rdblue commented on a change in pull request #1738: URL: https://github.com/apache/iceberg/pull/1738#discussion_r519070975
########## File path: spark3/src/main/java/org/apache/iceberg/spark/source/SparkFileBatchScan.java ########## @@ -0,0 +1,161 @@ +/* + * 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.Map; +import java.util.Objects; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.encryption.EncryptionManager; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.TableScanUtil; +import org.apache.spark.broadcast.Broadcast; +import org.apache.spark.sql.connector.read.Statistics; +import org.apache.spark.sql.connector.read.SupportsReadFileFilter; +import org.apache.spark.sql.util.CaseInsensitiveStringMap; + +import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK; +import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK_DEFAULT; +import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST; +import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST_DEFAULT; +import static org.apache.iceberg.TableProperties.SPLIT_SIZE; +import static org.apache.iceberg.TableProperties.SPLIT_SIZE_DEFAULT; + +public class SparkFileBatchScan extends BaseBatchScan implements SupportsReadFileFilter { + private List<FileScanTask> files; + + // lazy cache of tasks + private List<CombinedScanTask> tasks = null; + + public SparkFileBatchScan(Table table, List<FileScanTask> files, Broadcast<FileIO> io, + Broadcast<EncryptionManager> encryptionManager, boolean caseSensitive, + CaseInsensitiveStringMap options) { + super(table, table.schema(), io, encryptionManager, caseSensitive, options); + this.files = files; Review comment: I think I would pass this Scan into the write and expose `files()` to return the list. That way, we only implement `filterFiles` once and we know the two lists are always in sync. If we do that and rely on the fact that the scan and the write are built at the same time, then we can remove the write interface to expose `filterFiles`. ---------------------------------------------------------------- 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]
