openinx commented on a change in pull request #2945: URL: https://github.com/apache/iceberg/pull/2945#discussion_r700177068
########## File path: core/src/main/java/org/apache/iceberg/io/FanoutFileWriter.java ########## @@ -0,0 +1,107 @@ +/* + * 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.io; + +import java.io.IOException; +import java.util.Map; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.StructLikeMap; + +/** + * A writer capable of writing to multiple specs and partitions that keeps files for each + * seen spec/partition pair open until this writer is closed. + * <p> + * As opposed to {@link ClusteredFileWriter}, this writer does not requite the incoming records + * to be clustered by partition spec and partition. The downside is potentially larger memory + * consumption. + */ +abstract class FanoutFileWriter<T, R> implements PartitionAwareFileWriter<T, R> { + + private final Map<Integer, Map<StructLike, FileWriter<T, R>>> writers = Maps.newHashMap(); + private boolean closed = false; + + protected abstract FileWriter<T, R> newWriter(PartitionSpec spec, StructLike partition); + + protected abstract void addResult(R result); + + protected abstract R aggregatedResult(); + + public CharSequence currentPath(PartitionSpec spec, StructLike partition) { + return ((RollingFileWriter<?, ?, ?>) writer(spec, partition)).currentPath(); + } + + public long currentPosition(PartitionSpec spec, StructLike partition) { + return ((RollingFileWriter<?, ?, ?>) writer(spec, partition)).currentRows(); + } + + @Override + public void write(T row, PartitionSpec spec, StructLike partition) throws IOException { + FileWriter<T, R> writer = writer(spec, partition); + writer.write(row); + } + + private FileWriter<T, R> writer(PartitionSpec spec, StructLike partition) { + Map<StructLike, FileWriter<T, R>> specWriters = writers.computeIfAbsent( + spec.specId(), + id -> StructLikeMap.create(spec.partitionType())); + FileWriter<T, R> writer = specWriters.get(partition); + + if (writer == null) { + // copy the partition key as the key object is reused + StructLike copiedPartition = partition != null ? StructCopy.copy(partition) : null; + writer = newWriter(spec, copiedPartition); + specWriters.put(copiedPartition, writer); + } + + return writer; + } Review comment: Could we maintain those writers from different partition spec and different partition into a flatten Map<K, FileWriter<T,R>> rather than a nested Map, by using a composited key <partitionSpecId, partitionData> . I think that will make the writer choose strategy quite simple, it will also simplify the ClusteredFileWriter's write method. -- 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]
