joyhaldar commented on code in PR #17610: URL: https://github.com/apache/iceberg/pull/17610#discussion_r4333912762
########## spark/v4.2/spark/src/test/java/org/apache/iceberg/spark/data/TestSparkVectorizedFormatModel.java: ########## @@ -0,0 +1,142 @@ +/* + * 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.data; + +import static org.assertj.core.api.Assertions.assertThat; + +import java.util.Arrays; +import java.util.Collection; +import java.util.List; +import java.util.Set; +import org.apache.arrow.vector.ValueVector; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Schema; +import org.apache.iceberg.data.DataGenerators; +import org.apache.iceberg.data.ReadFormatModelTests; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.spark.SparkUtil; +import org.apache.iceberg.spark.data.vectorized.IcebergArrowColumnVector; +import org.apache.iceberg.types.Type; +import org.apache.spark.sql.vectorized.ColumnarBatch; +import org.junit.jupiter.params.provider.Arguments; + +class TestSparkVectorizedFormatModel extends ReadFormatModelTests<ColumnarBatch> { + + private static final FileFormat[] FILE_FORMATS = {FileFormat.ORC, FileFormat.PARQUET}; + + private static final List<Arguments> FORMAT_AND_GENERATOR = + Arrays.stream(FILE_FORMATS) + .flatMap( + format -> + Arrays.stream(DataGenerators.ALL) + .filter(generator -> supportsGenerator(format, generator)) + .map(generator -> Arguments.of(format, generator))) + .toList(); + + private static final Set<Type.TypeID> UNSUPPORTED_TYPE_IDS = + Set.of( + Type.TypeID.TIME, + Type.TypeID.TIMESTAMP_NANO, + Type.TypeID.STRUCT, + Type.TypeID.LIST, + Type.TypeID.MAP, + Type.TypeID.UUID, + Type.TypeID.GEOMETRY, + Type.TypeID.GEOGRAPHY); + + @Override + protected Collection<Type.TypeID> unsupportedTypeIds() { + return UNSUPPORTED_TYPE_IDS; + } + + @Override + protected boolean supportsBatchReads() { + return true; + } + + @Override + protected int countRows(List<ColumnarBatch> batches) { + return batches.stream().mapToInt(ColumnarBatch::numRows).sum(); + } + + @Override + protected void assertContainersReused(ColumnarBatch first, ColumnarBatch second) { + assertThat(second.numCols()).isEqualTo(first.numCols()); + + for (int i = 0; i < first.numCols(); i++) { + assertThat(arrowVector(second, i)).isSameAs(arrowVector(first, i)); + } + } + + private ValueVector arrowVector(ColumnarBatch batch, int col) { + IcebergArrowColumnVector vector = (IcebergArrowColumnVector) batch.column(col); + return vector.vectorAccessor().getVector(); + } + + @Override + protected void assertContainersNotReused(ColumnarBatch first, ColumnarBatch second) { + assertThat(second.numCols()).isEqualTo(first.numCols()); + + for (int i = 0; i < first.numCols(); i++) { + assertThat(arrowVector(second, i)).isNotSameAs(arrowVector(first, i)); + } + } + + @Override + protected Object engineSchema(Schema schema) { + return SparkSchemaUtil.convert(schema); + } + + @Override + protected Object convertConstantToEngine(Type type, Object value) { + return SparkUtil.internalToSpark(type, value); + } + + @Override + protected Class<ColumnarBatch> engineType() { + return ColumnarBatch.class; + } + + @Override + protected ColumnarBatch convertToEngine(Record record, Schema schema) { + throw new UnsupportedOperationException("Vectorized reads are read-only"); + } + + @Override + protected void assertEquals( + Schema schema, List<ColumnarBatch> expected, List<ColumnarBatch> actual) { + throw new UnsupportedOperationException("Use assertRecordsEqual for batch reads"); + } + + @Override + protected void assertRecordsEqual( Review Comment: You are right. I tested with `recordsPerBatch(2)` and found that collecting all batches before comparing caused failures. When we were doing this, ```java readRecords = ImmutableList.copyOf(reader); ``` the earlier batch data was overwritten when moving to the next batch, and `assertEquals` was failing. I [updated](https://github.com/apache/iceberg/pull/17610/changes/43466103a877e7d232faf2303af6ddc472c05358) `assertRecordsEqual()` to iterate over records or batches and compare with expected records when reading, before moving to the next batch. -- 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]
