rdblue commented on a change in pull request #1473: URL: https://github.com/apache/iceberg/pull/1473#discussion_r491093021
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/procedures/RollbackToSnapshotProcedure.scala ########## @@ -0,0 +1,57 @@ +/* + * 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. + */ + +package org.apache.spark.sql.catalyst.procedures + +import org.apache.spark.sql.{Row, SparkSession} +import org.apache.spark.sql.connector.catalog.TableCatalog +import org.apache.spark.sql.execution.command.RunnableCommand +import org.apache.spark.sql.types.{LongType, StringType} + +case class RollbackToSnapshotProcedure(catalog: TableCatalog) extends BaseIcebergProcedure { + + override val name: String = "rollback_to_snapshot" + override val parameters: Seq[Parameter] = Seq( + RequiredParameter("table", StringType), + RequiredParameter("snapshot_id", LongType)) + + override def createRunnableCommand(args: Array[Any]): RunnableCommand = { + val tableName = getAs[String](args, index = 0) + val snapshotId = getAs[Long](args, index = 1) + RollbackToSnapshotCommand(catalog, tableName, snapshotId) + } +} + +case class RollbackToSnapshotCommand( + catalog: TableCatalog, + tableName: String, + snapshotId: Long) extends BaseIcebergProcedureCommand { + + override def run(spark: SparkSession): Seq[Row] = { + val table = loadTable(spark, catalog, tableName) + + table.manageSnapshots() + .rollbackTo(snapshotId) + .commit() + + // TODO: refresh catalog and all cached plans that contain this table? Review comment: When caching, the table instance is reused across all plans and is automatically updated by the `commit`. When not caching, I think it's debatable whether we should refresh. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
