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

.. py:module:: airflow.contrib.hooks.databricks_hook


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

.. data:: RESTART_CLUSTER_ENDPOINT
   :annotation: = ['POST', 'api/2.0/clusters/restart']

   
.. data:: START_CLUSTER_ENDPOINT
   :annotation: = ['POST', 'api/2.0/clusters/start']

   
.. data:: TERMINATE_CLUSTER_ENDPOINT
   :annotation: = ['POST', 'api/2.0/clusters/delete']

   
.. data:: RUN_NOW_ENDPOINT
   :annotation: = ['POST', 'api/2.0/jobs/run-now']

   
.. data:: SUBMIT_RUN_ENDPOINT
   :annotation: = ['POST', 'api/2.0/jobs/runs/submit']

   
.. data:: GET_RUN_ENDPOINT
   :annotation: = ['GET', 'api/2.0/jobs/runs/get']

   
.. data:: CANCEL_RUN_ENDPOINT
   :annotation: = ['POST', 'api/2.0/jobs/runs/cancel']

   
.. data:: USER_AGENT_HEADER
   

.. py:class:: DatabricksHook(databricks_conn_id='databricks_default', timeout_seconds=180, retry_limit=3, retry_delay=1.0)

   Bases: :class:`airflow.hooks.base_hook.BaseHook`

   Interact with Databricks.

   
   .. staticmethod:: _parse_host(host)

      The purpose of this function is to be robust to improper connections
      settings provided by users, specifically in the host field.

      For example -- when users supply ``https://xx.cloud.databricks.com`` as the
      host, we must strip out the protocol to get the host.::

          h = DatabricksHook()
          assert h._parse_host('https://xx.cloud.databricks.com') ==                 'xx.cloud.databricks.com'

      In the case where users supply the correct ``xx.cloud.databricks.com`` as the
      host, this function is a no-op.::

          assert h._parse_host('xx.cloud.databricks.com') == 'xx.cloud.databricks.com'


   .. method:: _do_api_call(self, endpoint_info, json)

      Utility function to perform an API call with retries

      :param endpoint_info: Tuple of method and endpoint
      :type endpoint_info: tuple[string, string]
      :param json: Parameters for this API call.
      :type json: dict
      :return: If the api call returns a OK status code,
          this function returns the response in JSON. Otherwise,
          we throw an AirflowException.
      :rtype: dict


   .. method:: _log_request_error(self, attempt_num, error)


   .. method:: run_now(self, json)

      Utility function to call the ``api/2.0/jobs/run-now`` endpoint.

      :param json: The data used in the body of the request to the ``run-now`` endpoint.
      :type json: dict
      :return: the run_id as a string
      :rtype: str


   .. method:: submit_run(self, json)

      Utility function to call the ``api/2.0/jobs/runs/submit`` endpoint.

      :param json: The data used in the body of the request to the ``submit`` endpoint.
      :type json: dict
      :return: the run_id as a string
      :rtype: str


   .. method:: get_run_page_url(self, run_id)


   .. method:: get_run_state(self, run_id)


   .. method:: cancel_run(self, run_id)


   .. method:: restart_cluster(self, json)


   .. method:: start_cluster(self, json)


   .. method:: terminate_cluster(self, json)


.. function:: _retryable_error(exception)

.. data:: RUN_LIFE_CYCLE_STATES
   :annotation: = ['PENDING', 'RUNNING', 'TERMINATING', 'TERMINATED', 'SKIPPED', 'INTERNAL_ERROR']

   
.. py:class:: RunState(life_cycle_state, result_state, state_message)

   Utility class for the run state concept of Databricks runs.

   .. attribute:: is_terminal
      

   .. attribute:: is_successful
      

   .. method:: __eq__(self, other)


   .. method:: __repr__(self)


.. py:class:: _TokenAuth(token)

   Bases: :class:`requests.auth.AuthBase`

   Helper class for requests Auth field. AuthBase requires you to implement the __call__
   magic function.

   
   .. method:: __call__(self, r)