aokolnychyi commented on code in PR #5106: URL: https://github.com/apache/iceberg/pull/5106#discussion_r902915275
########## spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/DeleteOrphanFilesSparkAction.java: ########## @@ -0,0 +1,364 @@ +/* + * 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.io.File; +import java.io.IOException; +import java.io.Serializable; +import java.sql.Timestamp; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.TimeUnit; +import java.util.function.Consumer; +import java.util.function.Predicate; +import java.util.stream.Collectors; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.fs.PathFilter; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.BaseDeleteOrphanFilesActionResult; +import org.apache.iceberg.actions.DeleteOrphanFiles; +import org.apache.iceberg.exceptions.RuntimeIOException; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.hadoop.HiddenPathFilter; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Joiner; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +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.api.java.JavaRDD; +import org.apache.spark.api.java.function.FlatMapFunction; +import org.apache.spark.broadcast.Broadcast; +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.expressions.UserDefinedFunction; +import org.apache.spark.sql.functions; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.util.SerializableConfiguration; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.apache.iceberg.TableProperties.GC_ENABLED; +import static org.apache.iceberg.TableProperties.GC_ENABLED_DEFAULT; + +/** + * An action that removes orphan metadata, data and delete files by listing a given location and comparing + * the actual files in that location with content and metadata files referenced by all valid snapshots. + * The location must be accessible for listing via the Hadoop {@link FileSystem}. + * <p> + * By default, this action cleans up the table location returned by {@link Table#location()} and + * removes unreachable files that are older than 3 days using {@link Table#io()}. The behavior can be modified + * by passing a custom location to {@link #location} and a custom timestamp to {@link #olderThan(long)}. + * For example, someone might point this action to the data folder to clean up only orphan data files. + * <p> + * Configure an alternative delete method using {@link #deleteWith(Consumer)}. + * <p> + * For full control of the set of files being evaluated, use the {@link #compareToFileList(Dataset)} argument. This + * skips the directory listing - any files in the dataset provided which are not found in table metadata will + * be deleted, using the same {@link Table#location()} and {@link #olderThan(long)} filtering as above. + * <p> + * <em>Note:</em> It is dangerous to call this action with a short retention interval as it might corrupt + * the state of the table if another operation is writing at the same time. + */ +public class DeleteOrphanFilesSparkAction Review Comment: This is not a new file. I renamed the old one to keep the existing formatting and everything. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
