harishkrao commented on code in PR #28950: URL: https://github.com/apache/airflow/pull/28950#discussion_r1104100927
########## airflow/providers/databricks/sensors/databricks_partition.py: ########## @@ -0,0 +1,167 @@ +# +# 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 + +import datetime +from typing import Sequence + +from airflow.exceptions import AirflowException +from airflow.providers.databricks.hooks.databricks_sql import DatabricksSqlHook +from airflow.providers.databricks.sensors.databricks_sql import DatabricksSqlSensor +from airflow.providers.databricks.utils.databricks import ParamEscaper +from airflow.utils.context import Context + + +class DatabricksPartitionSensor(DatabricksSqlSensor): + """Sensor to detect the existence of partitions in a Delta table. + + :param databricks_conn_id: Reference to :ref:`Databricks + connection id<howto/connection:databricks>` (templated). + :param http_path: Optional string specifying HTTP path of Databricks SQL Endpoint or cluster. + If not specified, it should be either specified in the Databricks connection's extra parameters, + or ``sql_endpoint_name`` must be specified. + :param sql_endpoint_name: Optional name of Databricks SQL Endpoint. + If not specified, ``http_path`` must be provided as described above. + :param session_configuration: An optional dictionary of Spark session parameters. If not specified, + it could be specified in the Databricks connection's extra parameters. + :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 DBR version 9.0+ (templated) + :param _schema: An optional initial schema to use. Requires DBR version 9.0+ (templated) + :param table_name: Table name to generate the SQL query. + :param partitions: Partitions to check, supplied via a dict. + :param handler: Handler for DbApiHook.run() to return results, defaults to fetch_one_handler + :param client_parameters: Additional parameters internal to Databricks SQL Connector parameters. + :param partition_operator: Comparison operator for partitions. + """ + + template_fields: Sequence[str] = ( + "databricks_conn_id", + "_schema", + "http_headers", + "_catalog", + "table_name", + "partitions", + ) + + def __init__( + self, + table_name: str, + partitions: dict, + partition_operator: str = "=", + *args, + **kwargs, + ) -> None: + super().__init__(*args, **kwargs) + self.caller = "DatabricksPartitionSensor" + self.partitions = partitions + self.partition_operator = partition_operator + self.table_name = table_name + self.escaper = ParamEscaper() + + def _get_hook(self) -> DatabricksSqlHook: Review Comment: Removed them from both child classes. -- 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]
