aokolnychyi commented on code in PR #7029: URL: https://github.com/apache/iceberg/pull/7029#discussion_r1151424302
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkPositionDeletesRewrite.java: ########## @@ -0,0 +1,429 @@ +/* + * 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.io.IOException; +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import org.apache.iceberg.DeleteFile; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.MetadataColumns; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Partitioning; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.PositionDeletesTable; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.deletes.PositionDelete; +import org.apache.iceberg.io.ClusteredPositionDeleteWriter; +import org.apache.iceberg.io.DeleteWriteResult; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFileFactory; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.PositionDeletesRewriteCoordinator; +import org.apache.iceberg.spark.ScanTaskSetManager; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.spark.SparkWriteConf; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.StructProjection; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.broadcast.Broadcast; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.write.BatchWrite; +import org.apache.spark.sql.connector.write.DataWriter; +import org.apache.spark.sql.connector.write.DataWriterFactory; +import org.apache.spark.sql.connector.write.LogicalWriteInfo; +import org.apache.spark.sql.connector.write.PhysicalWriteInfo; +import org.apache.spark.sql.connector.write.Write; +import org.apache.spark.sql.connector.write.WriterCommitMessage; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import scala.Option; + +/** + * {@link Write} class for rewriting position delete files from Spark. Responsible for creating + * {@link PositionDeleteBatchWrite} + * + * <p>This class is meant to be used for an action to rewrite delete files. Hence, it makes an + * assumption that all incoming deletes belong to the same partition, and that incoming dataset is + * from {@link ScanTaskSetManager}. + */ +public class SparkPositionDeletesRewrite implements Write { + private static final Logger LOG = LoggerFactory.getLogger(SparkPositionDeletesRewrite.class); + + private final JavaSparkContext sparkContext; + private final Table table; + private final String queryId; + private final FileFormat format; + private final long targetFileSize; + private final Schema writeSchema; + private final StructType dsSchema; + private final String fileSetId; + private final int specId; + + /** + * Constructs a SparkPositionDeletesWrite. + * + * @param spark spark session + * @param table instance of {@link PositionDeletesTable} + * @param writeConf spark write config + * @param writeInfo spark write info + * @param writeSchema Iceberg output schema + * @param dsSchema schema of original incoming position deletes dataset + */ + SparkPositionDeletesRewrite( + SparkSession spark, + Table table, + SparkWriteConf writeConf, + LogicalWriteInfo writeInfo, + Schema writeSchema, + StructType dsSchema) { + this.sparkContext = JavaSparkContext.fromSparkContext(spark.sparkContext()); + this.table = table; + this.queryId = writeInfo.queryId(); + this.format = writeConf.dataFileFormat(); + this.targetFileSize = writeConf.targetDataFileSize(); + this.writeSchema = writeSchema; + this.dsSchema = dsSchema; + this.fileSetId = writeConf.rewrittenFileSetId(); + + // all files of rewrite group have same spec id + ScanTaskSetManager scanTaskSetManager = ScanTaskSetManager.get(); + List<PositionDeletesScanTask> scanTasks = scanTaskSetManager.fetchTasks(table, fileSetId); Review Comment: You are right. Up to you if you want to keep it or 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. 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
