nastra commented on code in PR #16958: URL: https://github.com/apache/iceberg/pull/16958#discussion_r3664408203
########## core/src/test/java/org/apache/iceberg/TestV4ManifestReader.java: ########## @@ -0,0 +1,820 @@ +/* + * 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; + +import static org.apache.iceberg.types.Types.NestedField.optional; +import static org.assertj.core.api.Assertions.assertThat; +import static org.assertj.core.api.Assertions.assertThatThrownBy; + +import java.io.IOException; +import java.nio.ByteBuffer; +import java.nio.file.Path; +import java.util.Collection; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.function.Consumer; +import java.util.stream.Stream; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.inmemory.InMemoryOutputFile; +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.metrics.DefaultMetricsContext; +import org.apache.iceberg.metrics.ScanMetrics; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.transforms.Transforms; +import org.apache.iceberg.types.Comparators; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.types.Types; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.io.TempDir; +import org.junit.jupiter.params.ParameterizedTest; +import org.junit.jupiter.params.provider.Arguments; +import org.junit.jupiter.params.provider.FieldSource; +import org.junit.jupiter.params.provider.MethodSource; + +public class TestV4ManifestReader { + private static final long SNAPSHOT_ID = 42L; + private static final int FORMAT_VERSION_V4 = 4; + private static final long RECORD_COUNT = 100L; + private static final long FILE_SIZE_IN_BYTES = 1024L; + private static final DeletionVector DV = + DeletionVectorStruct.builder() + .location("s3://bucket/dv.puffin") + .offset(100L) + .sizeInBytes(50L) + .cardinality(5L) + .build(); + + private static final Schema TABLE_SCHEMA = + new Schema( + optional(1, "id", Types.IntegerType.get()), optional(2, "data", Types.StringType.get())); + private static final PartitionSpec ID_PARTITIONING = + PartitionSpec.builderFor(TABLE_SCHEMA).identity("id").build(); + private static final Types.StructType PARTITION_TYPE = ID_PARTITIONING.partitionType(); + private static final Types.StructType EMPTY_PARTITION = Types.StructType.of(); + private static final PartitionData EMPTY_PARTITION_DATA = new PartitionData(EMPTY_PARTITION); + private static final Map<Integer, PartitionSpec> PARTITIONED_SPECS = + ImmutableMap.of(ID_PARTITIONING.specId(), ID_PARTITIONING); + private static final Map<Integer, PartitionSpec> UNPARTITIONED_SPECS = + ImmutableMap.of(PartitionSpec.unpartitioned().specId(), PartitionSpec.unpartitioned()); + + private static final List<FileFormat> FORMATS = + ImmutableList.of(FileFormat.AVRO, FileFormat.PARQUET); + + // a data file whose tracking carries every inheritable and change-tracking value set + private static final TrackedFile FILE_WITH_FULL_TRACKING = + new TrackedFileStruct( + new TrackingStruct( + EntryStatus.ADDED, + SNAPSHOT_ID, + 5L, // data sequence number + 6L, // file sequence number + 7L, // dv snapshot id + 8L, // first row id + new byte[] {1, 2}, // deleted positions + new byte[] {3, 4}), // replaced positions + FileContent.DATA, + FORMAT_VERSION_V4, + "s3://bucket/file.parquet", + FileFormat.PARQUET, + RECORD_COUNT, + FILE_SIZE_IN_BYTES, + 0, + EMPTY_PARTITION_DATA, + null, + null, + null, + null, + null, + null, + null); + + // shared data files: FILE_A is in partition id=1, FILE_B in partition id=2 + private static final TrackedFile FILE_A = dataFile("data-a.parquet", partition(1)); + private static final TrackedFile FILE_B = dataFile("data-b.parquet", partition(2)); + private static final TrackedFile EQ_DELETES_A = deleteFile("eq-deletes-a.parquet", partition(1)); + private static final TrackedFile EQ_DELETES_B = deleteFile("eq-deletes-b.parquet", partition(2)); + private static final TrackedFile DATA_MANIFEST_REF = + manifestRef(FileContent.DATA_MANIFEST, "data-leaf.parquet"); + private static final TrackedFile DELETE_MANIFEST_REF = + manifestRef(FileContent.DELETE_MANIFEST, "delete-leaf.parquet"); + + @TempDir private Path tempDir; + + private final FileIO fileIO = new TestTables.LocalFileIO(); + + @ParameterizedTest + @FieldSource("FORMATS") + public void testReadsWrittenFile(FileFormat format) throws IOException { + TrackedFile file = + new TrackedFileStruct( + addedTracking(), + FileContent.DATA, + FORMAT_VERSION_V4, + "s3://bucket/data/file.parquet", + FileFormat.PARQUET, + RECORD_COUNT, + FILE_SIZE_IN_BYTES, + ID_PARTITIONING.specId(), + partition(7), + null, + 1, // sort order id + DV, + null, + ByteBuffer.wrap(new byte[] {1, 2, 3}), + ImmutableList.of(50L, 100L), + null); + + InputFile manifest = writeManifest(format, PARTITION_TYPE, ImmutableList.of(file)); + + TrackedFile actual = Iterables.getOnlyElement(read(manifest, PARTITIONED_SPECS)); + + // compare with tracking reduced to status: the reader fills status-independent tracking + // fields (row position, sequence numbers via inheritance) that the written file does not have + Types.StructType comparisonType = + TypeUtil.replaceFieldTypes( + TrackedFile.schema(PARTITION_TYPE, Types.StructType.of()), + ImmutableMap.of( + TrackedFile.TRACKING.fieldId(), Types.StructType.of(Tracking.STATUS))) + .asStruct(); + assertThat((StructLike) actual) + .usingComparator(Comparators.forType(comparisonType)) + .isEqualTo((StructLike) file); Review Comment: nit: unnecessary cast -- 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]
