harishkesavarao commented on code in PR #30428: URL: https://github.com/apache/airflow/pull/30428#discussion_r1155436094
########## airflow/providers/databricks/sensors/sql.py: ########## @@ -0,0 +1,131 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# +"""This module contains Databricks sensors.""" + +from __future__ import annotations + +from typing import TYPE_CHECKING, Any, Callable, Iterable, Sequence + +from airflow.compat.functools import cached_property +from airflow.providers.common.sql.hooks.sql import fetch_all_handler +from airflow.providers.databricks.hooks.databricks_sql import DatabricksSqlHook +from airflow.sensors.base import BaseSensorOperator +from airflow.exceptions import AirflowException + +if TYPE_CHECKING: + from airflow.utils.context import Context + + +class DatabricksSqlSensor(BaseSensorOperator): + """ + Sensor that runs a SQL query on Databricks. + + :param databricks_conn_id: Reference to :ref:`Databricks + connection id<howto/connection:databricks>` (templated), defaults to + DatabricksSqlHook.default_conn_name. + :param sql_warehouse_name: Optional name of Databricks SQL Warehouse. If not specified, ``http_path`` + must be provided as described below, defaults to None + :param http_path: Optional string specifying HTTP path of Databricks SQL Warehouse or All Purpose Cluster. + If not specified, it should be either specified in the Databricks connection's + extra parameters, or ``sql_warehouse_name`` must be specified. + :param session_configuration: An optional dictionary of Spark session parameters. If not specified, + it could be specified in the Databricks connection's extra parameters., defaults to None + :param http_headers: An optional list of (k, v) pairs + that will be set as HTTP headers on every request. (templated). + :param catalog: An optional initial catalog to use. + Requires Databricks Runtime version 9.0+ (templated), defaults to "" + :param schema: An optional initial schema to use. + Requires Databricks Runtime version 9.0+ (templated), defaults to "default" + :param sql: SQL statement to be executed. + :param handler: Handler for DbApiHook.run() to return results, defaults to fetch_all_handler + :param client_parameters: Additional parameters internal to Databricks SQL Connector parameters. + """ + + template_fields: Sequence[str] = ( + "databricks_conn_id", + "sql", + "catalog", + "schema", + "http_headers", + ) + + template_ext: Sequence[str] = (".sql",) + template_fields_renderers = {"sql": "sql"} + + def __init__( + self, + *, + databricks_conn_id: str = DatabricksSqlHook.default_conn_name, + http_path: str | None = None, + sql_warehouse_name: str | None = None, + session_configuration=None, + http_headers: list[tuple[str, str]] | None = None, + catalog: str = "", + schema: str = "default", + sql: str | Iterable[str], + handler: Callable[[Any], Any] = fetch_all_handler, + client_parameters: dict[str, Any] | None = None, + **kwargs, + ) -> None: + """Creates DatabricksSqlSensor object using the specified input arguments.""" + self.databricks_conn_id = databricks_conn_id + self._http_path = http_path + self._sql_warehouse_name = sql_warehouse_name + self.session_config = session_configuration + self.http_headers = http_headers + self.catalog = catalog + self.schema = schema + self.sql = sql + self.caller = "DatabricksSqlSensor" + self.client_parameters = client_parameters or {} + self.hook_params = kwargs.pop("hook_params", {}) + self.handler = handler + super().__init__(**kwargs) + + @cached_property + def _get_hook(self) -> DatabricksSqlHook: + """Creates and returns a DatabricksSqlHook object.""" + return DatabricksSqlHook( + self.databricks_conn_id, + self._http_path, + self._sql_warehouse_name, + self.session_config, + self.http_headers, + self.catalog, + self.schema, + self.caller, + **self.client_parameters, + **self.hook_params, + ) + + def _get_results(self) -> bool: + """Uses the Databricks SQL hook and runs the specified SQL query.""" + if self._http_path in (None, "") and self._sql_warehouse_name in (None, ""): Review Comment: Changed. ########## tests/system/providers/databricks/example_databricks_sensor.py: ########## @@ -0,0 +1,86 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +from __future__ import annotations + +import os +import textwrap +from datetime import datetime + +from airflow import DAG +from airflow.providers.databricks.sensors.sql import DatabricksSqlSensor + +# [Env variable to be used from the OS] +ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID") +# [DAG name to be shown on Airflow UI] +DAG_ID = "example_databricks_sensor" + +with DAG( + dag_id=DAG_ID, + schedule="@daily", + start_date=datetime(2021, 1, 1), + tags=["example"], + catchup=False, +) as dag: + dag.doc_md = textwrap.dedent( + """ + + This is an example DAG which uses the DatabricksSqlSensor + sensor. The example task in the DAG executes the provided + SQL query against the Databricks SQL warehouse and if a + result is returned, the sensor returns True/succeeds. + If no results are returned, the sensor returns False/ + fails. + + """ + ) + # [START howto_sensor_databricks_connection_setup] + # Connection string setup for Databricks workspace. + connection_id = "databricks_default" + sql_warehouse_name = "Starter Warehouse" + # [END howto_sensor_databricks_connection_setup] + + # [START howto_sensor_databricks_sql] + # Example of using the Databricks SQL Sensor to check existence of data/partitions for a Delta table. Review Comment: Changed. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
