ahmedabu98 commented on code in PR #33504: URL: https://github.com/apache/beam/pull/33504#discussion_r2005261992
########## sdks/java/io/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/ReadUtils.java: ########## @@ -0,0 +1,192 @@ +/* + * 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.beam.sdk.io.iceberg; + +import static org.apache.iceberg.util.SnapshotUtil.ancestorsOf; + +import java.util.Collection; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.function.BiFunction; +import java.util.stream.Collectors; +import org.apache.beam.sdk.io.iceberg.IcebergIO.ReadRows.StartingStrategy; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.MoreObjects; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Lists; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Sets; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.data.IdentityPartitionConverters; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.encryption.EncryptedFiles; +import org.apache.iceberg.encryption.EncryptedInputFile; +import org.apache.iceberg.hadoop.HadoopInputFile; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.mapping.NameMappingParser; +import org.apache.iceberg.parquet.ParquetReader; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.util.PartitionUtil; +import org.apache.iceberg.util.SnapshotUtil; +import org.apache.parquet.HadoopReadOptions; +import org.apache.parquet.ParquetReadOptions; +import org.checkerframework.checker.nullness.qual.Nullable; + +/** Helper class for source operations. */ +public class ReadUtils { + // default is 8MB. keep this low to avoid overwhelming memory + static final int MAX_FILE_BUFFER_SIZE = 1 << 18; // 256KB + private static final Collection<String> READ_PROPERTIES_TO_REMOVE = + Sets.newHashSet( + "parquet.read.filter", + "parquet.private.read.filter.predicate", + "parquet.read.support.class", + "parquet.crypto.factory.class"); + + static ParquetReader<Record> createReader(FileScanTask task, Table table) { Review Comment: Yep would be a good optimization, will add a TODO Although maybe not a big priority. Looking at the profiler, the extra conversion step seems insignificant -- 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: github-unsubscr...@beam.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
