
gcsPath=dataflow_template,
body={
"jobName": name,
"parameters": parameters,
"environment": environment,
},
))
response = request.execute(num_retries=self.num_retries)
job_id = response["job"]["id"]
if on_new_job_id_callback:
on_new_job_id_callback(job_id)
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
name=name,
job_id=job_id,
location=location,
poll_sleep=self.poll_sleep,
num_retries=self.num_retries,
drain_pipeline=self.drain_pipeline,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
jobs_controller.wait_for_done()
return response["job"]
@GoogleBaseHook.fallback_to_default_project_id
def start_flex_template(
self,
body: dict,
location: str,
project_id: str,
on_new_job_id_callback: Optional[Callable[[str], None]] = None,
):
"""
Starts flex templates with the Dataflow pipeline.
:param body: The request body. See:
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.locations.flexTemplates/launch#request-body
:param location: The location of the Dataflow job (for example europe-west1)
:type location: str
:param project_id: The ID of the GCP project that owns the job.
If set to ``None`` or missing, the default project_id from the GCP connection is used.
:type project_id: Optional[str]
:param on_new_job_id_callback: A callback that is called when a Job ID is detected.
:return: the Job
"""
service = self.get_conn()
request = (service.projects().locations().flexTemplates().launch(
projectId=project_id, body=body, location=location))
response = request.execute(num_retries=self.num_retries)
job_id = response["job"]["id"]
if on_new_job_id_callback:
on_new_job_id_callback(job_id)
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
job_id=job_id,
location=location,
poll_sleep=self.poll_sleep,
num_retries=self.num_retries,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
jobs_controller.wait_for_done()
return jobs_controller.get_jobs(refresh=True)[0]
@_fallback_to_location_from_variables
@_fallback_to_project_id_from_variables
@GoogleBaseHook.fallback_to_default_project_id
def start_python_dataflow(
self,
job_name: str,
variables: dict,
dataflow: str,
py_options: List[str],
project_id: str,
py_interpreter: str = "python3",
py_requirements: Optional[List[str]] = None,
py_system_site_packages: bool = False,
append_job_name: bool = True,
on_new_job_id_callback: Optional[Callable[[str], None]] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
):
"""
Starts Dataflow job.
:param job_name: The name of the job.
:type job_name: str
:param variables: Variables passed to the job.
:type variables: Dict
:param dataflow: Name of the Dataflow process.
:type dataflow: str
:param py_options: Additional options.
:type py_options: List[str]
:param project_id: The ID of the GCP project that owns the job.
If set to ``None`` or missing, the default project_id from the GCP connection is used.
:type project_id: Optional[str]
: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
: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.
:type py_interpreter: str
:param append_job_name: True if unique suffix has to be appended to job name.
:type append_job_name: bool
: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.
:param on_new_job_id_callback: Callback called when the job ID is known.
:type on_new_job_id_callback: callable
:param location: Job location.
:type location: str
"""
warnings.warn(
"""This method is deprecated.
Please use `airflow.providers.apache.beam.hooks.beam.start.start_python_pipeline`
to start pipeline and `providers.google.cloud.hooks.dataflow.DataflowHook.wait_for_done`
to wait for the required pipeline state.
""",
DeprecationWarning,
stacklevel=3,
)
name = self.build_dataflow_job_name(job_name, append_job_name)
variables["job_name"] = name
variables["region"] = location
variables["project"] = project_id
self.beam_hook.start_python_pipeline(
variables=variables,
py_file=dataflow,
py_options=py_options,
py_interpreter=py_interpreter,
py_requirements=py_requirements,
py_system_site_packages=py_system_site_packages,
process_line_callback=
process_line_and_extract_dataflow_job_id_callback(
on_new_job_id_callback),
)
self.wait_for_done(
job_name=name,
location=location,
job_id=self.job_id,
)
@staticmethod
def build_dataflow_job_name(job_name: str,
append_job_name: bool = True) -> str:
"""Builds Dataflow job name."""
base_job_name = str(job_name).replace("_", "-")
if not re.match(r"^[a-z]([-a-z0-9]*[a-z0-9])?$", base_job_name):
raise ValueError(
"Invalid job_name ({}); the name must consist of"
"only the characters [-a-z0-9], starting with a "
"letter and ending with a letter or number ".format(
base_job_name))
if append_job_name:
safe_job_name = base_job_name + "-" + str(uuid.uuid4())[:8]
else:
safe_job_name = base_job_name
return safe_job_name
@_fallback_to_location_from_variables
@_fallback_to_project_id_from_variables
@GoogleBaseHook.fallback_to_default_project_id
def is_job_dataflow_running(
self,
name: str,
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
variables: Optional[dict] = None,
) -> bool:
"""
Helper method to check if jos is still running in dataflow
:param name: The name of the job.
:type name: 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
:return: True if job is running.
:rtype: bool
"""
if variables:
warnings.warn(
"The variables parameter has been deprecated. You should pass location using "
"the location parameter.",
DeprecationWarning,
stacklevel=4,
)
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
name=name,
location=location,
poll_sleep=self.poll_sleep,
drain_pipeline=self.drain_pipeline,
num_retries=self.num_retries,
cancel_timeout=self.cancel_timeout,
)
return jobs_controller.is_job_running()
@GoogleBaseHook.fallback_to_default_project_id
def cancel_job(
self,
project_id: str,
job_name: Optional[str] = None,
job_id: Optional[str] = None,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> None:
"""
Cancels the job with the specified name prefix or Job ID.
Parameter ``name`` and ``job_id`` are mutually exclusive.
:param job_name: Name prefix specifying which jobs are to be canceled.
:type job_name: str
:param job_id: Job ID specifying which jobs are to be canceled.
:type job_id: str
:param location: Job location.
:type location: 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:
"""
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
name=job_name,
job_id=job_id,
location=location,
poll_sleep=self.poll_sleep,
drain_pipeline=self.drain_pipeline,
num_retries=self.num_retries,
cancel_timeout=self.cancel_timeout,
)
jobs_controller.cancel()
@GoogleBaseHook.fallback_to_default_project_id
def start_sql_job(
self,
job_name: str,
query: str,
options: Dict[str, Any],
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
on_new_job_id_callback: Optional[Callable[[str], None]] = None,
):
"""
Starts Dataflow SQL query.
:param job_name: The unique name to assign to the Cloud Dataflow job.
:type job_name: str
:param query: The SQL query to execute.
:type query: str
:param options: Job parameters to be executed.
For more information, look at:
`https://cloud.google.com/sdk/gcloud/reference/beta/dataflow/sql/query
<gcloud beta dataflow sql query>`__
command reference
:param location: The location of the Dataflow job (for example europe-west1)
:type location: str
:param project_id: The ID of the GCP project that owns the job.
If set to ``None`` or missing, the default project_id from the GCP connection is used.
:type project_id: Optional[str]
:param on_new_job_id_callback: Callback called when the job ID is known.
:type on_new_job_id_callback: callable
:return: the new job object
"""
cmd = [
"gcloud",
"dataflow",
"sql",
"query",
query,
f"--project={project_id}",
"--format=value(job.id)",
f"--job-name={job_name}",
f"--region={location}",
*(beam_options_to_args(options)),
]
self.log.info("Executing command: %s",
" ".join(shlex.quote(c) for c in cmd))
with self.provide_authorized_gcloud():
proc = subprocess.run(cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
self.log.info("Output: %s", proc.stdout.decode())
self.log.warning("Stderr: %s", proc.stderr.decode())
self.log.info("Exit code %d", proc.returncode)
if proc.returncode != 0:
raise AirflowException(
f"Process exit with non-zero exit code. Exit code: {proc.returncode}"
)
job_id = proc.stdout.decode().strip()
self.log.info("Created job ID: %s", job_id)
if on_new_job_id_callback:
on_new_job_id_callback(job_id)
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
job_id=job_id,
location=location,
poll_sleep=self.poll_sleep,
num_retries=self.num_retries,
drain_pipeline=self.drain_pipeline,
wait_until_finished=self.wait_until_finished,
)
jobs_controller.wait_for_done()
return jobs_controller.get_jobs(refresh=True)[0]
@GoogleBaseHook.fallback_to_default_project_id
def get_job(
self,
job_id: str,
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> dict:
"""
Gets the job with the specified Job ID.
:param job_id: Job ID to get.
:type job_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:
:param location: The location of the Dataflow job (for example europe-west1). See:
https://cloud.google.com/dataflow/docs/concepts/regional-endpoints
:return: the Job
:rtype: dict
"""
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
location=location,
)
return jobs_controller.fetch_job_by_id(job_id)
@GoogleBaseHook.fallback_to_default_project_id
def fetch_job_metrics_by_id(
self,
job_id: str,
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> dict:
"""
Gets the job metrics with the specified Job ID.
:param job_id: Job ID to get.
:type job_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:
:param location: The location of the Dataflow job (for example europe-west1). See:
https://cloud.google.com/dataflow/docs/concepts/regional-endpoints
:return: the JobMetrics. See:
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/JobMetrics
:rtype: dict
"""
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
location=location,
)
return jobs_controller.fetch_job_metrics_by_id(job_id)
@GoogleBaseHook.fallback_to_default_project_id
def fetch_job_messages_by_id(
self,
job_id: str,
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> List[dict]:
"""
Gets the job messages with the specified Job ID.
:param job_id: Job ID to get.
:type job_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:
:param location: Job location.
:type location: str
:return: the list of JobMessages. See:
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/ListJobMessagesResponse#JobMessage
:rtype: List[dict]
"""
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
location=location,
)
return jobs_controller.fetch_job_messages_by_id(job_id)
@GoogleBaseHook.fallback_to_default_project_id
def fetch_job_autoscaling_events_by_id(
self,
job_id: str,
project_id: str,
location: str = DEFAULT_DATAFLOW_LOCATION,
) -> List[dict]:
"""
Gets the job autoscaling events with the specified Job ID.
:param job_id: Job ID to get.
:type job_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:
:param location: Job location.
:type location: str
:return: the list of AutoscalingEvents. See:
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/ListJobMessagesResponse#autoscalingevent
:rtype: List[dict]
"""
jobs_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
location=location,
)
return jobs_controller.fetch_job_autoscaling_events_by_id(job_id)
@GoogleBaseHook.fallback_to_default_project_id
def wait_for_done(
self,
job_name: str,
location: str,
project_id: str,
job_id: Optional[str] = None,
multiple_jobs: bool = False,
) -> None:
"""
Wait for Dataflow job.
:param job_name: The 'jobName' to use when executing the DataFlow job
(templated). This ends up being set in the pipeline options, so any entry
with key ``'jobName'`` in ``options`` will be overwritten.
:type job_name: str
:param location: location the job is running
:type location: 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:
:param job_id: a Dataflow job ID
:type job_id: str
:param multiple_jobs: If pipeline creates multiple jobs then monitor all jobs
:type multiple_jobs: boolean
"""
job_controller = _DataflowJobsController(
dataflow=self.get_conn(),
project_number=project_id,
name=job_name,
location=location,
poll_sleep=self.poll_sleep,
job_id=job_id or self.job_id,
num_retries=self.num_retries,
multiple_jobs=multiple_jobs,
drain_pipeline=self.drain_pipeline,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
job_controller.wait_for_done()
class DataflowCreateJavaJobOperator(BaseOperator):
"""
Start a Java Cloud Dataflow batch job. The parameters of the operation
will be passed to the job.
This class is deprecated.
Please use `providers.apache.beam.operators.beam.BeamRunJavaPipelineOperator`.
**Example**: ::
default_args = {
"owner": "airflow",
"depends_on_past": False,
"start_date": (2016, 8, 1),
"email": ["*****@*****.**"],
"email_on_failure": False,
"email_on_retry": False,
"retries": 1,
"retry_delay": timedelta(minutes=30),
"dataflow_default_options": {
"project": "my-gcp-project",
"zone": "us-central1-f",
"stagingLocation": "gs://bucket/tmp/dataflow/staging/",
},
}
dag = DAG("test-dag", default_args=default_args)
task = DataflowCreateJavaJobOperator(
gcp_conn_id="gcp_default",
task_id="normalize-cal",
jar="{{var.value.gcp_dataflow_base}}pipeline-ingress-cal-normalize-1.0.jar",
options={
"autoscalingAlgorithm": "BASIC",
"maxNumWorkers": "50",
"start": "{{ds}}",
"partitionType": "DAY",
},
dag=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:DataflowCreateJavaJobOperator`
:param jar: The reference to a self executing Dataflow jar (templated).
:param job_name: The 'jobName' to use when executing the Dataflow job
(templated). This ends up being set in the pipeline options, so any entry
with key ``'jobName'`` in ``options`` will be overwritten.
:param dataflow_default_options: Map of default job options.
: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.
: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.
:param location: Job location.
:param gcp_conn_id: The connection ID to use connecting to Google Cloud.
: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.
: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.
:param job_class: The name of the dataflow job class to be executed, it
is often not the main class configured in the dataflow jar file.
:param multiple_jobs: If pipeline creates multiple jobs then monitor all jobs
:param check_if_running: before running job, validate that a previous run is not in process
if job is running finish with nothing, WaitForRun= wait until job finished and the run job)
``jar``, ``options``, and ``job_name`` are templated so you can use variables in them.
:param cancel_timeout: How long (in seconds) operator should wait for the pipeline to be
successfully cancelled when task is being killed.
: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.
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.
It's a good practice to define dataflow_* parameters in the default_args of the dag
like the project, zone and staging location.
.. code-block:: python
default_args = {
"dataflow_default_options": {
"zone": "europe-west1-d",
"stagingLocation": "gs://my-staging-bucket/staging/",
}
}
You need to pass the path to your dataflow as a file reference with the ``jar``
parameter, the jar needs to be a self executing jar (see documentation here:
https://beam.apache.org/documentation/runners/dataflow/#self-executing-jar).
Use ``options`` to pass on options to your job.
.. code-block:: python
t1 = DataflowCreateJavaJobOperator(
task_id="dataflow_example",
jar="{{var.value.gcp_dataflow_base}}pipeline/build/libs/pipeline-example-1.0.jar",
options={
"autoscalingAlgorithm": "BASIC",
"maxNumWorkers": "50",
"start": "{{ds}}",
"partitionType": "DAY",
"labels": {"foo": "bar"},
},
gcp_conn_id="airflow-conn-id",
dag=my - dag,
)
"""
template_fields: Sequence[str] = ("options", "jar", "job_name")
ui_color = "#0273d4"
def __init__(
self,
*,
jar: str,
job_name: str = "{{task.task_id}}",
dataflow_default_options: Optional[dict] = None,
options: Optional[dict] = None,
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,
job_class: Optional[str] = None,
check_if_running: CheckJobRunning = CheckJobRunning.WaitForRun,
multiple_jobs: bool = False,
cancel_timeout: Optional[int] = 10 * 60,
wait_until_finished: Optional[bool] = None,
**kwargs,
) -> None:
# TODO: Remove one day
warnings.warn(
f"The `{self.__class__.__name__}` operator is deprecated, "
f"please use `providers.apache.beam.operators.beam.BeamRunJavaPipelineOperator` instead.",
DeprecationWarning,
stacklevel=2,
)
super().__init__(**kwargs)
dataflow_default_options = dataflow_default_options or {}
options = options or {}
options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
self.project_id = project_id
self.location = location
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.jar = jar
self.multiple_jobs = multiple_jobs
self.job_name = job_name
self.dataflow_default_options = dataflow_default_options
self.options = options
self.poll_sleep = poll_sleep
self.job_class = job_class
self.check_if_running = check_if_running
self.cancel_timeout = cancel_timeout
self.wait_until_finished = wait_until_finished
self.job_id = None
self.beam_hook: Optional[BeamHook] = None
self.dataflow_hook: Optional[DataflowHook] = None
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
self.beam_hook = BeamHook(runner=BeamRunnerType.DataflowRunner)
self.dataflow_hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
job_name = self.dataflow_hook.build_dataflow_job_name(
job_name=self.job_name)
pipeline_options = copy.deepcopy(self.dataflow_default_options)
pipeline_options["jobName"] = self.job_name
pipeline_options[
"project"] = self.project_id or self.dataflow_hook.project_id
pipeline_options["region"] = self.location
pipeline_options.update(self.options)
pipeline_options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
pipeline_options.update(self.options)
def set_current_job_id(job_id):
self.job_id = job_id
process_line_callback = process_line_and_extract_dataflow_job_id_callback(
on_new_job_id_callback=set_current_job_id)
with ExitStack() as exit_stack:
if self.jar.lower().startswith("gs://"):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
tmp_gcs_file = exit_stack.enter_context(
gcs_hook.provide_file(object_url=self.jar))
self.jar = tmp_gcs_file.name
is_running = False
if self.check_if_running != CheckJobRunning.IgnoreJob:
is_running = self.dataflow_hook.is_job_dataflow_running(
name=self.job_name,
variables=pipeline_options,
)
while is_running and self.check_if_running == CheckJobRunning.WaitForRun:
is_running = self.dataflow_hook.is_job_dataflow_running(
name=self.job_name,
variables=pipeline_options,
)
if not is_running:
pipeline_options["jobName"] = job_name
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_java_pipeline(
variables=pipeline_options,
jar=self.jar,
job_class=self.job_class,
process_line_callback=process_line_callback,
)
self.dataflow_hook.wait_for_done(
job_name=job_name,
location=self.location,
job_id=self.job_id,
multiple_jobs=self.multiple_jobs,
)
return {"job_id": self.job_id}
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job_id:
self.dataflow_hook.cancel_job(job_id=self.job_id,
project_id=self.project_id
or self.dataflow_hook.project_id)
class BeamRunJavaPipelineOperator(BaseOperator, BeamDataflowMixin):
"""
Launching Apache Beam pipelines written in Java.
Note that both
``default_pipeline_options`` and ``pipeline_options`` will be merged to specify pipeline
execution parameter, and ``default_pipeline_options`` is expected to save
high-level pipeline_options, for instances, project and zone information, which
apply to all Apache Beam operators in the DAG.
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:BeamRunJavaPipelineOperator`
.. seealso::
For more detail on Apache Beam have a look at the reference:
https://beam.apache.org/documentation/
You need to pass the path to your jar file as a file reference with the ``jar``
parameter, the jar needs to be a self executing jar (see documentation here:
https://beam.apache.org/documentation/runners/dataflow/#self-executing-jar).
Use ``pipeline_options`` to pass on pipeline_options to your job.
:param jar: The reference to a self executing Apache Beam jar (templated).
:type jar: str
:param runner: Runner on which pipeline will be run. By default "DirectRunner" is being used.
See:
https://beam.apache.org/documentation/runners/capability-matrix/
:type runner: str
:param job_class: The name of the Apache Beam pipeline class to be executed, it
is often not the main class configured in the pipeline jar file.
:type job_class: str
:param default_pipeline_options: Map of default job pipeline_options.
:type default_pipeline_options: dict
:param pipeline_options: Map of job specific pipeline_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 pipeline_options will be added for each key.
If the value is ``['A', 'B']`` and the key is ``key`` then the ``--key=A --key-B`` pipeline_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 pipeline_options: dict
:param gcp_conn_id: The connection ID to use connecting to Google Cloud Storage if jar is on GCS
:type gcp_conn_id: 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 dataflow_config: Dataflow configuration, used when runner type is set to DataflowRunner
:type dataflow_config: Union[dict, providers.google.cloud.operators.dataflow.DataflowConfiguration]
"""
template_fields: Sequence[str] = (
"jar",
"runner",
"job_class",
"pipeline_options",
"default_pipeline_options",
"dataflow_config",
)
template_fields_renderers = {
'dataflow_config': 'json',
'pipeline_options': 'json'
}
ui_color = "#0273d4"
def __init__(
self,
*,
jar: str,
runner: str = "DirectRunner",
job_class: Optional[str] = None,
default_pipeline_options: Optional[dict] = None,
pipeline_options: Optional[dict] = None,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
dataflow_config: Optional[Union[DataflowConfiguration, dict]] = None,
**kwargs,
) -> None:
super().__init__(**kwargs)
self.jar = jar
self.runner = runner
self.default_pipeline_options = default_pipeline_options or {}
self.pipeline_options = pipeline_options or {}
self.job_class = job_class
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.dataflow_job_id = None
self.dataflow_hook: Optional[DataflowHook] = None
self.beam_hook: Optional[BeamHook] = None
self._dataflow_job_name: Optional[str] = None
if dataflow_config is None:
self.dataflow_config = DataflowConfiguration()
elif isinstance(dataflow_config, dict):
self.dataflow_config = DataflowConfiguration(**dataflow_config)
else:
self.dataflow_config = dataflow_config
if self.dataflow_config and self.runner.lower(
) != BeamRunnerType.DataflowRunner.lower():
self.log.warning(
"dataflow_config is defined but runner is different than DataflowRunner (%s)",
self.runner)
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
self.beam_hook = BeamHook(runner=self.runner)
pipeline_options = self.default_pipeline_options.copy()
process_line_callback: Optional[Callable] = None
is_dataflow = self.runner.lower(
) == BeamRunnerType.DataflowRunner.lower()
dataflow_job_name: Optional[str] = None
if is_dataflow:
dataflow_job_name, pipeline_options, process_line_callback = self._set_dataflow(
pipeline_options=pipeline_options, job_name_variable_key=None)
pipeline_options.update(self.pipeline_options)
with ExitStack() as exit_stack:
if self.jar.lower().startswith("gs://"):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
tmp_gcs_file = exit_stack.enter_context(
gcs_hook.provide_file(object_url=self.jar))
self.jar = tmp_gcs_file.name
if is_dataflow and self.dataflow_hook:
is_running = False
if self.dataflow_config.check_if_running != CheckJobRunning.IgnoreJob:
is_running = (
# The reason for disable=no-value-for-parameter is that project_id parameter is
# required but here is not passed, moreover it cannot be passed here.
# This method is wrapped by @_fallback_to_project_id_from_variables decorator which
# fallback project_id value from variables and raise error if project_id is
# defined both in variables and as parameter (here is already defined in variables)
self.dataflow_hook.is_job_dataflow_running(
name=self.dataflow_config.job_name,
variables=pipeline_options,
))
while is_running and self.dataflow_config.check_if_running == CheckJobRunning.WaitForRun:
# The reason for disable=no-value-for-parameter is that project_id parameter is
# required but here is not passed, moreover it cannot be passed here.
# This method is wrapped by @_fallback_to_project_id_from_variables decorator which
# fallback project_id value from variables and raise error if project_id is
# defined both in variables and as parameter (here is already defined in variables)
is_running = self.dataflow_hook.is_job_dataflow_running(
name=self.dataflow_config.job_name,
variables=pipeline_options,
)
if not is_running:
pipeline_options["jobName"] = dataflow_job_name
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_java_pipeline(
variables=pipeline_options,
jar=self.jar,
job_class=self.job_class,
process_line_callback=process_line_callback,
)
if dataflow_job_name and self.dataflow_config.location:
multiple_jobs = (self.dataflow_config.multiple_jobs
if self.dataflow_config.multiple_jobs
else False)
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=multiple_jobs,
project_id=self.dataflow_config.project_id,
)
else:
self.beam_hook.start_java_pipeline(
variables=pipeline_options,
jar=self.jar,
job_class=self.job_class,
process_line_callback=process_line_callback,
)
return {"dataflow_job_id": self.dataflow_job_id}
def on_kill(self) -> None:
if self.dataflow_hook and self.dataflow_job_id:
self.log.info(
'Dataflow job with id: `%s` was requested to be cancelled.',
self.dataflow_job_id)
self.dataflow_hook.cancel_job(
job_id=self.dataflow_job_id,
project_id=self.dataflow_config.project_id,
)