aokolnychyi commented on a change in pull request #2945: URL: https://github.com/apache/iceberg/pull/2945#discussion_r685458640
########## File path: core/src/main/java/org/apache/iceberg/io/ClusteredWriter.java ########## @@ -0,0 +1,117 @@ +/* + * 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.Comparator; +import java.util.Set; +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.Sets; +import org.apache.iceberg.types.Comparators; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.StructLikeSet; + +/** + * A writer capable of writing to multiple specs and partitions ensuring the incoming records are properly clustered. + */ +public abstract class ClusteredWriter<T, R> implements PartitionAwareWriter<T, R> { + + private final Set<Integer> completedSpecs = Sets.newHashSet(); + + private PartitionSpec currentSpec = null; + private Comparator<StructLike> partitionComparator = null; + private Set<StructLike> completedPartitions = null; + private StructLike currentPartition = null; + private Writer<T, R> currentWriter = null; + + private boolean closed = false; + + protected abstract Writer<T, R> newWriter(PartitionSpec spec, StructLike partition); + + protected abstract void add(R result); + + protected abstract R aggregatedResult(); + + @Override + public void write(T row, PartitionSpec spec, StructLike partition) throws IOException { + if (!spec.equals(currentSpec)) { + if (currentSpec != null) { + closeCurrent(); + completedSpecs.add(currentSpec.specId()); + completedPartitions.clear(); + } + + if (completedSpecs.contains(spec.specId())) { + throw new IllegalStateException("Already closed files for spec: " + spec.specId()); + } + + Types.StructType partitionType = spec.partitionType(); + + currentSpec = spec; + partitionComparator = Comparators.forType(partitionType); + completedPartitions = StructLikeSet.create(partitionType); Review comment: Using `PartitionKey` is not even an option. For delete files, the partition struct will come from a metadata column, not by applying `PartitionKey` on data. It seems `StructLikeSet` is a nice solution and since we are not calling it for every single row, it should not be much more expensive. -- 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]
