def test_exec_success(self, db_mock_class):
"""
Test the execute function in case where the run is successful.
"""
run = {
'notebook_params': NOTEBOOK_PARAMS,
'notebook_task': NOTEBOOK_TASK,
'jar_params': JAR_PARAMS
}
op = DatabricksRunNowOperator(task_id=TASK_ID, job_id=JOB_ID, json=run)
db_mock = db_mock_class.return_value
db_mock.run_now.return_value = 1
db_mock.get_run_state.return_value = RunState('TERMINATED', 'SUCCESS',
'')
op.execute(None)
expected = databricks_operator._deep_string_coerce({
'notebook_params': NOTEBOOK_PARAMS,
'notebook_task': NOTEBOOK_TASK,
'jar_params': JAR_PARAMS,
'job_id': JOB_ID,
})
db_mock_class.assert_called_once_with(
DEFAULT_CONN_ID,
retry_limit=op.databricks_retry_limit,
retry_delay=op.databricks_retry_delay)
db_mock.run_now.assert_called_once_with(expected)
db_mock.get_run_page_url.assert_called_once_with(RUN_ID)
db_mock.get_run_state.assert_called_once_with(RUN_ID)
assert RUN_ID == op.run_id
def test_exec_failure(self, db_mock_class):
"""
Test the execute function in case where the run failed.
"""
run = {
'notebook_params': NOTEBOOK_PARAMS,
'notebook_task': NOTEBOOK_TASK,
'jar_params': JAR_PARAMS
}
op = DatabricksRunNowOperator(task_id=TASK_ID, job_id=JOB_ID, json=run)
db_mock = db_mock_class.return_value
db_mock.run_now.return_value = 1
db_mock.get_run_state.return_value = RunState('TERMINATED', 'FAILED',
'')
with self.assertRaises(AirflowException):
op.execute(None)
expected = databricks_operator._deep_string_coerce({
'notebook_params': NOTEBOOK_PARAMS,
'notebook_task': NOTEBOOK_TASK,
'jar_params': JAR_PARAMS,
'job_id': JOB_ID
})
db_mock_class.assert_called_once_with(
DEFAULT_CONN_ID,
retry_limit=op.databricks_retry_limit,
retry_delay=op.databricks_retry_delay)
db_mock.run_now.assert_called_once_with(expected)
db_mock.get_run_page_url.assert_called_once_with(RUN_ID)
db_mock.get_run_state.assert_called_once_with(RUN_ID)
self.assertEqual(RUN_ID, op.run_id)
def test_on_kill(self, db_mock_class):
run = {'notebook_params': NOTEBOOK_PARAMS, 'notebook_task': NOTEBOOK_TASK, 'jar_params': JAR_PARAMS}
op = DatabricksRunNowOperator(task_id=TASK_ID, job_id=JOB_ID, json=run)
db_mock = db_mock_class.return_value
op.run_id = RUN_ID
op.on_kill()
db_mock.cancel_run.assert_called_once_with(RUN_ID)
def test_init_with_templating(self):
json = {'notebook_params': NOTEBOOK_PARAMS, 'jar_params': TEMPLATED_JAR_PARAMS}
dag = DAG('test', start_date=datetime.now())
op = DatabricksRunNowOperator(dag=dag, task_id=TASK_ID, job_id=JOB_ID, json=json)
op.render_template_fields(context={'ds': DATE})
expected = databricks_operator._deep_string_coerce(
{
'notebook_params': NOTEBOOK_PARAMS,
'jar_params': RENDERED_TEMPLATED_JAR_PARAMS,
'job_id': JOB_ID,
}
)
self.assertDictEqual(expected, op.json)
def test_init_with_bad_type(self):
json = {'test': datetime.now()}
# Looks a bit weird since we have to escape regex reserved symbols.
exception_message = r'Type \<(type|class) \'datetime.datetime\'\> used ' + \
r'for parameter json\[test\] is not a number or a string'
with self.assertRaisesRegex(AirflowException, exception_message):
DatabricksRunNowOperator(task_id=TASK_ID, job_id=JOB_ID, json=json)
def test_init_with_merging(self):
"""
Test the initializer when json and other named parameters are both
provided. The named parameters should override top level keys in the
json dict.
"""
override_notebook_params = {'workers': 999}
json = {'notebook_params': NOTEBOOK_PARAMS, 'jar_params': JAR_PARAMS}
op = DatabricksRunNowOperator(task_id=TASK_ID,
json=json,
job_id=JOB_ID,
notebook_params=override_notebook_params,
python_params=PYTHON_PARAMS,
spark_submit_params=SPARK_SUBMIT_PARAMS)
expected = databricks_operator._deep_string_coerce({
'notebook_params':
override_notebook_params,
'jar_params':
JAR_PARAMS,
'python_params':
PYTHON_PARAMS,
'spark_submit_params':
SPARK_SUBMIT_PARAMS,
'job_id':
JOB_ID
})
self.assertDictEqual(expected, op.json)
def test_init_with_json(self):
"""
Test the initializer with json data.
"""
json = {
'notebook_params': NOTEBOOK_PARAMS,
'jar_params': JAR_PARAMS,
'python_params': PYTHON_PARAMS,
'spark_submit_params': SPARK_SUBMIT_PARAMS,
'job_id': JOB_ID
}
op = DatabricksRunNowOperator(task_id=TASK_ID, json=json)
expected = databricks_operator._deep_string_coerce({
'notebook_params':
NOTEBOOK_PARAMS,
'jar_params':
JAR_PARAMS,
'python_params':
PYTHON_PARAMS,
'spark_submit_params':
SPARK_SUBMIT_PARAMS,
'job_id':
JOB_ID
})
self.assertDictEqual(expected, op.json)
def test_init_with_named_parameters(self):
"""
Test the initializer with the named parameters.
"""
op = DatabricksRunNowOperator(job_id=JOB_ID, task_id=TASK_ID)
expected = databricks_operator._deep_string_coerce({'job_id': 42})
self.assertDictEqual(expected, op.json)
with DAG(
'orchestration_good_practices',
start_date=datetime(2021, 1, 1),
schedule_interval='@daily',
catchup=False,
default_args={
'owner': 'airflow',
'email_on_failure': False,
'retries': 1,
'retry_delay': timedelta(minutes=1)
},
) as dag:
opr_refresh_mat_view = PostgresOperator(
task_id='refresh_mat_view',
postgres_conn_id='postgres_default',
sql='REFRESH MATERIALIZED VIEW example_view;',
)
opr_submit_run = DatabricksSubmitRunOperator(
task_id='submit_run',
databricks_conn_id='databricks',
new_cluster=new_cluster,
notebook_task=notebook_task)
opr_run_now = DatabricksRunNowOperator(task_id='run_now',
databricks_conn_id='databricks',
job_id=5,
notebook_params=notebook_params)
opr_refresh_mat_view >> opr_submit_run >> opr_run_now
"depends_on_past": False,
"email_on_failure": False,
"email_on_retry": False,
"retries": 1,
"retry_delay": timedelta(minutes=2),
}
with DAG(
"databricks_dag",
start_date=datetime(2021, 1, 1),
schedule_interval="@daily",
catchup=False,
default_args=default_args,
) as dag:
opr_submit_run = DatabricksSubmitRunOperator(
task_id="submit_run",
databricks_conn_id="databricks",
new_cluster=new_cluster,
notebook_task=notebook_task,
)
opr_run_now = DatabricksRunNowOperator(
task_id="run_now",
databricks_conn_id="databricks",
job_id=5,
notebook_params=notebook_params,
)
opr_submit_run >> opr_run_now
from airflow import DAG
from airflow.operators.bash import BashOperator
from airflow.providers.databricks.operators.databricks import DatabricksSubmitRunOperator, DatabricksRunNowOperator
from datetime import datetime, timedelta
default_args = {
'owner': 'airflow',
'depends_on_past': False,
'email_on_failure': False,
'email_on_retry': False,
'retries': 1,
'retry_delay': timedelta(minutes=2)
}
with DAG('databricks_dieg_dag',
start_date=datetime(2021, 1, 1),
schedule_interval='@daily',
catchup=False,
default_args=default_args) as dag:
helloworld1 = DatabricksRunNowOperator(task_id='run_now',
databricks_conn_id='Databricksdieg',
job_id=5)
helloworld2 = BashOperator(
task_id='running_bash_bitch',
bash_command='echo donneeeeeeeeeeeeeeeee',
)
helloworld1 >> helloworld2
