RussellSpitzer commented on a change in pull request #2591: URL: https://github.com/apache/iceberg/pull/2591#discussion_r665520638
########## File path: spark3/src/main/java/org/apache/iceberg/spark/actions/Spark3BinPackStrategy.java ########## @@ -0,0 +1,89 @@ +/* + * 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.iceberg.spark.actions; + +import java.util.List; +import java.util.Set; +import java.util.UUID; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.BinPackStrategy; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.spark.FileRewriteCoordinator; +import org.apache.iceberg.spark.FileScanTaskSetManager; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.iceberg.spark.SparkWriteOptions; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.internal.SQLConf; + +public class Spark3BinPackStrategy extends BinPackStrategy { + private final Table table; + private final SparkSession spark; + private final FileScanTaskSetManager manager = FileScanTaskSetManager.get(); + private final FileRewriteCoordinator rewriteCoordinator = FileRewriteCoordinator.get(); + + public Spark3BinPackStrategy(Table table, SparkSession spark) { + this.table = table; + this.spark = spark; + } + + @Override + public Table table() { + return table; + } + + @Override + public Set<DataFile> rewriteFiles(List<FileScanTask> filesToRewrite) { + Set<DataFile> results; + + String groupID = UUID.randomUUID().toString(); + try { + manager.stageTasks(table, groupID, filesToRewrite); + + // Disable Adaptive Query Execution as this may change the output partitioning of our write + SparkSession cloneSession = spark.cloneSession(); Review comment: I'm not sure what you are asking here, this method's doc ```Create an identical copy of this SparkSession, sharing the underlying SparkContext and shared state. All the state of this session (i.e. SQL configurations, temporary tables, registered functions) is copied over, and the cloned session is set up with the same shared state as this session. The cloned session is independent of this session, that is, any non-global change in either session is not reflected in the other.``` We basically just use this make sure we don't change the user's spark session config -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
