lw309637554 commented on a change in pull request #2263: URL: https://github.com/apache/hudi/pull/2263#discussion_r528207858
########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/cluster/strategy/PartitionAwareScheduleClusteringStrategy.java ########## @@ -0,0 +1,108 @@ +/* + * 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.table.action.cluster.strategy; + +import org.apache.hudi.avro.model.HoodieClusteringGroup; +import org.apache.hudi.avro.model.HoodieClusteringPlan; +import org.apache.hudi.avro.model.HoodieClusteringStrategy; +import org.apache.hudi.client.common.HoodieEngineContext; +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.model.FileSlice; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieIOException; +import org.apache.hudi.table.HoodieTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; + +import java.io.IOException; +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.Stream; + +/** + * Scheduling strategy with restriction that clustering groups can only contain files from same partition. + */ +public abstract class PartitionAwareScheduleClusteringStrategy<T extends HoodieRecordPayload,I,K,O> extends ScheduleClusteringStrategy<T,I,K,O> { + private static final Logger LOG = LogManager.getLogger(PartitionAwareScheduleClusteringStrategy.class); + + public PartitionAwareScheduleClusteringStrategy(HoodieTable table, HoodieEngineContext engineContext, HoodieWriteConfig writeConfig) { + super(table, engineContext, writeConfig); + } + + /** + * Create Clustering group based on files eligible for clustering in the partition. + */ + protected abstract Stream<HoodieClusteringGroup> buildClusteringGroupsForPartition(String partitionPath, + List<FileSlice> fileSlices, + long maxDataInGroup); Review comment: The implement of buildClusteringGroupsForPartition method in SparkBoundedDayBasedScheduleClusteringStrategy. Get params about clustering from maxDataInGroup、getWriteConfig().getClusteringTargetFileSize()、getWriteConfig().getClusteringTargetFileSize(). Maybe other implement will need more params . Can we just abstract buildClusteringGroupsForPartition with the HoodieWriteConfig for param ? maybe like : protected abstract Stream<HoodieClusteringGroup> buildClusteringGroupsForPartition(String partitionPath, List<FileSlice> fileSlices, HoodieWriteConfig writeConfig); ---------------------------------------------------------------- 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]
