rdblue commented on a change in pull request #2472: URL: https://github.com/apache/iceberg/pull/2472#discussion_r615322733
########## File path: spark3/src/main/java/org/apache/iceberg/spark/FileScanTaskSetManager.java ########## @@ -0,0 +1,66 @@ +/* + * 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; + +import java.util.List; +import java.util.Map; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.Pair; + +public class FileScanTaskSetManager { + + private static final FileScanTaskSetManager INSTANCE = new FileScanTaskSetManager(); + + private final Map<Pair<String, String>, List<FileScanTask>> tasksMap = Maps.newConcurrentMap(); + + private FileScanTaskSetManager() { + } + + public static FileScanTaskSetManager get() { + return INSTANCE; + } + + public void stageTasks(Table table, String setID, List<FileScanTask> tasks) { + Preconditions.checkArgument(tasks != null && tasks.size() > 0, "Cannot stage null or empty tasks"); + Pair<String, String> id = toID(table, setID); + tasksMap.put(id, tasks); + } + + public List<FileScanTask> fetchTasks(Table table, String setID) { + Pair<String, String> id = toID(table, setID); + return tasksMap.get(id); + } + + public void removeTasks(Table table, String setID) { Review comment: Would it make sense to follow the same convention as `Map.remove` and return the tasks here? That way there is no need to call `fetchTasks` immediately followed by `removeTasks`. -- 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]
