airflow.contrib.hooks.gcp_dataproc_hook

Module Contents

class airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob(dataproc_api, project_id, job, region='global', job_error_states=None, num_retries=None)

Bases: airflow.utils.log.logging_mixin.LoggingMixin

wait_for_done(self)

raise_error(self, message=None)

get(self)

class airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder(project_id, task_id, cluster_name, job_type, properties)

add_variables(self, variables)

add_args(self, args)

add_query(self, query)

add_query_uri(self, query_uri)

add_jar_file_uris(self, jars)

add_archive_uris(self, archives)

add_file_uris(self, files)

add_python_file_uris(self, pyfiles)

set_main(self, main_jar, main_class)

set_python_main(self, main)

set_job_name(self, name)

build(self)

class airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation(dataproc_api, operation, num_retries)

Bases: airflow.utils.log.logging_mixin.LoggingMixin

Continuously polls Dataproc Operation until it completes.

wait_for_done(self)

get(self)

_check_done(self)

_raise_error(self)

class airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook(gcp_conn_id='google_cloud_default', delegate_to=None, api_version='v1beta2')

Bases: airflow.contrib.hooks.gcp_api_base_hook.GoogleCloudBaseHook

Hook for Google Cloud Dataproc APIs.

get_conn(self)

Returns a Google Cloud Dataproc service object.

get_cluster(self, project_id, region, cluster_name)

submit(self, project_id, job, region='global', job_error_states=None)

create_job_template(self, task_id, cluster_name, job_type, properties)

wait(self, operation)

Awaits for Google Cloud Dataproc Operation to complete.

cancel(self, project_id, job_id, region='global')

Cancel a Google Cloud DataProc job. :param project_id: Name of the project the job belongs to :type project_id: str :param job_id: Identifier of the job to cancel :type job_id: int :param region: Region used for the job :type region: str :returns A Job json dictionary representing the canceled job