satishkotha commented on a change in pull request #2263: URL: https://github.com/apache/hudi/pull/2263#discussion_r535602730
########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/RDDCustomColumnsSortPartitioner.java ########## @@ -0,0 +1,66 @@ +/* + * 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.avro.Schema; +import org.apache.avro.generic.GenericRecord; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.table.BulkInsertPartitioner; +import org.apache.spark.api.java.JavaRDD; + +/** + * A partitioner that does sorting based on specified column values for each RDD partition. + * + * @param <T> HoodieRecordPayload type + */ +public class RDDCustomColumnsSortPartitioner<T extends HoodieRecordPayload> + implements BulkInsertPartitioner<JavaRDD<HoodieRecord<T>>> { + + private final String[] sortColumnNames; + private final String schemaString; + + public RDDCustomColumnsSortPartitioner(String[] columnNames, Schema schema) { + this.sortColumnNames = columnNames; + //TODO Schema is not serializable. So convert to String here. Figure out how to improve this + this.schemaString = schema.toString(); + } + + @Override + public JavaRDD<HoodieRecord<T>> repartitionRecords(JavaRDD<HoodieRecord<T>> records, + int outputSparkPartitions) { + final String[] sortColumns = this.sortColumnNames; + final String schemaStr = this.schemaString; + return records.sortBy(record -> { Review comment: I like this suggestion. This 'sortColumn' is probably needed only for this 'BulkInsert' based clustering strategy. So, just want to make sure its ok to add new fields in HoodieRecord even though this is needed only for one small usecase. If you think thats acceptable, I'll make the change. Let me know. ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/RDDCustomColumnsSortPartitioner.java ########## @@ -0,0 +1,66 @@ +/* + * 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.avro.Schema; +import org.apache.avro.generic.GenericRecord; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.table.BulkInsertPartitioner; +import org.apache.spark.api.java.JavaRDD; + +/** + * A partitioner that does sorting based on specified column values for each RDD partition. + * + * @param <T> HoodieRecordPayload type + */ +public class RDDCustomColumnsSortPartitioner<T extends HoodieRecordPayload> + implements BulkInsertPartitioner<JavaRDD<HoodieRecord<T>>> { + + private final String[] sortColumnNames; + private final String schemaString; + + public RDDCustomColumnsSortPartitioner(String[] columnNames, Schema schema) { + this.sortColumnNames = columnNames; + //TODO Schema is not serializable. So convert to String here. Figure out how to improve this + this.schemaString = schema.toString(); + } + + @Override + public JavaRDD<HoodieRecord<T>> repartitionRecords(JavaRDD<HoodieRecord<T>> records, + int outputSparkPartitions) { + final String[] sortColumns = this.sortColumnNames; + final String schemaStr = this.schemaString; + return records.sortBy(record -> { Review comment: I like this suggestion. This 'sortColumn' is probably needed only for this 'BulkInsert' based clustering strategy. So, just want to make sure its ok to add new fields in HoodieRecord even though this is needed only for one usecase. If you think thats acceptable, I'll make the change. Let me know. ---------------------------------------------------------------- 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]
