deniskuzZ commented on code in PR #11216: URL: https://github.com/apache/iceberg/pull/11216#discussion_r1907057882
########## data/src/main/java/org/apache/iceberg/data/PartitionStatsHandler.java: ########## @@ -0,0 +1,332 @@ +/* + * 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.data; + +import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT; +import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT; + +import java.io.Closeable; +import java.io.IOException; +import java.io.UncheckedIOException; +import java.util.Collection; +import java.util.Iterator; +import java.util.List; +import java.util.Locale; +import java.util.function.BiFunction; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.ImmutableGenericPartitionStatisticsFile; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.PartitionStatisticsFile; +import org.apache.iceberg.PartitionStats; +import org.apache.iceberg.PartitionStatsUtil; +import org.apache.iceberg.Partitioning; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.Table; +import org.apache.iceberg.avro.Avro; +import org.apache.iceberg.data.avro.DataReader; +import org.apache.iceberg.data.orc.GenericOrcReader; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.encryption.EncryptedFiles; +import org.apache.iceberg.encryption.EncryptionKeyMetadata; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.DataWriter; +import org.apache.iceberg.io.FileWriterFactory; +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.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.types.Types.IntegerType; +import org.apache.iceberg.types.Types.LongType; +import org.apache.iceberg.types.Types.NestedField; +import org.apache.iceberg.types.Types.StructType; +import org.apache.iceberg.util.SnapshotUtil; + +/** + * Computes, writes and reads the {@link PartitionStatisticsFile}. Uses generic readers and writers + * to support writing and reading of the stats in table default format. + */ +public final class PartitionStatsHandler { + + private PartitionStatsHandler() {} + + public enum Column { + PARTITION(0), + SPEC_ID(1), + DATA_RECORD_COUNT(2), + DATA_FILE_COUNT(3), + TOTAL_DATA_FILE_SIZE_IN_BYTES(4), + POSITION_DELETE_RECORD_COUNT(5), + POSITION_DELETE_FILE_COUNT(6), + EQUALITY_DELETE_RECORD_COUNT(7), + EQUALITY_DELETE_FILE_COUNT(8), + TOTAL_RECORD_COUNT(9), + LAST_UPDATED_AT(10), + LAST_UPDATED_SNAPSHOT_ID(11); + + private final int id; + + Column(int id) { + this.id = id; + } + + public int id() { + return id; + } + } + + /** + * Generates the partition stats file schema based on a given partition type. + * + * <p>Note: Provide the unified partition schema type as mentioned in the spec. + * + * @param partitionType unified partition schema type. + * @return a schema that corresponds to the provided unified partition type. + */ + public static Schema schema(StructType partitionType) { + Preconditions.checkState(!partitionType.fields().isEmpty(), "table must be partitioned"); + + return new Schema( + NestedField.required(1, Column.PARTITION.name(), partitionType), + NestedField.required(2, Column.SPEC_ID.name(), IntegerType.get()), + NestedField.required(3, Column.DATA_RECORD_COUNT.name(), LongType.get()), + NestedField.required(4, Column.DATA_FILE_COUNT.name(), IntegerType.get()), + NestedField.required(5, Column.TOTAL_DATA_FILE_SIZE_IN_BYTES.name(), LongType.get()), + NestedField.optional(6, Column.POSITION_DELETE_RECORD_COUNT.name(), LongType.get()), + NestedField.optional(7, Column.POSITION_DELETE_FILE_COUNT.name(), IntegerType.get()), + NestedField.optional(8, Column.EQUALITY_DELETE_RECORD_COUNT.name(), LongType.get()), + NestedField.optional(9, Column.EQUALITY_DELETE_FILE_COUNT.name(), IntegerType.get()), + NestedField.optional(10, Column.TOTAL_RECORD_COUNT.name(), LongType.get()), + NestedField.optional(11, Column.LAST_UPDATED_AT.name(), LongType.get()), + NestedField.optional(12, Column.LAST_UPDATED_SNAPSHOT_ID.name(), LongType.get())); + } + + /** + * Computes and writes the {@link PartitionStatisticsFile} for a given table's current snapshot. + * + * @param table The {@link Table} for which the partition statistics is computed. + * @return {@link PartitionStatisticsFile} for the current snapshot. + */ + public static PartitionStatisticsFile computeAndWriteStatsFile(Table table) { + return computeAndWriteStatsFile(table, null); + } + + /** + * Computes and writes the {@link PartitionStatisticsFile} for a given table and branch. + * + * @param table The {@link Table} for which the partition statistics is computed. + * @param branch A branch information to select the required snapshot. + * @return {@link PartitionStatisticsFile} for the given branch. + */ + public static PartitionStatisticsFile computeAndWriteStatsFile(Table table, String branch) { Review Comment: Wouldn't it be better not to have fat methods with multiple responsibilities? What if we introduce the write method that gets the stats iterator as an argument. We might not need to execute the complete stats rebuild for all the registered partitions, but only for those that were changed in the current snapshot. Snapshot summary already has a metric for the number of changed partitions, maybe we could extend it with the partition list and re-compute stats only for them. Then generate a new stats file based on the prev snapshot stats with updates to the changed partitions. -- 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
