satishkotha commented on a change in pull request #2263: URL: https://github.com/apache/hudi/pull/2263#discussion_r532815506
########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/cluster/strategy/RunClusteringStrategy.java ########## @@ -0,0 +1,67 @@ +/* + * 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.avro.Schema; +import org.apache.hudi.client.common.HoodieEngineContext; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; + +import java.io.Serializable; +import java.util.Map; + +/** + * Pluggable implementation for writing data into new file groups based on ClusteringPlan. + */ +public abstract class RunClusteringStrategy<T extends HoodieRecordPayload,I,K,O> implements Serializable { + private static final Logger LOG = LogManager.getLogger(RunClusteringStrategy.class); + + private final HoodieTable<T,I,K,O> hoodieTable; + private final HoodieEngineContext engineContext; + private final HoodieWriteConfig writeConfig; + + public RunClusteringStrategy(HoodieTable table, HoodieEngineContext engineContext, HoodieWriteConfig writeConfig) { + this.writeConfig = writeConfig; + this.hoodieTable = table; + this.engineContext = engineContext; + } + + /** + * Run clustering to write inputRecords into new files as defined by rules in strategy parameters. The number of new + * file groups created is bounded by numOutputGroups. + * Note that commit is not done as part of strategy. commit is callers responsibility. + */ + public abstract O performClustering(final I inputRecords, final int numOutputGroups, final String instantTime, Review comment: This is "readerSchema" for all inputRecords being clustered. This is useful to read values for specified sort columns from inputRecords. Let me know if theres a better way to do this. ---------------------------------------------------------------- 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]
