lokeshj1703 commented on code in PR #13526: URL: https://github.com/apache/hudi/pull/13526#discussion_r2218396954
########## hudi-common/src/main/java/org/apache/hudi/Comparables.java: ########## @@ -0,0 +1,103 @@ +/* + * 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; + +import org.apache.hudi.common.util.ValidationUtils; + +import java.io.Serializable; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Objects; +import java.util.function.Function; +import java.util.stream.Collectors; + +import static org.apache.hudi.common.model.HoodieRecord.DEFAULT_ORDERING_VALUE; + +public class Comparables implements Comparable, Serializable { + protected static final long serialVersionUID = 1L; + + private final List<Comparable> comparables; Review Comment: I have added an optimisation to use singleton list when size is 1. This is kind of a mid way solution between list and maintaining a separate singleton element. It will be easier to maintain. Although the memory utilisation is a bit higher compared to a singleton element but much lower compared to maintaining a list. Please let me know what you think. ########## hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieWriteConfig.java: ########## @@ -1360,8 +1362,13 @@ public HoodieTableType getTableType() { HoodieTableConfig.TYPE, HoodieTableConfig.TYPE.defaultValue().name()).toUpperCase()); } - public String getPreCombineField() { - return getString(PRECOMBINE_FIELD_NAME); + public List<String> getPreCombineField() { Review Comment: Addressed ########## hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieDatasetBulkInsertHelper.scala: ########## @@ -213,12 +213,12 @@ object HoodieDatasetBulkInsertHelper }), SQLConf.get).toJavaRDD()) } - private def dedupeRows(rdd: RDD[InternalRow], schema: StructType, preCombineFieldRef: String, isGlobalIndex: Boolean, targetParallelism: Int): RDD[InternalRow] = { + private def dedupeRows(rdd: RDD[InternalRow], schema: StructType, preCombineFields: List[String], isGlobalIndex: Boolean, targetParallelism: Int): RDD[InternalRow] = { val recordKeyMetaFieldOrd = schema.fieldIndex(HoodieRecord.RECORD_KEY_METADATA_FIELD) val partitionPathMetaFieldOrd = schema.fieldIndex(HoodieRecord.PARTITION_PATH_METADATA_FIELD) // NOTE: Pre-combine field could be a nested field - val preCombineFieldPath = composeNestedFieldPath(schema, preCombineFieldRef) - .getOrElse(throw new HoodieException(s"Pre-combine field $preCombineFieldRef is missing in $schema")) + val preCombineFieldPaths = preCombineFields.map(preCombineField => composeNestedFieldPath(schema, preCombineField) + .getOrElse(throw new HoodieException(s"Pre-combine field $preCombineFields is missing in $schema"))) Review Comment: Addressed -- 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]
