aakash-db commented on code in PR #50942: URL: https://github.com/apache/spark/pull/50942#discussion_r2101015244
########## sql/connect/common/src/main/protobuf/spark/connect/pipelines.proto: ########## @@ -0,0 +1,173 @@ +/* + * 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. + */ + +syntax = "proto3"; + +package spark.connect; + +import "spark/connect/relations.proto"; +import "spark/connect/types.proto"; + +option java_multiple_files = true; +option java_package = "org.apache.spark.connect.proto"; + +// Dispatch object for pipelines commands. See each individual command for documentation. +message PipelineCommand { + oneof command_type { + CreateDataflowGraph create_dataflow_graph = 1; + DefineDataset define_dataset = 2; + DefineFlow define_flow = 3; + DropDataflowGraph drop_dataflow_graph = 4; + StartRun start_run = 5; + StopRun stop_run = 6; + DefineSqlGraphElements define_sql_graph_elements = 7; + } + + // Request to create a new dataflow graph. + message CreateDataflowGraph { + // The default catalog. + optional string default_catalog = 1; + + // The default database. + optional string default_database = 2; + + // SQL configurations for all flows in this graph. + map<string, string> sql_conf = 5; + + message Response { + // The ID of the created graph. + string dataflow_graph_id = 1; + } + } + + // Drops the graph and stops any running attached flows. + message DropDataflowGraph { + // The graph to drop. + string dataflow_graph_id = 1; + } + + // Request to define a dataset: a table, a materialized view, or a temporary view. + message DefineDataset { + // The graph to attach this dataset to. + string dataflow_graph_id = 1; + + // Name of the dataset. Can be partially or fully qualified. + string dataset_name = 2; + + // The type of the dataset. + DatasetType dataset_type = 3; + + // Optional comment for the dataset. + optional string comment = 4; + + // Optional table properties. Only applies to dataset_type == TABLE and dataset_type == MATERIALIZED_VIEW. + map<string, string> table_properties = 5; + + // Optional partition columns for the dataset. Only applies to dataset_type == TABLE and + // dataset_type == MATERIALIZED_VIEW. + repeated string partition_cols = 6; + + // Schema for the dataset. If unset, this will be inferred from incoming flows. + optional spark.connect.DataType schema = 7; + + // The output table format of the dataset. Only applies to dataset_type == TABLE and + // dataset_type == MATERIALIZED_VIEW. + optional string format = 8; + } + + // Request to define a flow targeting a dataset. + message DefineFlow { + // The graph to attach this dataset to. + string dataflow_graph_id = 1; + + // Name of the flow. For standalone flows, this must be a single-part name. + string flow_name = 2; + + // Name of the dataset this flow writes to. Can be partially or fully qualified. + string target_dataset_name = 3; + + // An unresolved relation that defines the dataset's flow. + spark.connect.Relation plan = 4; Review Comment: but I added optional anyways just for consistency and to make this obvious. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
