nssalian commented on code in PR #17520: URL: https://github.com/apache/iceberg/pull/17520#discussion_r3739668618
########## data/src/test/java/org/apache/iceberg/data/TestRecordVariantShreddingAnalyzer.java: ########## @@ -0,0 +1,559 @@ +/* + * 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.assertj.core.api.Assertions.assertThat; +import static org.assertj.core.api.Assertions.assertThatThrownBy; + +import java.io.IOException; +import java.util.List; +import java.util.Map; +import org.apache.hadoop.fs.Path; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Files; +import org.apache.iceberg.InternalTestHelpers; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.TestTables; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.encryption.EncryptedFiles; +import org.apache.iceberg.encryption.EncryptedOutputFile; +import org.apache.iceberg.formats.FileWriterBuilder; +import org.apache.iceberg.formats.FormatModelRegistry; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.DataWriter; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.io.OutputFileFactory; +import org.apache.iceberg.parquet.Parquet; +import org.apache.iceberg.parquet.ParquetFileTestUtils; +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.Lists; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.variants.Variant; +import org.apache.iceberg.variants.VariantTestUtil; +import org.apache.iceberg.variants.Variants; +import org.apache.parquet.example.data.Group; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.hadoop.example.GroupReadSupport; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.io.TempDir; + +public class TestRecordVariantShreddingAnalyzer { + + private static final Schema VARIANT_AFTER_ID_SCHEMA = + new Schema( + Types.NestedField.required(1, "id", Types.LongType.get()), + Types.NestedField.optional(2, "v", Types.VariantType.get())); + + private static final Schema VARIANT_BEFORE_ID_SCHEMA = + new Schema( + Types.NestedField.optional(1, "v", Types.VariantType.get()), + Types.NestedField.required(2, "id", Types.LongType.get())); + + private static final Schema MULTI_VARIANT_SCHEMA = + new Schema( + Types.NestedField.required(1, "id", Types.LongType.get()), + Types.NestedField.optional(2, "v1", Types.VariantType.get()), + Types.NestedField.optional(3, "other", Types.StringType.get()), + Types.NestedField.optional(4, "v2", Types.VariantType.get())); + + // Engine schema whose variant column is named "w" instead of "v", so the "v" column resolved + // from the Iceberg schema is not found and shredding does not activate. + private static final Schema MISMATCHED_ENGINE_SCHEMA = + new Schema( + Types.NestedField.required(1, "id", Types.LongType.get()), + Types.NestedField.optional(2, "w", Types.VariantType.get())); + + private static final int VARIANT_FIELD_ID = 2; + private static final int VARIANT_FIRST_FIELD_ID = 1; + private static final int FIRST_MULTI_VARIANT_FIELD_ID = 2; + private static final int SECOND_MULTI_VARIANT_FIELD_ID = 4; + private static final String BUFFER_SIZE = "2"; + + private Variant variant; + private List<Record> records; + + @TempDir private java.nio.file.Path temp; + + @BeforeEach + public void before() { + variant = + VariantTestUtil.variant( + ImmutableMap.of( + "a", Variants.of(42), + "b", Variants.of("hello"))); + + GenericRecord record = GenericRecord.create(VARIANT_AFTER_ID_SCHEMA); + records = + ImmutableList.of( + record.copy(ImmutableMap.of("id", 1L, "v", variant)), + record.copy(ImmutableMap.of("id", 2L, "v", variant)), + record.copy(ImmutableMap.of("id", 3L, "v", variant))); + } + + @Test + public void testAnalyzeVariantColumnsUsesIcebergColumnOrder() { + RecordVariantShreddingAnalyzer analyzer = new RecordVariantShreddingAnalyzer(); + + Map<Integer, Type> shreddedTypes = + analyzer.analyzeVariantColumns(records, VARIANT_AFTER_ID_SCHEMA, VARIANT_AFTER_ID_SCHEMA); + + assertThat(shreddedTypes).containsOnlyKeys(VARIANT_FIELD_ID); + GroupType typedValue = shreddedTypes.get(VARIANT_FIELD_ID).asGroupType(); + assertThat(typedValue.getName()).isEqualTo("typed_value"); + assertThat(typedValue.containsField("a")).isTrue(); + assertThat(typedValue.containsField("b")).isTrue(); + } + + @Test + public void testAnalyzeVariantColumnsWhenVariantIsFirstColumn() { + GenericRecord record = GenericRecord.create(VARIANT_BEFORE_ID_SCHEMA); + List<Record> variantFirstRecords = + ImmutableList.of( + record.copy(ImmutableMap.of("v", variant, "id", 1L)), + record.copy(ImmutableMap.of("v", variant, "id", 2L))); + + RecordVariantShreddingAnalyzer analyzer = new RecordVariantShreddingAnalyzer(); + Map<Integer, Type> shreddedTypes = + analyzer.analyzeVariantColumns( + variantFirstRecords, VARIANT_BEFORE_ID_SCHEMA, VARIANT_BEFORE_ID_SCHEMA); Review Comment: Added tests for both a swapped single variant and two swapped variant columns -- 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]
