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 DataflowCreateJavaJobOperator(BaseOperator):
"""
Start a Java Cloud DataFlow batch job. The parameters of the operation
will be passed to the job.
**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 = DataFlowJavaOperator(
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
:param jar: The reference to a self executing DataFlow jar (templated).
:type jar: str
: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 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 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 gcp_conn_id: The connection ID to use connecting to Google Cloud.
: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 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 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.
:type job_class: str
:param multiple_jobs: If pipeline creates multiple jobs then monitor all jobs
:type multiple_jobs: boolean
:param check_if_running: before running job, validate that a previous run is not in process
:type check_if_running: CheckJobRunning(IgnoreJob = do not check if running, FinishIfRunning=
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.
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 = DataFlowJavaOperator(
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 = ['options', 'jar', 'job_name']
ui_color = '#0273d4'
# pylint: disable=too-many-arguments
@apply_defaults
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: Optional[bool] = None,
**kwargs,
) -> None:
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.job_id = None
self.hook = None
def execute(self, context):
self.hook = DataflowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
dataflow_options = copy.copy(self.dataflow_default_options)
dataflow_options.update(self.options)
is_running = False
if self.check_if_running != CheckJobRunning.IgnoreJob:
is_running = self.hook.is_job_dataflow_running(
name=self.job_name,
variables=dataflow_options,
project_id=self.project_id,
location=self.location,
)
while is_running and self.check_if_running == CheckJobRunning.WaitForRun:
is_running = self.hook.is_job_dataflow_running(
name=self.job_name,
variables=dataflow_options,
project_id=self.project_id,
location=self.location,
)
if not is_running:
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( # pylint: disable=no-member
gcs_hook.provide_file(object_url=self.jar))
self.jar = tmp_gcs_file.name
def set_current_job_id(job_id):
self.job_id = job_id
self.hook.start_java_dataflow(
job_name=self.job_name,
variables=dataflow_options,
jar=self.jar,
job_class=self.job_class,
append_job_name=True,
multiple_jobs=self.multiple_jobs,
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.
This class is deprecated.
Please use `providers.apache.beam.operators.beam.BeamRunPythonPipelineOperator`.
.. 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)
: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.
:param py_options: Additional python options, e.g., ["-m", "-v"].
: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 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.
: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.
: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 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 drain_pipeline: Optional, set to True if want to stop streaming job by draining it
instead of canceling during killing task instance. See:
https://cloud.google.com/dataflow/docs/guides/stopping-a-pipeline
: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.
"""
template_fields: Sequence[str] = ("options", "dataflow_default_options",
"job_name", "py_file")
def __init__(
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:
# TODO: Remove one day
warnings.warn(
f"The `{self.__class__.__name__}` operator is deprecated, "
"please use `providers.apache.beam.operators.beam.BeamRunPythonPipelineOperator` instead.",
DeprecationWarning,
stacklevel=2,
)
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.beam_hook: Optional[BeamHook] = None
self.dataflow_hook: Optional[DataflowHook] = None
def execute(self, context: 'Context'):
"""Execute the python dataflow job."""
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,
impersonation_chain=None,
drain_pipeline=self.drain_pipeline,
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 = self.dataflow_default_options.copy()
pipeline_options["job_name"] = job_name
pipeline_options[
"project"] = self.project_id or self.dataflow_hook.project_id
pipeline_options["region"] = self.location
pipeline_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_pipeline_options = {
camel_to_snake(key): pipeline_options[key]
for key in pipeline_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.py_file.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.py_file))
self.py_file = tmp_gcs_file.name
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_python_pipeline(
variables=formatted_pipeline_options,
py_file=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,
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=False,
)
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 DataflowTemplatedJobStartOperator(BaseOperator):
"""
Start a Templated Cloud DataFlow batch job. The parameters of the operation
will be passed to the job.
:param template: The reference to the DataFlow template.
:type template: str
:param job_name: The 'jobName' to use when executing the DataFlow template
(templated).
:param options: 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 options: dict
:param dataflow_default_options: Map of default job environment options.
:type dataflow_default_options: dict
:param parameters: Map of job specific parameters for the template.
:type parameters: 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.
:type project_id: str
:param location: Job location.
:type location: str
:param gcp_conn_id: The connection ID to use connecting to Google Cloud.
: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 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 impersonation_chain: Optional service account to impersonate using short-term
credentials, or chained list of accounts required to get the access_token
of the last account in the list, which will be impersonated in the request.
If set as a string, the account must grant the originating account
the Service Account Token Creator IAM role.
If set as a sequence, the identities from the list must grant
Service Account Token Creator IAM role to the directly preceding identity, with first
account from the list granting this role to the originating account (templated).
:type impersonation_chain: Union[str, Sequence[str]]
It's a good practice to define dataflow_* parameters in the default_args of the dag
like the project, zone and staging location.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
.. code-block:: python
default_args = {
'dataflow_default_options': {
'zone': 'europe-west1-d',
'tempLocation': 'gs://my-staging-bucket/staging/',
}
}
}
You need to pass the path to your dataflow template as a file reference with the
``template`` parameter. Use ``parameters`` to pass on parameters to your job.
Use ``environment`` to pass on runtime environment variables to your job.
.. code-block:: python
t1 = DataflowTemplateOperator(
task_id='dataflow_example',
template='{{var.value.gcp_dataflow_base}}',
parameters={
'inputFile': "gs://bucket/input/my_input.txt",
'outputFile': "gs://bucket/output/my_output.txt"
},
gcp_conn_id='airflow-conn-id',
dag=my-dag)
``template``, ``dataflow_default_options``, ``parameters``, and ``job_name`` are
templated so you can use variables in them.
Note that ``dataflow_default_options`` is expected to save high-level options
for project information, which apply to all dataflow operators in the DAG.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3
/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
For more detail on job template execution have a look at the reference:
https://cloud.google.com/dataflow/docs/templates/executing-templates
"""
template_fields = [
'template',
'job_name',
'options',
'parameters',
'project_id',
'location',
'gcp_conn_id',
'impersonation_chain',
]
ui_color = '#0273d4'
@apply_defaults
def __init__( # pylint: disable=too-many-arguments
self,
*,
template: str,
job_name: str = '{{task.task_id}}',
options: Optional[Dict[str, Any]] = None,
dataflow_default_options: Optional[Dict[str, Any]] = None,
parameters: Optional[Dict[str, str]] = 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,
impersonation_chain: Optional[Union[str, Sequence[str]]] = None,
**kwargs,
) -> None:
super().__init__(**kwargs)
self.template = template
self.job_name = job_name
self.options = options or {}
self.dataflow_default_options = dataflow_default_options or {}
self.parameters = parameters or {}
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: Optional[DataflowHook] = None
self.impersonation_chain = impersonation_chain
def execute(self, context):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep,
impersonation_chain=self.impersonation_chain,
)
def set_current_job_id(job_id):
self.job_id = job_id
options = self.dataflow_default_options
options.update(self.options)
job = self.hook.start_template_dataflow(
job_name=self.job_name,
variables=options,
parameters=self.parameters,
dataflow_template=self.template,
on_new_job_id_callback=set_current_job_id,
project_id=self.project_id,
location=self.location,
)
return job
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 DataflowStartFlexTemplateOperator(BaseOperator):
"""
Starts flex templates with the Dataflow pipeline.
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:DataflowStartFlexTemplateOperator`
: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)
: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.
:param gcp_conn_id: The connection ID to use connecting to Google Cloud
Platform.
:param delegate_to: The account to impersonate, if any.
For this to work, the service account making the request must have
domain-wide delegation enabled.
:param drain_pipeline: Optional, set to True if want to stop streaming job by draining it
instead of canceling during killing task instance. See:
https://cloud.google.com/dataflow/docs/guides/stopping-a-pipeline
: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.
"""
template_fields: Sequence[str] = ("body", "location", "project_id",
"gcp_conn_id")
operator_extra_links = (DataflowJobLink(), )
def __init__(
self,
body: Dict,
location: str,
project_id: Optional[str] = None,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
drain_pipeline: bool = False,
cancel_timeout: Optional[int] = 10 * 60,
wait_until_finished: Optional[bool] = None,
*args,
**kwargs,
) -> None:
super().__init__(*args, **kwargs)
self.body = body
self.location = location
self.project_id = project_id
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.drain_pipeline = drain_pipeline
self.cancel_timeout = cancel_timeout
self.wait_until_finished = wait_until_finished
self.job = None
self.hook: Optional[DataflowHook] = None
def execute(self, context: 'Context'):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
drain_pipeline=self.drain_pipeline,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
def set_current_job(current_job):
self.job = current_job
DataflowJobLink.persist(self, context, self.project_id,
self.location, self.job.get("id"))
job = self.hook.start_flex_template(
body=self.body,
location=self.location,
project_id=self.project_id,
on_new_job_callback=set_current_job,
)
return job
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job:
self.hook.cancel_job(
job_id=self.job.get("id"),
project_id=self.job.get("projectId"),
location=self.job.get("location"),
)
class DataflowStartSqlJobOperator(BaseOperator):
"""
Starts Dataflow SQL query.
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:DataflowStartSqlJobOperator`
.. warning::
This operator requires ``gcloud`` command (Google Cloud SDK) must be installed on the Airflow worker
<https://cloud.google.com/sdk/docs/install>`__
:param job_name: The unique name to assign to the Cloud Dataflow job.
:param query: The SQL query to execute.
:param options: Job parameters to be executed. It can be a dictionary with the following keys.
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)
: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.
:param gcp_conn_id: The connection ID to use connecting to Google Cloud
Platform.
:param delegate_to: The account to impersonate, if any.
For this to work, the service account making the request must have
domain-wide delegation enabled.
:param drain_pipeline: Optional, set to True if want to stop streaming job by draining it
instead of canceling during killing task instance. See:
https://cloud.google.com/dataflow/docs/guides/stopping-a-pipeline
"""
template_fields: Sequence[str] = (
"job_name",
"query",
"options",
"location",
"project_id",
"gcp_conn_id",
)
template_fields_renderers = {"query": "sql"}
def __init__(
self,
job_name: str,
query: str,
options: Dict[str, Any],
location: str = DEFAULT_DATAFLOW_LOCATION,
project_id: Optional[str] = None,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
drain_pipeline: bool = False,
*args,
**kwargs,
) -> None:
super().__init__(*args, **kwargs)
self.job_name = job_name
self.query = query
self.options = options
self.location = location
self.project_id = project_id
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.drain_pipeline = drain_pipeline
self.job = None
self.hook: Optional[DataflowHook] = None
def execute(self, context: 'Context'):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
drain_pipeline=self.drain_pipeline,
)
def set_current_job(current_job):
self.job = current_job
job = self.hook.start_sql_job(
job_name=self.job_name,
query=self.query,
options=self.options,
location=self.location,
project_id=self.project_id,
on_new_job_callback=set_current_job,
)
return job
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job:
self.hook.cancel_job(
job_id=self.job.get("id"),
project_id=self.job.get("projectId"),
location=self.job.get("location"),
)
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 DataflowTemplatedJobStartOperator(BaseOperator):
"""
Start a Templated Cloud Dataflow job. The parameters of the operation
will be passed to the job.
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:DataflowTemplatedJobStartOperator`
:param template: The reference to the Dataflow template.
:param job_name: The 'jobName' to use when executing the Dataflow template
(templated).
:param options: 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>`__
:param dataflow_default_options: Map of default job environment options.
:param parameters: Map of job specific parameters for the template.
: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 impersonation_chain: Optional service account to impersonate using short-term
credentials, or chained list of accounts required to get the access_token
of the last account in the list, which will be impersonated in the request.
If set as a string, the account must grant the originating account
the Service Account Token Creator IAM role.
If set as a sequence, the identities from the list must grant
Service Account Token Creator IAM role to the directly preceding identity, with first
account from the list granting this role to the originating account (templated).
:param 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>`__
: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.
It's a good practice to define dataflow_* parameters in the default_args of the dag
like the project, zone and staging location.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
.. code-block:: python
default_args = {
"dataflow_default_options": {
"zone": "europe-west1-d",
"tempLocation": "gs://my-staging-bucket/staging/",
}
}
You need to pass the path to your dataflow template as a file reference with the
``template`` parameter. Use ``parameters`` to pass on parameters to your job.
Use ``environment`` to pass on runtime environment variables to your job.
.. code-block:: python
t1 = DataflowTemplatedJobStartOperator(
task_id="dataflow_example",
template="{{var.value.gcp_dataflow_base}}",
parameters={
"inputFile": "gs://bucket/input/my_input.txt",
"outputFile": "gs://bucket/output/my_output.txt",
},
gcp_conn_id="airflow-conn-id",
dag=my - dag,
)
``template``, ``dataflow_default_options``, ``parameters``, and ``job_name`` are
templated so you can use variables in them.
Note that ``dataflow_default_options`` is expected to save high-level options
for project information, which apply to all dataflow operators in the DAG.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3
/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
For more detail on job template execution have a look at the reference:
https://cloud.google.com/dataflow/docs/templates/executing-templates
"""
template_fields: Sequence[str] = (
"template",
"job_name",
"options",
"parameters",
"project_id",
"location",
"gcp_conn_id",
"impersonation_chain",
"environment",
"dataflow_default_options",
)
ui_color = "#0273d4"
operator_extra_links = (DataflowJobLink(), )
def __init__(
self,
*,
template: str,
job_name: str = "{{task.task_id}}",
options: Optional[Dict[str, Any]] = None,
dataflow_default_options: Optional[Dict[str, Any]] = None,
parameters: Optional[Dict[str, str]] = 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,
impersonation_chain: Optional[Union[str, Sequence[str]]] = None,
environment: Optional[Dict] = None,
cancel_timeout: Optional[int] = 10 * 60,
wait_until_finished: Optional[bool] = None,
**kwargs,
) -> None:
super().__init__(**kwargs)
self.template = template
self.job_name = job_name
self.options = options or {}
self.dataflow_default_options = dataflow_default_options or {}
self.parameters = parameters or {}
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 = None
self.hook: Optional[DataflowHook] = None
self.impersonation_chain = impersonation_chain
self.environment = environment
self.cancel_timeout = cancel_timeout
self.wait_until_finished = wait_until_finished
def execute(self, context: 'Context') -> dict:
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep,
impersonation_chain=self.impersonation_chain,
cancel_timeout=self.cancel_timeout,
wait_until_finished=self.wait_until_finished,
)
def set_current_job(current_job):
self.job = current_job
DataflowJobLink.persist(self, context, self.project_id,
self.location, self.job.get("id"))
options = self.dataflow_default_options
options.update(self.options)
job = self.hook.start_template_dataflow(
job_name=self.job_name,
variables=options,
parameters=self.parameters,
dataflow_template=self.template,
on_new_job_callback=set_current_job,
project_id=self.project_id,
location=self.location,
environment=self.environment,
)
return job
def on_kill(self) -> None:
self.log.info("On kill.")
if self.job:
self.hook.cancel_job(
job_id=self.job.get("id"),
project_id=self.job.get("projectId"),
location=self.job.get("location"),
)
class TestDataflowTemplateHook(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(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow(self, mock_conn, mock_controller,
mock_uuid):
launch_method = (mock_conn.return_value.projects.return_value.
locations.return_value.templates.return_value.launch)
launch_method.return_value.execute.return_value = {
"job": {
"id": TEST_JOB_ID
}
}
self.dataflow_hook.start_template_dataflow(
job_name=JOB_NAME,
variables=DATAFLOW_OPTIONS_TEMPLATE,
parameters=PARAMETERS,
dataflow_template=TEMPLATE)
options_with_region = {'region': 'us-central1'}
options_with_region.update(DATAFLOW_OPTIONS_TEMPLATE)
options_with_region_without_project = copy.deepcopy(
options_with_region)
del options_with_region_without_project['project']
launch_method.assert_called_once_with(
body={
'jobName': 'test-dataflow-pipeline-12345678',
'parameters': PARAMETERS,
'environment': {
'zone': 'us-central1-f',
'tempLocation': 'gs://test/temp'
}
},
gcsPath='gs://dataflow-templates/wordcount/template_file',
location='us-central1',
projectId='test')
mock_controller.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id='test-job-id',
location='us-central1',
name='test-dataflow-pipeline-12345678',
num_retries=5,
poll_sleep=10,
project_number='test')
mock_controller.return_value.wait_for_done.assert_called_once()
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow_with_runtime_env(self, mock_conn,
mock_dataflowjob,
mock_uuid):
dataflow_options_template = copy.deepcopy(DATAFLOW_OPTIONS_TEMPLATE)
options_with_runtime_env = copy.deepcopy(RUNTIME_ENV)
options_with_runtime_env.update(dataflow_options_template)
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
method = (mock_conn.return_value.projects.return_value.locations.
return_value.templates.return_value.launch)
method.return_value.execute.return_value = {'job': {'id': TEST_JOB_ID}}
self.dataflow_hook.start_template_dataflow(
job_name=JOB_NAME,
variables=options_with_runtime_env,
parameters=PARAMETERS,
dataflow_template=TEMPLATE)
body = {
"jobName": mock.ANY,
"parameters": PARAMETERS,
"environment": RUNTIME_ENV
}
method.assert_called_once_with(
projectId=options_with_runtime_env['project'],
location='us-central1',
gcsPath=TEMPLATE,
body=body,
)
mock_dataflowjob.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id=TEST_JOB_ID,
location='us-central1',
name='test-dataflow-pipeline-{}'.format(MOCK_UUID),
num_retries=5,
poll_sleep=10,
project_number='test')
mock_uuid.assert_called_once_with()
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_cancel_job(self, mock_get_conn, jobs_controller):
self.dataflow_hook.cancel_job(
job_name=TEST_JOB_NAME,
job_id=TEST_JOB_ID,
project_id=TEST_PROJECT,
)
jobs_controller.assert_called_once_with(
dataflow=mock_get_conn.return_value,
job_id=TEST_JOB_ID,
location='us-central1',
name=TEST_JOB_NAME,
poll_sleep=10,
project_number=TEST_PROJECT)
jobs_controller.cancel()
class DataflowTemplatedJobStartOperator(BaseOperator):
"""
Start a Templated Cloud DataFlow batch job. The parameters of the operation
will be passed to the job.
:param template: The reference to the DataFlow template.
:type template: str
:param job_name: The 'jobName' to use when executing the DataFlow template
(templated).
:param dataflow_default_options: Map of default job environment options.
:type dataflow_default_options: dict
:param parameters: Map of job specific parameters for the template.
:type parameters: dict
:param project_id: Optional, the GCP project ID in which to start a job.
If set to None or missing, the default project_id from the GCP connection is used.
:type project_id: str
:param location: Job location.
:type location: str
:param gcp_conn_id: The connection ID to use connecting to Google Cloud
Platform.
:type gcp_conn_id: str
:param delegate_to: The account to impersonate, 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
It's a good practice to define dataflow_* parameters in the default_args of the dag
like the project, zone and staging location.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
.. code-block:: python
default_args = {
'dataflow_default_options': {
'zone': 'europe-west1-d',
'tempLocation': 'gs://my-staging-bucket/staging/',
}
}
}
You need to pass the path to your dataflow template as a file reference with the
``template`` parameter. Use ``parameters`` to pass on parameters to your job.
Use ``environment`` to pass on runtime environment variables to your job.
.. code-block:: python
t1 = DataflowTemplateOperator(
task_id='dataflow_example',
template='{{var.value.gcp_dataflow_base}}',
parameters={
'inputFile': "gs://bucket/input/my_input.txt",
'outputFile': "gs://bucket/output/my_output.txt"
},
gcp_conn_id='airflow-conn-id',
dag=my-dag)
``template``, ``dataflow_default_options``, ``parameters``, and ``job_name`` are
templated so you can use variables in them.
Note that ``dataflow_default_options`` is expected to save high-level options
for project information, which apply to all dataflow operators in the DAG.
.. seealso::
https://cloud.google.com/dataflow/docs/reference/rest/v1b3
/LaunchTemplateParameters
https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment
For more detail on job template execution have a look at the reference:
https://cloud.google.com/dataflow/docs/templates/executing-templates
"""
template_fields = ['parameters', 'dataflow_default_options', 'template', 'job_name']
ui_color = '#0273d4'
@apply_defaults
def __init__(
self,
template: str,
job_name: str = '{{task.task_id}}',
dataflow_default_options: Optional[dict] = None,
parameters: 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,
*args,
**kwargs) -> None:
super().__init__(*args, **kwargs)
dataflow_default_options = dataflow_default_options or {}
parameters = parameters or {}
self.template = template
self.job_name = job_name
self.dataflow_default_options = dataflow_default_options
self.parameters = parameters
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: Optional[DataflowHook] = None
def execute(self, context):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep
)
def set_current_job_id(job_id):
self.job_id = job_id
job = self.hook.start_template_dataflow(
job_name=self.job_name,
variables=self.dataflow_default_options,
parameters=self.parameters,
dataflow_template=self.template,
on_new_job_id_callback=set_current_job_id,
project_id=self.project_id,
location=self.location
)
return job
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 BeamRunPythonPipelineOperator(BaseOperator):
"""
Launching Apache Beam pipelines written in Python. 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 options, for instances, project and zone information, which
apply to all beam operators in the DAG.
.. seealso::
For more information on how to use this operator, take a look at the guide:
:ref:`howto/operator:BeamRunPythonPipelineOperator`
.. seealso::
For more detail on Apache Beam have a look at the reference:
https://beam.apache.org/documentation/
:param py_file: Reference to the python Apache Beam pipeline file.py, e.g.,
/some/local/file/path/to/your/python/pipeline/file. (templated)
:type py_file: str
:param runner: Runner on which pipeline will be run. By default "DirectRunner" is being used.
Other possible options: DataflowRunner, SparkRunner, FlinkRunner.
See: :class:`~providers.apache.beam.hooks.beam.BeamRunnerType`
See: https://beam.apache.org/documentation/runners/capability-matrix/
If you use Dataflow runner check dedicated operator:
:class:`~providers.google.cloud.operators.dataflow.DataflowCreatePythonJobOperator`
:type runner: str
:param py_options: Additional python options, e.g., ["-m", "-v"].
:type py_options: list[str]
:param default_pipeline_options: Map of default pipeline options.
:type default_pipeline_options: dict
:param pipeline_options: Map of 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 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 pipeline_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: Optional.
The connection ID to use connecting to Google Cloud Storage if python file is on GCS.
:type gcp_conn_id: str
:param delegate_to: Optional.
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 = [
"py_file", "runner", "pipeline_options", "default_pipeline_options",
"dataflow_config"
]
template_fields_renderers = {
'dataflow_config': 'json',
'pipeline_options': 'json'
}
@apply_defaults
def __init__(
self,
*,
py_file: str,
runner: str = "DirectRunner",
default_pipeline_options: Optional[dict] = None,
pipeline_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,
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.py_file = py_file
self.runner = runner
self.py_options = py_options or []
self.default_pipeline_options = default_pipeline_options or {}
self.pipeline_options = pipeline_options or {}
self.pipeline_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.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.dataflow_config = dataflow_config or {}
self.beam_hook: Optional[BeamHook] = None
self.dataflow_hook: Optional[DataflowHook] = None
self.dataflow_job_id: Optional[str] = None
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):
"""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()
if isinstance(self.dataflow_config, dict):
self.dataflow_config = DataflowConfiguration(
**self.dataflow_config)
if is_dataflow:
self.dataflow_hook = DataflowHook(
gcp_conn_id=self.dataflow_config.gcp_conn_id
or self.gcp_conn_id,
delegate_to=self.dataflow_config.delegate_to
or self.delegate_to,
poll_sleep=self.dataflow_config.poll_sleep,
impersonation_chain=self.dataflow_config.impersonation_chain,
drain_pipeline=self.dataflow_config.drain_pipeline,
cancel_timeout=self.dataflow_config.cancel_timeout,
wait_until_finished=self.dataflow_config.wait_until_finished,
)
self.dataflow_config.project_id = self.dataflow_config.project_id or self.dataflow_hook.project_id
dataflow_job_name = DataflowHook.build_dataflow_job_name(
self.dataflow_config.job_name,
self.dataflow_config.append_job_name)
pipeline_options["job_name"] = dataflow_job_name
pipeline_options["project"] = self.dataflow_config.project_id
pipeline_options["region"] = self.dataflow_config.location
pipeline_options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
def set_current_dataflow_job_id(job_id):
self.dataflow_job_id = job_id
process_line_callback = process_line_and_extract_dataflow_job_id_callback(
on_new_job_id_callback=set_current_dataflow_job_id)
pipeline_options.update(self.pipeline_options)
# Convert argument names from lowerCamelCase to snake case.
formatted_pipeline_options = {
convert_camel_to_snake(key): pipeline_options[key]
for key in pipeline_options
}
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.beam_hook.start_python_pipeline(
variables=formatted_pipeline_options,
py_file=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,
process_line_callback=process_line_callback,
)
if is_dataflow:
self.dataflow_hook.wait_for_done( # pylint: disable=no-value-for-parameter
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=False,
)
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,
)
class BeamRunJavaPipelineOperator(BaseOperator):
"""
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/
If you use Dataflow runner check dedicated operator:
:class:`~providers.google.cloud.operators.dataflow.DataflowCreateJavaJobOperator`
: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 = [
"jar",
"runner",
"job_class",
"pipeline_options",
"default_pipeline_options",
"dataflow_config",
]
template_fields_renderers = {
'dataflow_config': 'json',
'pipeline_options': 'json'
}
ui_color = "#0273d4"
@apply_defaults
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.dataflow_config = dataflow_config or {}
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 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):
"""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()
if isinstance(self.dataflow_config, dict):
self.dataflow_config = DataflowConfiguration(
**self.dataflow_config)
if is_dataflow:
self.dataflow_hook = DataflowHook(
gcp_conn_id=self.dataflow_config.gcp_conn_id
or self.gcp_conn_id,
delegate_to=self.dataflow_config.delegate_to
or self.delegate_to,
poll_sleep=self.dataflow_config.poll_sleep,
impersonation_chain=self.dataflow_config.impersonation_chain,
drain_pipeline=self.dataflow_config.drain_pipeline,
cancel_timeout=self.dataflow_config.cancel_timeout,
wait_until_finished=self.dataflow_config.wait_until_finished,
)
self.dataflow_config.project_id = self.dataflow_config.project_id or self.dataflow_hook.project_id
self._dataflow_job_name = DataflowHook.build_dataflow_job_name(
self.dataflow_config.job_name,
self.dataflow_config.append_job_name)
pipeline_options["jobName"] = self.dataflow_config.job_name
pipeline_options["project"] = self.dataflow_config.project_id
pipeline_options["region"] = self.dataflow_config.location
pipeline_options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
def set_current_dataflow_job_id(job_id):
self.dataflow_job_id = job_id
process_line_callback = process_line_and_extract_dataflow_job_id_callback(
on_new_job_id_callback=set_current_dataflow_job_id)
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( # pylint: disable=no-member
gcs_hook.provide_file(object_url=self.jar))
self.jar = tmp_gcs_file.name
if is_dataflow:
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( # pylint: disable=no-value-for-parameter
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)
# pylint: disable=no-value-for-parameter
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"] = self._dataflow_job_name
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=self._dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=self.dataflow_config.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,
)
class DataflowStartFlexTemplateOperator(BaseOperator):
"""
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 gcp_conn_id: The connection ID to use connecting to Google Cloud
Platform.
:type gcp_conn_id: str
:param delegate_to: The account to impersonate, if any.
For this to work, the service account making the request must have
domain-wide delegation enabled.
:type delegate_to: str
"""
template_fields = ["body", 'location', 'project_id', 'gcp_conn_id']
@apply_defaults
def __init__(
self,
body: Dict,
location: str,
project_id: Optional[str] = None,
gcp_conn_id: str = 'google_cloud_default',
delegate_to: Optional[str] = None,
*args,
**kwargs,
) -> None:
super().__init__(*args, **kwargs)
self.body = body
self.location = location
self.project_id = project_id
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.job_id = None
self.hook: Optional[DataflowHook] = None
def execute(self, context):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
)
def set_current_job_id(job_id):
self.job_id = job_id
job = self.hook.start_flex_template(
body=self.body,
location=self.location,
project_id=self.project_id,
on_new_job_id_callback=set_current_job_id,
)
return job
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 TestDataflowTemplateHook(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(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow(self, mock_conn, mock_controller,
mock_uuid):
launch_method = (mock_conn.return_value.projects.return_value.
locations.return_value.templates.return_value.launch)
launch_method.return_value.execute.return_value = {
"job": {
"id": TEST_JOB_ID
}
}
variables = {'zone': 'us-central1-f', 'tempLocation': 'gs://test/temp'}
self.dataflow_hook.start_template_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=copy.deepcopy(variables),
parameters=PARAMETERS,
dataflow_template=TEST_TEMPLATE,
project_id=TEST_PROJECT,
)
launch_method.assert_called_once_with(
body={
'jobName': 'test-dataflow-pipeline-12345678',
'parameters': PARAMETERS,
'environment': variables,
},
gcsPath='gs://dataflow-templates/wordcount/template_file',
projectId=TEST_PROJECT,
location=DEFAULT_DATAFLOW_LOCATION,
)
mock_controller.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id='test-job-id',
name='test-dataflow-pipeline-12345678',
num_retries=5,
poll_sleep=10,
project_number=TEST_PROJECT,
location=DEFAULT_DATAFLOW_LOCATION,
)
mock_controller.return_value.wait_for_done.assert_called_once()
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow_with_custom_region_as_variable(
self, mock_conn, mock_controller, mock_uuid):
launch_method = (mock_conn.return_value.projects.return_value.
locations.return_value.templates.return_value.launch)
launch_method.return_value.execute.return_value = {
"job": {
"id": TEST_JOB_ID
}
}
self.dataflow_hook.start_template_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables={'region': TEST_LOCATION},
parameters=PARAMETERS,
dataflow_template=TEST_TEMPLATE,
project_id=TEST_PROJECT,
)
launch_method.assert_called_once_with(
projectId=TEST_PROJECT,
location=TEST_LOCATION,
gcsPath=TEST_TEMPLATE,
body=mock.ANY,
)
mock_controller.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id=TEST_JOB_ID,
name=UNIQUE_JOB_NAME,
num_retries=5,
poll_sleep=10,
project_number=TEST_PROJECT,
location=TEST_LOCATION,
)
mock_controller.return_value.wait_for_done.assert_called_once()
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow_with_custom_region_as_parameter(
self, mock_conn, mock_controller, mock_uuid):
launch_method = (mock_conn.return_value.projects.return_value.
locations.return_value.templates.return_value.launch)
launch_method.return_value.execute.return_value = {
"job": {
"id": TEST_JOB_ID
}
}
self.dataflow_hook.start_template_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables={},
parameters=PARAMETERS,
dataflow_template=TEST_TEMPLATE,
location=TEST_LOCATION,
project_id=TEST_PROJECT,
)
launch_method.assert_called_once_with(
body={
'jobName': UNIQUE_JOB_NAME,
'parameters': PARAMETERS,
'environment': {}
},
gcsPath='gs://dataflow-templates/wordcount/template_file',
projectId=TEST_PROJECT,
location=TEST_LOCATION,
)
mock_controller.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id=TEST_JOB_ID,
name=UNIQUE_JOB_NAME,
num_retries=5,
poll_sleep=10,
project_number=TEST_PROJECT,
location=TEST_LOCATION,
)
mock_controller.return_value.wait_for_done.assert_called_once()
@mock.patch(DATAFLOW_STRING.format('uuid.uuid4'), return_value=MOCK_UUID)
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_start_template_dataflow_with_runtime_env(self, mock_conn,
mock_dataflowjob,
mock_uuid):
options_with_runtime_env = copy.deepcopy(RUNTIME_ENV)
dataflowjob_instance = mock_dataflowjob.return_value
dataflowjob_instance.wait_for_done.return_value = None
# fmt: off
method = (mock_conn.return_value.projects.return_value.locations.
return_value.templates.return_value.launch)
# fmt: on
method.return_value.execute.return_value = {'job': {'id': TEST_JOB_ID}}
self.dataflow_hook.start_template_dataflow( # pylint: disable=no-value-for-parameter
job_name=JOB_NAME,
variables=options_with_runtime_env,
parameters=PARAMETERS,
dataflow_template=TEST_TEMPLATE,
project_id=TEST_PROJECT,
)
body = {
"jobName": mock.ANY,
"parameters": PARAMETERS,
"environment": RUNTIME_ENV
}
method.assert_called_once_with(
projectId=TEST_PROJECT,
location=DEFAULT_DATAFLOW_LOCATION,
gcsPath=TEST_TEMPLATE,
body=body,
)
mock_dataflowjob.assert_called_once_with(
dataflow=mock_conn.return_value,
job_id=TEST_JOB_ID,
location=DEFAULT_DATAFLOW_LOCATION,
name='test-dataflow-pipeline-{}'.format(MOCK_UUID),
num_retries=5,
poll_sleep=10,
project_number=TEST_PROJECT,
)
mock_uuid.assert_called_once_with()
@mock.patch(DATAFLOW_STRING.format('_DataflowJobsController'))
@mock.patch(DATAFLOW_STRING.format('DataflowHook.get_conn'))
def test_cancel_job(self, mock_get_conn, jobs_controller):
self.dataflow_hook.cancel_job(job_name=UNIQUE_JOB_NAME,
job_id=TEST_JOB_ID,
project_id=TEST_PROJECT,
location=TEST_LOCATION)
jobs_controller.assert_called_once_with(
dataflow=mock_get_conn.return_value,
job_id=TEST_JOB_ID,
location=TEST_LOCATION,
name=UNIQUE_JOB_NAME,
poll_sleep=10,
project_number=TEST_PROJECT,
)
jobs_controller.cancel()
class DataflowStartFlexTemplateOperator(BaseOperator):
"""
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 gcp_conn_id: The connection ID to use connecting to Google Cloud
Platform.
:type gcp_conn_id: str
:param delegate_to: The account to impersonate, if any.
For this to work, the service account making the request must have
domain-wide delegation enabled.
:type delegate_to: str
: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]
"""
template_fields = ["body", "location", "project_id", "gcp_conn_id"]
@apply_defaults
def __init__(
self,
body: Dict,
location: str,
project_id: Optional[str] = None,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
drain_pipeline: bool = False,
cancel_timeout: Optional[int] = 10 * 60,
*args,
**kwargs,
) -> None:
super().__init__(*args, **kwargs)
self.body = body
self.location = location
self.project_id = project_id
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.drain_pipeline = drain_pipeline
self.cancel_timeout = cancel_timeout
self.job_id = None
self.hook: Optional[DataflowHook] = None
def execute(self, context):
self.hook = DataflowHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
drain_pipeline=self.drain_pipeline,
cancel_timeout=self.cancel_timeout,
)
def set_current_job_id(job_id):
self.job_id = job_id
job = self.hook.start_flex_template(
body=self.body,
location=self.location,
project_id=self.project_id,
on_new_job_id_callback=set_current_job_id,
)
return job
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)
