manuzhang commented on code in PR #14948: URL: https://github.com/apache/iceberg/pull/14948#discussion_r3245907595
########## spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/source/MergingSortedRowDataReader.java: ########## @@ -0,0 +1,299 @@ +/* + * 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.io.UncheckedIOException; +import java.util.Arrays; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.stream.Collectors; +import org.apache.iceberg.BaseScanTaskGroup; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.SortField; +import org.apache.iceberg.SortOrder; +import org.apache.iceberg.SortOrderComparators; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.Table; +import org.apache.iceberg.io.CloseableGroup; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.CloseableIterator; +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.SparkSchemaUtil; +import org.apache.iceberg.spark.source.metrics.TaskNumDeletes; +import org.apache.iceberg.spark.source.metrics.TaskNumSplits; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.SortedMerge; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.catalyst.expressions.GenericInternalRow; +import org.apache.spark.sql.connector.metric.CustomTaskMetric; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.StructType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * A {@link PartitionReader} that reads multiple sorted files and merges them into a single sorted + * stream using a k-way heap merge ({@link SortedMerge}). + * + * <p>This reader is used when {@code preserve-data-ordering} is enabled and the task group contains + * multiple files that all have the same sort order. + * + * <p>Sort key columns absent from the requested projection are temporarily added to the read schema + * so that {@link SortOrderComparators} can access them during the merge. The extra columns are + * stripped from each row before it is returned to Spark. + */ +class MergingSortedRowDataReader implements PartitionReader<InternalRow> { + private static final Logger LOG = LoggerFactory.getLogger(MergingSortedRowDataReader.class); + + private final CloseableGroup resources; + private final CloseableIterator<InternalRow> mergedIterator; + private final List<RowDataReader> fileReaders; + // non-null only when sort key columns were added to the read schema beyond what Spark projected + private final int[] outputPositions; + private final DataType[] outputDataTypes; + private final Object[] outputValues; // reused per row to avoid per-row allocation + private InternalRow current; + + MergingSortedRowDataReader(SparkInputPartition partition) { + Table table = partition.table(); + ScanTaskGroup<FileScanTask> taskGroup = partition.taskGroup(); + Schema projection = partition.projection(); + SortOrder sortOrder = table.sortOrder(); + + Preconditions.checkState( + sortOrder.isSorted(), "Cannot create merging reader for unsorted table %s", table.name()); + Preconditions.checkState( + taskGroup.tasks().size() > 1, Review Comment: nit: this only needs to be called once. -- 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]
