boneanxs commented on code in PR #5502: URL: https://github.com/apache/hudi/pull/5502#discussion_r881177283
########## hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/CustomColumnsSortPartitionerWithRows.java: ########## @@ -0,0 +1,60 @@ +/* + * 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.config.HoodieWriteConfig; +import org.apache.hudi.table.BulkInsertPartitioner; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; + +import java.util.Arrays; + +/** + * A partitioner that does sorting based on specified column values for each spark partitions. + */ +public class CustomColumnsSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> { + + private final String[] sortColumnNames; + + public CustomColumnsSortPartitionerWithRows(HoodieWriteConfig config) { + this.sortColumnNames = getSortColumnName(config); + } + + public CustomColumnsSortPartitionerWithRows(String[] columnNames) { + this.sortColumnNames = columnNames; + } + + @Override + public Dataset<Row> repartitionRecords(Dataset<Row> records, int outputSparkPartitions) { + final String[] sortColumns = this.sortColumnNames; + return records.coalesce(outputSparkPartitions) Review Comment: Yes, it support null values: ```scala scala> val df1 = Seq(("foo", "test"), ("bar", null), ("foo", "test1"), ("bar", "test")).toDF("k", "v") df1: org.apache.spark.sql.DataFrame = [k: string, v: string] scala> df1.coalesce(1).sortWithinPartitions("k", "v").collect res8: Array[org.apache.spark.sql.Row] = Array([bar,null], [bar,test], [foo,test], [foo,test1]) ``` ########## hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/CustomColumnsSortPartitionerWithRows.java: ########## @@ -0,0 +1,60 @@ +/* + * 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.config.HoodieWriteConfig; +import org.apache.hudi.table.BulkInsertPartitioner; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; + +import java.util.Arrays; + +/** + * A partitioner that does sorting based on specified column values for each spark partitions. + */ +public class CustomColumnsSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> { + + private final String[] sortColumnNames; + + public CustomColumnsSortPartitionerWithRows(HoodieWriteConfig config) { + this.sortColumnNames = getSortColumnName(config); + } + + public CustomColumnsSortPartitionerWithRows(String[] columnNames) { + this.sortColumnNames = columnNames; + } + + @Override + public Dataset<Row> repartitionRecords(Dataset<Row> records, int outputSparkPartitions) { + final String[] sortColumns = this.sortColumnNames; + return records.coalesce(outputSparkPartitions) Review Comment: Yes, it support null values: ```scala scala> val df1 = Seq(("foo", "test"), ("bar", null), ("foo", "test1"), ("bar", "test")).toDF("k", "v") df1: org.apache.spark.sql.DataFrame = [k: string, v: string] scala> df1.coalesce(1).sortWithinPartitions("k", "v").collect res8: Array[org.apache.spark.sql.Row] = Array([bar,null], [bar,test], [foo,test], [foo,test1]) ``` -- 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