[ https://issues.apache.org/jira/browse/HUDI-1104?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17375758#comment-17375758 ]
ASF GitHub Bot commented on HUDI-1104: -------------------------------------- nsivabalan commented on a change in pull request #3149: URL: https://github.com/apache/hudi/pull/3149#discussion_r664612327 ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/RDDPartitionSortPartitionerWithRows.java ########## @@ -0,0 +1,73 @@ +/* + * 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.execution.bulkinsert; + +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.table.BulkInsertPartitioner; + +import org.apache.spark.api.java.function.MapPartitionsFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.analysis.SimpleAnalyzer$; +import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder; +import org.apache.spark.sql.catalyst.encoders.RowEncoder; +import org.apache.spark.sql.catalyst.expressions.Attribute; +import org.apache.spark.sql.types.StructType; + +import java.util.ArrayList; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.stream.Collectors; + +import scala.collection.JavaConversions; +import scala.collection.JavaConverters; + +/** + * A built-in partitioner that does local sorting for each spark partitions after coalesce for bulk insert operation, corresponding to the {@code BulkInsertSortMode.PARTITION_SORT} mode. + */ +public class RDDPartitionSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> { + + @Override + public Dataset<Row> repartitionRecords(Dataset<Row> rows, int outputSparkPartitions) { + ExpressionEncoder encoder = getEncoder(rows.schema()); + return rows.coalesce(outputSparkPartitions).mapPartitions((MapPartitionsFunction<Row, Row>) input -> { + // Sort locally in partition Review comment: good suggestion. will fix it. my bad to overlook. Inspired from existing RDDPartitionSortPartitioner in write client path. may be we should revisit that in a follow up PR as well. -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org > Bulk insert Dataset - UserDefinedPartitioner > -------------------------------------------- > > Key: HUDI-1104 > URL: https://issues.apache.org/jira/browse/HUDI-1104 > Project: Apache Hudi > Issue Type: Sub-task > Components: Writer Core > Reporter: sivabalan narayanan > Assignee: sivabalan narayanan > Priority: Blocker > Labels: pull-request-available > Fix For: 0.9.0 > > -- This message was sent by Atlassian Jira (v8.3.4#803005)