kbendick commented on a change in pull request #1572: URL: https://github.com/apache/iceberg/pull/1572#discussion_r503507114
########## File path: parquet/src/main/java/org/apache/iceberg/parquet/ReusableMapData.java ########## @@ -0,0 +1,72 @@ +/* + * 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.parquet; + +import java.util.Map; + +public interface ReusableMapData { + ReusableArrayData keys(); + ReusableArrayData values(); + + default void grow() { + keys().grow(); + values().grow(); + } + + default int capacity() { + return keys().capacity(); + } + + default void setNumElements(int numElements) { + keys().setNumElements(numElements); + values().setNumElements(numElements); + } + + int size(); + + @SuppressWarnings("unchecked") + default <K, V> Map.Entry<K, V> getRaw( + int pos, + ParquetValueReaders.ReusableEntry<K, V> reuse, + ParquetValueReaders.ReusableEntry<K, V> def) { + if (pos < capacity()) { + reuse.set((K) keys().getObj(pos), (V) values().getObj(pos)); + return reuse; + } + return def; + } + + default void addPair(Object key, Object value) { + if (size() >= capacity()) { + grow(); + } + keys().update(size(), key); + values().update(size(), value); + setNumElements(size() + 1); Review comment: I might be misinterpreting your question / concern, but it seems like at least in the `SparkReusableMapData` this is the case. If I'm reading this correctly, addPair is overwritten and then `setNumElements` is only called on `buildMap`. Again, I might be misinterpreting the question / concern but for a default implementation this seems fine given that it seems to be overridden on the Spark side and on the Flink side too (where theres a `buildMap` function). ```java private static class MapReader<K, V> extends RepeatedKeyValueReader<MapData, SparkReusableMapData, K, V> { // Removed to the bare minimum .... @Override protected void addPair(SparkReusableMapData map, K key, V value) { if (writePos >= map.capacity()) { map.grow(); } map.keys.values[writePos] = key; map.values.values[writePos] = value; writePos += 1; } @Override protected MapData buildMap(SparkReusableMapData map) { map.setNumElements(writePos); return map; } ``` ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
