aokolnychyi commented on code in PR #6924: URL: https://github.com/apache/iceberg/pull/6924#discussion_r1130406457
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkStagedScan.java: ########## @@ -0,0 +1,114 @@ +/* + * 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.source; + +import java.util.List; +import java.util.Objects; +import org.apache.iceberg.ScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Table; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.spark.ScanTaskSetManager; +import org.apache.iceberg.spark.SparkReadConf; +import org.apache.iceberg.util.TableScanUtil; +import org.apache.spark.sql.SparkSession; + +class SparkStagedScan extends SparkScan { + + private final String taskSetID; + private final long splitSize; + private final int splitLookback; + private final long splitOpenFileCost; + + private List<ScanTaskGroup<ScanTask>> taskGroups = null; // lazy cache of tasks + + SparkStagedScan(SparkSession spark, Table table, SparkReadConf readConf) { + super(spark, table, readConf, table.schema(), ImmutableList.of()); + + this.taskSetID = readConf.scanTaskSetId(); + this.splitSize = readConf.splitSize(); + this.splitLookback = readConf.splitLookback(); + this.splitOpenFileCost = readConf.splitOpenFileCost(); + } + + protected String taskSetID() { + return taskSetID; + } + + protected long splitSize() { + return splitSize; + } + + protected int splitLookback() { + return splitLookback; + } + + protected long splitOpenFileCost() { + return splitOpenFileCost; + } + + @Override + protected List<ScanTaskGroup<ScanTask>> taskGroups() { + if (taskGroups == null) { + + ScanTaskSetManager taskSetManager = ScanTaskSetManager.get(); + List<ScanTask> tasks = taskSetManager.fetchTasks(table(), taskSetID); + ValidationException.check( + tasks != null, + "Task set manager has no tasks for table %s with id %s", Review Comment: nit: `with id ` -> `with task set ID` -- 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
