rahulsmahadev commented on code in PR #17622: URL: https://github.com/apache/iceberg/pull/17622#discussion_r4291116568
########## spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/actions/RepairTableSparkAction.java: ########## @@ -0,0 +1,957 @@ +/* + * 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 static org.apache.iceberg.MetadataTableType.ENTRIES; + +import java.io.Serializable; +import java.util.EnumMap; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.UUID; +import java.util.function.Function; +import java.util.stream.Collectors; +import org.apache.hadoop.fs.Path; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DeleteFile; +import org.apache.iceberg.FileContent; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.GenericManifestFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.ManifestContent; +import org.apache.iceberg.ManifestFile; +import org.apache.iceberg.ManifestFiles; +import org.apache.iceberg.ManifestReader; +import org.apache.iceberg.ManifestWriter; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.MetricsConfig; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Partitioning; +import org.apache.iceberg.RewriteManifests; +import org.apache.iceberg.RollingManifestWriter; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.SnapshotSummary; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.actions.ImmutableRepairTable; +import org.apache.iceberg.actions.RepairTable; +import org.apache.iceberg.encryption.EncryptedOutputFile; +import org.apache.iceberg.encryption.EncryptingFileIO; +import org.apache.iceberg.exceptions.CleanableFailure; +import org.apache.iceberg.exceptions.CommitStateUnknownException; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.io.SupportsBulkOperations; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.spark.SparkContentFile; +import org.apache.iceberg.spark.SparkDataFile; +import org.apache.iceberg.spark.SparkDeleteFile; +import org.apache.iceberg.spark.source.SerializableTableWithSize; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.ScanTaskUtil; +import org.apache.iceberg.util.Tasks; +import org.apache.iceberg.util.ThreadPools; +import org.apache.spark.api.java.function.MapPartitionsFunction; +import org.apache.spark.broadcast.Broadcast; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Encoder; +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.apache.spark.sql.types.StructType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import scala.Tuple2; + +/** + * An action that repairs incorrect statistics in the manifests of a table. + * + * <p>The statistics of every live manifest entry are compared against the file the entry refers to. + * Only manifests that contain at least one incorrect entry are rewritten. Snapshot totals are + * recomputed from the live entries when committing a repair. + * + * <p>Deletion vectors (delete blobs stored in Puffin files) are not verified or repaired. NaN + * counts and floating-point bounds are preserved because footers cannot reconstruct them reliably. + */ +public class RepairTableSparkAction extends BaseSnapshotUpdateSparkAction<RepairTableSparkAction> + implements RepairTable { + + public static final String USE_CACHING = "use-caching"; + public static final boolean USE_CACHING_DEFAULT = false; + + /** + * Whether to compare and repair column level statistics. When disabled, only record counts and + * file sizes are compared and repaired. + * + * <p>This is disabled by default. Recomputed column statistics reflect the current metrics config + * of the table, but the config a file was written under is not recorded, so a table whose config + * changed reports column statistics that legitimately differ from the recomputed ones. Repairing + * them in that case would overwrite correct statistics. Reading the footer of every candidate + * file happens regardless of this option; it only controls whether column statistics are + * compared. + */ + public static final String REPAIR_COLUMN_METRICS = "repair-column-metrics"; Review Comment: Done -- 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]
