:mod:`airflow.contrib.hooks.gcp_dataproc_hook`
==============================================

.. py:module:: airflow.contrib.hooks.gcp_dataproc_hook


Module Contents
---------------

.. py:class:: _DataProcJob(dataproc_api, project_id, job, region='global', job_error_states=None, num_retries=5)

   Bases: :class:`airflow.utils.log.logging_mixin.LoggingMixin`

   
   .. method:: wait_for_done(self)


   .. method:: raise_error(self, message=None)


   .. method:: get(self)


.. py:class:: _DataProcJobBuilder(project_id, task_id, cluster_name, job_type, properties)

   
   .. method:: add_labels(self, labels)

      Set labels for Dataproc job.

      :param labels: Labels for the job query.
      :type labels: dict


   .. method:: add_variables(self, variables)


   .. method:: add_args(self, args)


   .. method:: add_query(self, query)


   .. method:: add_query_uri(self, query_uri)


   .. method:: add_jar_file_uris(self, jars)


   .. method:: add_archive_uris(self, archives)


   .. method:: add_file_uris(self, files)


   .. method:: add_python_file_uris(self, pyfiles)


   .. method:: set_main(self, main_jar, main_class)


   .. method:: set_python_main(self, main)


   .. method:: set_job_name(self, name)


   .. method:: build(self)


.. py:class:: _DataProcOperation(dataproc_api, operation, num_retries)

   Bases: :class:`airflow.utils.log.logging_mixin.LoggingMixin`

   Continuously polls Dataproc Operation until it completes.

   
   .. method:: wait_for_done(self)


   .. method:: get(self)


   .. method:: _check_done(self)


   .. method:: _raise_error(self)


.. py:class:: DataProcHook(gcp_conn_id='google_cloud_default', delegate_to=None, api_version='v1beta2')

   Bases: :class:`airflow.contrib.hooks.gcp_api_base_hook.GoogleCloudBaseHook`

   Hook for Google Cloud Dataproc APIs.

   
   .. method:: get_conn(self)

      Returns a Google Cloud Dataproc service object.


   .. method:: get_cluster(self, project_id, region, cluster_name)


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


   .. method:: create_job_template(self, task_id, cluster_name, job_type, properties)


   .. method:: wait(self, operation)

      Awaits for Google Cloud Dataproc Operation to complete.


   .. method:: 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