kengtin commented on code in PR #7161: URL: https://github.com/apache/iceberg/pull/7161#discussion_r1159010720
########## flink/v1.16/flink/src/main/java/org/apache/iceberg/flink/sink/BucketPartitioner.java: ########## @@ -0,0 +1,86 @@ +/* + * 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.sink; + +import java.util.Optional; +import org.apache.flink.api.common.functions.Partitioner; +import org.apache.iceberg.PartitionField; +import org.apache.iceberg.PartitionSpec; + +/** + * This partitioner will redirect elements to writers deterministically so that each writer only + * targets 1 bucket. If the number of writers > number of buckets each partitioner will keep a state + * of multiple writers per bucket as evenly as possible, and will round-robin the requests across + * them. + */ +public class BucketPartitioner implements Partitioner<Integer> { + + private final Integer maxBuckets; + + private final int[] currentWriterOffset; + + BucketPartitioner(PartitionSpec partitionSpec) { + // The current implementation redirects to writers based on the _FIRST_ bucket found + Optional<PartitionField> bucket = + partitionSpec.fields().stream() + .filter(f -> f.transform().dedupName().contains("bucket")) + .findFirst(); + + if (!bucket.isPresent()) { Review Comment: OK, we can fail here in case this partitioner is accessed directly. And have the `FlinkSink.distributeDataStream` only use this strategy if only 1 bucket is defined in the partition spec. -- 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
