pvary commented on code in PR #10956: URL: https://github.com/apache/iceberg/pull/10956#discussion_r1720898887
########## flink/v1.20/flink/src/main/java/org/apache/iceberg/flink/source/reader/ConverterReaderFunction.java: ########## @@ -0,0 +1,95 @@ +/* + * 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.flink.source.reader; + +import java.util.List; +import org.apache.flink.annotation.Internal; +import org.apache.flink.configuration.ReadableConfig; +import org.apache.iceberg.Schema; +import org.apache.iceberg.encryption.EncryptionManager; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.flink.source.DataIterator; +import org.apache.iceberg.flink.source.RowDataFileScanTaskReader; +import org.apache.iceberg.flink.source.split.IcebergSourceSplit; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; + +@Internal +public class ConverterReaderFunction<T> extends DataIteratorReaderFunction<T> { + private final RowDataConverter<T> converter; + private final Schema tableSchema; + private final Schema readSchema; + private final String nameMapping; + private final boolean caseSensitive; + private final FileIO io; + private final EncryptionManager encryption; + private final List<Expression> filters; + private final long limit; + + private transient RecordLimiter recordLimiter = null; + + public ConverterReaderFunction( + RowDataConverter<T> converter, + ReadableConfig config, + Schema tableSchema, + Schema projectedSchema, + String nameMapping, + boolean caseSensitive, + FileIO io, + EncryptionManager encryption, + List<Expression> filters, + long limit) { + super(new ListDataIteratorBatcher<>(config)); + this.converter = converter; + this.tableSchema = tableSchema; + this.readSchema = readSchema(tableSchema, projectedSchema); + this.nameMapping = nameMapping; + this.caseSensitive = caseSensitive; + this.io = io; + this.encryption = encryption; + this.filters = filters; + this.limit = limit; + } + + @Override + protected DataIterator<T> createDataIterator(IcebergSourceSplit split) { + RowDataFileScanTaskReader rowDataReader = + new RowDataFileScanTaskReader(tableSchema, readSchema, nameMapping, caseSensitive, filters); + return new LimitableDataIterator<>( + new ConverterFileScanTaskReader<>(rowDataReader, converter), Review Comment: Would it worth to add the converter to the reader instead of adding a new wrapper? Getting a bit hard to follow this many embedded readers -- 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
