nastra commented on code in PR #10024: URL: https://github.com/apache/iceberg/pull/10024#discussion_r1537451796
########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/BaseCopyTableSparkAction.java: ########## @@ -0,0 +1,871 @@ +/* + * 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.UncheckedIOException; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.UUID; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.DeleteFile; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.FileMetadata; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.ManifestEntry; +import org.apache.iceberg.ManifestFile; +import org.apache.iceberg.ManifestFiles; +import org.apache.iceberg.ManifestLists; +import org.apache.iceberg.ManifestReader; +import org.apache.iceberg.ManifestWriter; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.SerializableTable; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.StaticTableOperations; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableMetadata; +import org.apache.iceberg.TableMetadata.MetadataLogEntry; +import org.apache.iceberg.TableMetadataParser; +import org.apache.iceberg.TableMetadataUtil; +import org.apache.iceberg.actions.BaseCopyTableActionResult; +import org.apache.iceberg.actions.CopyTable; +import org.apache.iceberg.avro.Avro; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.data.avro.DataReader; +import org.apache.iceberg.data.avro.DataWriter; +import org.apache.iceberg.data.orc.GenericOrcReader; +import org.apache.iceberg.data.orc.GenericOrcWriter; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.data.parquet.GenericParquetWriter; +import org.apache.iceberg.deletes.PositionDelete; +import org.apache.iceberg.deletes.PositionDeleteWriter; +import org.apache.iceberg.exceptions.RuntimeIOException; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.DeleteSchemaUtil; +import org.apache.iceberg.io.FileAppender; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.orc.ORC; +import org.apache.iceberg.parquet.Parquet; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +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.SaveMode; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.functions; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class BaseCopyTableSparkAction extends BaseSparkAction<CopyTable> implements CopyTable { + + private static final Logger LOG = LoggerFactory.getLogger(BaseCopyTableSparkAction.class); + private static final String DATA_FILE_LIST_DIR = "data-file-list-to-move"; + private static final String METADATA_FILE_LIST_DIR = "metadata-file-list-to-move"; + + private final Table table; + private final Set<String> metadataFilesToMove = Collections.synchronizedSet(Sets.newHashSet()); + private final Set<String> manifestFilePaths = Collections.synchronizedSet(Sets.newHashSet()); + private final Set<ManifestFile> manifestFilesToRewrite = + Collections.synchronizedSet(Sets.newHashSet()); + private String dataFileListPath = null; + private String metadataFileListPath = null; + private final boolean enabledPME; + + private String sourcePrefix = ""; + private String targetPrefix = ""; + private String startVersion = ""; + private String endVersion = ""; + private String stagingDir = ""; + private Table targetTable = null; + + private Table startStaticTable = null; + private Table endStaticTable = null; + + public BaseCopyTableSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + enabledPME = table.properties().containsKey("parquet.encryption.footer.key"); + } + + @Override + public CopyTable rewriteLocationPrefix(String sPrefix, String tPrefix) { + Preconditions.checkArgument( + sPrefix != null && !sPrefix.isEmpty(), "Source prefix('%s') cannot be empty.", sPrefix); + this.sourcePrefix = sPrefix; + + if (tPrefix != null) { + this.targetPrefix = tPrefix; + } + return this; + } + + @Override + public CopyTable lastCopiedVersion(String sVersion) { Review Comment: it's not clear what `sVersion` refers to, so why not `newStartVersion`? Same for all the other params -- 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
