Guosmilesmile commented on code in PR #14435: URL: https://github.com/apache/iceberg/pull/14435#discussion_r2568285206
########## spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/actions/SparkParquetFileMergeRunner.java: ########## @@ -0,0 +1,504 @@ +/* + * 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.IOException; +import java.io.Serializable; +import java.nio.ByteBuffer; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.MetadataColumns; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.MetricsConfig; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.TableUtil; +import org.apache.iceberg.actions.RewriteFileGroup; +import org.apache.iceberg.encryption.EncryptedOutputFile; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.io.OutputFileFactory; +import org.apache.iceberg.parquet.ParquetFileMerger; +import org.apache.iceberg.parquet.ParquetUtil; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +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.FileRewriteCoordinator; +import org.apache.iceberg.types.Conversions; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.parquet.schema.MessageType; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * Extension of SparkBinPackFileRewriteRunner that uses ParquetFileMerger for efficient row-group + * level merging of Parquet files when applicable. + * + * <p>This runner uses {@link ParquetFileMerger} to merge Parquet files at the row-group level + * without full deserialization, which is significantly faster than the standard Spark rewrite + * approach for Parquet files. + * + * <p>The decision to use this runner vs. SparkBinPackFileRewriteRunner is controlled by the + * configuration option {@code use-parquet-file-merger}. + */ +public class SparkParquetFileMergeRunner extends SparkBinPackFileRewriteRunner { Review Comment: I think we should add some lineage-related test cases for this class to make sure the lineage information is neither lost nor incomplete. -- 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]
