aokolnychyi commented on code in PR #9841: URL: https://github.com/apache/iceberg/pull/9841#discussion_r1594829408
########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/BatchReadConf.java: ########## @@ -0,0 +1,47 @@ +/* + * 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; + +import java.io.Serializable; + +public class BatchReadConf implements Serializable { Review Comment: After thinking a bit more, I'd consider changing the initial approach that I suggested. How about this? - Define separate `ParquetBatchReadConf` and `OrcBatchReadConf`, so that we can parse them separately. If there is an invalid value for a Parquet property and we are reading ORC, it should not fail the job. We can use Immutables to generate the implementations. See below. ``` @Value.Immutable public interface ParquetBatchReadConf extends Serializable { ParquetReaderType readerType(); int batchSize(); } @Value.Immutable public interface OrcBatchReadConf extends Serializable { int batchSize(); } ``` - Move all the logic to decide which reader to use and whether vectorized reads are supported to `SparkBatch`. ``` @Override public PartitionReaderFactory createReaderFactory() { if (useCometBatchReads()) { return new SparkColumnarReaderFactory(parquetBatchReadConf(ParquetReaderType.COMET)); } else if (useParquetBatchReads()) { return new SparkColumnarReaderFactory(parquetBatchReadConf(ParquetReaderType.ICEBERG)); } else if (useOrcBatchReads()) { return new SparkColumnarReaderFactory(orcBatchReadConf()); } else { return new SparkRowReaderFactory(); } } ``` ``` private boolean useCometBatchReads() { return readConf.parquetVectorizationEnabled() && readConf.parquetReaderType() == ParquetReaderType.COMET && expectedSchema.columns().stream().allMatch(this::supportsCometBatchReads) && taskGroups.stream().allMatch(this::supportsParquetBatchReads); } private boolean supportsCometBatchReads(Types.NestedField field) { return field.type().isPrimitiveType() && !field.type().typeId().equals(Type.TypeID.UUID); } ``` - Only keep `parquetReaderType()` in `SparkConf`. - Have two fields in `BaseBatchReader`. ``` abstract class BaseBatchReader<T extends ScanTask> extends BaseReader<ColumnarBatch, T> { private final ParquetBatchReadConf parquetConf; private final OrcBatchReadConf orcConf; ``` -- 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
