stevenzwu commented on a change in pull request #3866: URL: https://github.com/apache/iceberg/pull/3866#discussion_r799921247
########## File path: flink/v1.14/flink/src/main/java/org/apache/iceberg/flink/source/reader/RowDataRecordFactory.java ########## @@ -0,0 +1,57 @@ +/* + * 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 org.apache.flink.api.common.typeutils.TypeSerializer; +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.runtime.typeutils.InternalSerializers; +import org.apache.flink.table.types.logical.RowType; +import org.apache.iceberg.flink.data.RowDataUtil; + +class RowDataRecordFactory implements RecordFactory<RowData> { + private final RowType rowType; + private final TypeSerializer[] fieldSerializers; + + RowDataRecordFactory(final RowType rowType) { + this.rowType = rowType; + this.fieldSerializers = createFieldSerializers(rowType); + } + + static TypeSerializer[] createFieldSerializers(RowType rowType) { + return rowType.getChildren().stream() + .map(InternalSerializers::create) + .toArray(TypeSerializer[]::new); + } + + @Override + public RowData[] createBatch(int batchSize) { + RowData[] arr = new RowData[batchSize]; + for (int i = 0; i < batchSize; ++i) { + arr[i] = new GenericRowData(rowType.getFieldCount()); + } + return arr; + } + + @Override + public void clone(RowData from, RowData to) { Review comment: I adopted this API. The reason I had the RecordFactory interface is to work with both RowData and Avro GenericRecord iterator. Both Netflix and Apple uses Avro GenericRecord. For the DataIterator with Avro GenericRecord, the iterator returns non-reused/fresh object for every record. In the Avro case, the clone impl can directly set the `from` object into the `toBatch` array. -- 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]
