zoomake commented on code in PR #14087: URL: https://github.com/apache/hudi/pull/14087#discussion_r2467733218
########## hudi-client/hudi-flink-client/src/main/java/org/apache/hudi/client/clustering/plan/strategy/FlinkSkipSingleFileClusteringPlanStrategy.java: ########## @@ -0,0 +1,63 @@ +/* + * 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.hudi.client.clustering.plan.strategy; + +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.model.FileSlice; +import org.apache.hudi.common.model.HoodieBaseFile; +import org.apache.hudi.common.util.StringUtils; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; + +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.Stream; + +/** + * An extension of {@link FlinkSizeBasedClusteringPlanStrategy} that skips clustering + * for partitions containing only one small file. + */ +public class FlinkSkipSingleFileClusteringPlanStrategy<T> + extends FlinkSizeBasedClusteringPlanStrategy<T> { + + public FlinkSkipSingleFileClusteringPlanStrategy(HoodieTable table, + HoodieEngineContext engineContext, + HoodieWriteConfig writeConfig) { + super(table, engineContext, writeConfig); + } + + @Override + protected Stream<FileSlice> getFileSlicesEligibleForClustering(final String partition) { + List<FileSlice> fileSlices = super.getFileSlicesEligibleForClustering(partition) + // Only files that have base file size smaller than small file size are eligible. + .filter(slice -> slice.getBaseFile().map(HoodieBaseFile::getFileSize).orElse(0L) Review Comment: @danny0405 Thanks, Removed the redundant filtering since the parent method already filters small files. -- 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]
