aokolnychyi commented on a change in pull request #2415: URL: https://github.com/apache/iceberg/pull/2415#discussion_r645842876
########## File path: spark/src/main/java/org/apache/iceberg/spark/actions/BaseRemoveFilesSparkAction.java ########## @@ -0,0 +1,220 @@ +/* + * 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.HashSet; +import java.util.Iterator; +import java.util.List; +import java.util.Set; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.atomic.AtomicLong; +import java.util.function.Consumer; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableMetadataParser; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.actions.RemoveFiles; +import org.apache.iceberg.actions.RemoveFilesActionResult; +import org.apache.iceberg.exceptions.NotFoundException; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.Tasks; +import org.apache.spark.sql.Column; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Encoders; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.functions; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * An action that performs the same operation as {@link RemoveFiles} but uses Spark + * to determine the files that needs to be deleted. The action uses metadata tables to + * find the files to be deleted. + * Deletes are performed locally after retrieving the results from the Spark executors. + */ +@SuppressWarnings("UnnecessaryAnonymousClass") +public class BaseRemoveFilesSparkAction + extends BaseSparkAction<RemoveFiles, RemoveFiles.Result> implements RemoveFiles { + private static final Logger LOG = LoggerFactory.getLogger(BaseRemoveFilesSparkAction.class); + + private static final String DATA_FILE = "Data File"; + private static final String MANIFEST = "Manifest"; + private static final String MANIFEST_LIST = "Manifest List"; + private static final String OTHERS = "Others"; + + private static final String STREAM_RESULTS = "stream-results"; + + // Creates an executor service that runs each task in the thread that invokes execute/submit. + private static final ExecutorService DEFAULT_DELETE_EXECUTOR_SERVICE = null; + + private final Table table; + private final TableOperations ops; + private final Consumer<String> defaultDelete = new Consumer<String>() { + @Override + public void accept(String file) { + ops.io().deleteFile(file); + } + }; + + private Consumer<String> deleteFunc = defaultDelete; + private ExecutorService deleteExecutorService = DEFAULT_DELETE_EXECUTOR_SERVICE; + + public BaseRemoveFilesSparkAction(SparkSession spark, Table table) { Review comment: I consider this action as something we would mostly use from Iceberg code. For example, we currently drop the table and then call `CatalogUtil$dropTableData` that will try to clean as much as possible but may also fail at some point. I see this as a replacement of that logic that should scale much better as we will use metadata tables. I hope users will not really interact with this action and just use the regular DROP with or without purge. The only case when someone would need to invoke this manually is if something went wrong during DROP. In that case, it seems reasonable to ask the user to check whether the table was dropped and find a recent metadata file to use for cleaning the file tree. By calling this as `RemoveReachableFiles` and accepting a metadata location instead of a table we send a message it is something that is invoked after DROP. -- 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]
