def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
snake_case_pipeline_options,
process_line_callback,
) = self._init_pipeline_options(format_pipeline_options=True,
job_name_variable_key="job_name")
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
with ExitStack() as exit_stack:
if self.go_file.lower().startswith("gs://"):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
with tempfile.TemporaryDirectory(
prefix="apache-beam-go") as tmp_dir:
tmp_gcs_file = exit_stack.enter_context(
gcs_hook.provide_file(object_url=self.go_file,
dir=tmp_dir))
self.go_file = tmp_gcs_file.name
self.should_init_go_module = True
if is_dataflow and self.dataflow_hook:
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_go_pipeline(
variables=snake_case_pipeline_options,
go_file=self.go_file,
process_line_callback=process_line_callback,
should_init_module=self.should_init_go_module,
)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
if dataflow_job_name and self.dataflow_config.location:
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=False,
project_id=self.dataflow_config.project_id,
)
return {"dataflow_job_id": self.dataflow_job_id}
else:
self.beam_hook.start_go_pipeline(
variables=snake_case_pipeline_options,
go_file=self.go_file,
process_line_callback=process_line_callback,
should_init_module=self.should_init_go_module,
)
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
snake_case_pipeline_options,
process_line_callback,
) = self._init_pipeline_options(format_pipeline_options=True,
job_name_variable_key="job_name")
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
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
if is_dataflow and self.dataflow_hook:
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_python_pipeline(
variables=snake_case_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,
)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
if dataflow_job_name and self.dataflow_config.location:
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=False,
project_id=self.dataflow_config.project_id,
)
return {"dataflow_job_id": self.dataflow_job_id}
else:
self.beam_hook.start_python_pipeline(
variables=snake_case_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,
)
def set_current_job(current_job):
self.job = current_job
DataflowJobLink.persist(self, context, self.project_id,
self.location, self.job.get("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 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 BeamRunGoPipelineOperator(BeamBasePipelineOperator):
"""
Launching Apache Beam pipelines written in Go. 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:BeamRunGoPipelineOperator`
.. seealso::
For more detail on Apache Beam have a look at the reference:
https://beam.apache.org/documentation/
:param go_file: Reference to the Go Apache Beam pipeline e.g.,
/some/local/file/path/to/your/go/pipeline/file.go
"""
template_fields = [
"go_file",
"runner",
"pipeline_options",
"default_pipeline_options",
"dataflow_config",
]
template_fields_renderers = {
'dataflow_config': 'json',
'pipeline_options': 'json'
}
operator_extra_links = (DataflowJobLink(), )
def __init__(
self,
*,
go_file: str,
runner: str = "DirectRunner",
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__(
runner=runner,
default_pipeline_options=default_pipeline_options,
pipeline_options=pipeline_options,
gcp_conn_id=gcp_conn_id,
delegate_to=delegate_to,
dataflow_config=dataflow_config,
**kwargs,
)
if self.dataflow_config.impersonation_chain:
self.log.info(
"Impersonation chain parameter is not supported for Apache Beam GO SDK and will be skipped "
"in the execution")
self.dataflow_support_impersonation = False
self.go_file = go_file
self.should_init_go_module = False
self.pipeline_options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
snake_case_pipeline_options,
process_line_callback,
) = self._init_pipeline_options(format_pipeline_options=True,
job_name_variable_key="job_name")
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
with ExitStack() as exit_stack:
if self.go_file.lower().startswith("gs://"):
gcs_hook = GCSHook(self.gcp_conn_id, self.delegate_to)
with tempfile.TemporaryDirectory(
prefix="apache-beam-go") as tmp_dir:
tmp_gcs_file = exit_stack.enter_context(
gcs_hook.provide_file(object_url=self.go_file,
dir=tmp_dir))
self.go_file = tmp_gcs_file.name
self.should_init_go_module = True
if is_dataflow and self.dataflow_hook:
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_go_pipeline(
variables=snake_case_pipeline_options,
go_file=self.go_file,
process_line_callback=process_line_callback,
should_init_module=self.should_init_go_module,
)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
if dataflow_job_name and self.dataflow_config.location:
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=False,
project_id=self.dataflow_config.project_id,
)
return {"dataflow_job_id": self.dataflow_job_id}
else:
self.beam_hook.start_go_pipeline(
variables=snake_case_pipeline_options,
go_file=self.go_file,
process_line_callback=process_line_callback,
should_init_module=self.should_init_go_module,
)
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,
)
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
pipeline_options,
process_line_callback,
) = self._init_pipeline_options()
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
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)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
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,
)
return {"dataflow_job_id": self.dataflow_job_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,
)
class BeamRunJavaPipelineOperator(BeamBasePipelineOperator):
"""
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).
: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.
"""
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"
operator_extra_links = (DataflowJobLink(), )
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__(
runner=runner,
default_pipeline_options=default_pipeline_options,
pipeline_options=pipeline_options,
gcp_conn_id=gcp_conn_id,
delegate_to=delegate_to,
dataflow_config=dataflow_config,
**kwargs,
)
self.jar = jar
self.job_class = job_class
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
pipeline_options,
process_line_callback,
) = self._init_pipeline_options()
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
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)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
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,
)
return {"dataflow_job_id": self.dataflow_job_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,
)
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 BeamRunPythonPipelineOperator(BeamBasePipelineOperator):
"""
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)
:param py_options: Additional python options, e.g., ["-m", "-v"].
: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.
"""
template_fields: Sequence[str] = (
"py_file",
"runner",
"pipeline_options",
"default_pipeline_options",
"dataflow_config",
)
template_fields_renderers = {
'dataflow_config': 'json',
'pipeline_options': 'json'
}
operator_extra_links = (DataflowJobLink(), )
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__(
runner=runner,
default_pipeline_options=default_pipeline_options,
pipeline_options=pipeline_options,
gcp_conn_id=gcp_conn_id,
delegate_to=delegate_to,
dataflow_config=dataflow_config,
**kwargs,
)
self.py_file = py_file
self.py_options = py_options or []
self.py_interpreter = py_interpreter
self.py_requirements = py_requirements
self.py_system_site_packages = py_system_site_packages
self.pipeline_options.setdefault("labels", {}).update({
"airflow-version":
"v" + version.replace(".", "-").replace("+", "-")
})
def execute(self, context: 'Context'):
"""Execute the Apache Beam Pipeline."""
(
is_dataflow,
dataflow_job_name,
snake_case_pipeline_options,
process_line_callback,
) = self._init_pipeline_options(format_pipeline_options=True,
job_name_variable_key="job_name")
if not self.beam_hook:
raise AirflowException("Beam hook is not defined.")
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
if is_dataflow and self.dataflow_hook:
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_python_pipeline(
variables=snake_case_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,
)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
if dataflow_job_name and self.dataflow_config.location:
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
job_id=self.dataflow_job_id,
multiple_jobs=False,
project_id=self.dataflow_config.project_id,
)
return {"dataflow_job_id": self.dataflow_job_id}
else:
self.beam_hook.start_python_pipeline(
variables=snake_case_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,
)
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,
)