rdblue commented on code in PR #11904: URL: https://github.com/apache/iceberg/pull/11904#discussion_r1906095465
########## parquet/src/main/java/org/apache/iceberg/data/parquet/InternalReader.java: ########## @@ -0,0 +1,207 @@ +/* + * 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.parquet; + +import java.util.List; +import java.util.Map; +import java.util.Optional; +import org.apache.iceberg.Schema; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.data.GenericRecord; +import org.apache.iceberg.parquet.ParquetValueReader; +import org.apache.iceberg.parquet.ParquetValueReaders; +import org.apache.iceberg.parquet.ParquetValueReaders.StructReader; +import org.apache.iceberg.types.Types.StructType; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.schema.LogicalTypeAnnotation; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.PrimitiveType; +import org.apache.parquet.schema.Type; + +public class InternalReader extends BaseParquetReaders<StructLike> { + + private static final InternalReader INSTANCE = new InternalReader(); + + private InternalReader() {} + + public static ParquetValueReader<StructLike> buildReader( + Schema expectedSchema, MessageType fileSchema) { + return INSTANCE.createReader(expectedSchema, fileSchema); + } + + public static ParquetValueReader<StructLike> buildReader( + Schema expectedSchema, MessageType fileSchema, Map<Integer, ?> idToConstant) { + return INSTANCE.createReader(expectedSchema, fileSchema, idToConstant); + } + + @Override + protected ParquetValueReader<StructLike> createStructReader( + List<Type> types, List<ParquetValueReader<?>> fieldReaders, StructType structType) { + return new ParquetStructReader(types, fieldReaders, structType); + } + + @Override + protected LogicalTypeAnnotation.LogicalTypeAnnotationVisitor<ParquetValueReader<?>> + logicalTypeReaderVisitor( + ColumnDescriptor desc, + org.apache.iceberg.types.Type.PrimitiveType expected, + PrimitiveType primitive) { + return new LogicalTypeAnnotationParquetValueReaderVisitor(desc, expected, primitive); + } + + @Override + protected ParquetValueReaders.PrimitiveReader<?> fixedReader(ColumnDescriptor desc) { + return new ParquetValueReaders.BytesReader(desc); + } + + @Override + protected ParquetValueReaders.PrimitiveReader<?> int96Reader(ColumnDescriptor desc) { + // normal handling as int96 + return new ParquetValueReaders.UnboxedReader<>(desc); Review Comment: This isn't correct. The unboxed reader will return a `Binary` for int96 columns. Instead, this needs to use the same logic as the Spark reader (which also uses the internal representation): ```java private static class TimestampInt96Reader extends UnboxedReader<Long> { TimestampInt96Reader(ColumnDescriptor desc) { super(desc); } @Override public Long read(Long ignored) { return readLong(); } @Override public long readLong() { final ByteBuffer byteBuffer = column.nextBinary().toByteBuffer().order(ByteOrder.LITTLE_ENDIAN); return ParquetUtil.extractTimestampInt96(byteBuffer); } } ``` You can move that class into the `parquet` package to share it. -- 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
