kunal642 commented on a change in pull request #3538: [CARBONDATA-3637] Optimize insert into flow URL: https://github.com/apache/carbondata/pull/3538#discussion_r374615892
########## File path: integration/spark2/src/main/scala/org/apache/spark/sql/execution/command/management/CarbonInsertIntoWithDf.scala ########## @@ -0,0 +1,230 @@ +/* + * 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.spark.sql.execution.command.management + +import java.text.SimpleDateFormat +import java.util + +import org.apache.spark.sql.{AnalysisException, CarbonUtils, DataFrame, Dataset, Row, SparkSession} +import org.apache.spark.sql.execution.command.{DataLoadTableFileMapping, UpdateTableModel} +import org.apache.spark.sql.execution.datasources.LogicalRelation +import org.apache.spark.util.{CarbonReflectionUtils, CausedBy, SparkUtil} + +import org.apache.carbondata.common.logging.LogServiceFactory +import org.apache.carbondata.core.datastore.impl.FileFactory +import org.apache.carbondata.core.indexstore.PartitionSpec +import org.apache.carbondata.core.metadata.schema.table.{CarbonTable, TableInfo} +import org.apache.carbondata.core.statusmanager.{LoadMetadataDetails, SegmentStatus, SegmentStatusManager} +import org.apache.carbondata.core.util.{CarbonProperties, ThreadLocalSessionInfo} +import org.apache.carbondata.core.util.path.CarbonTablePath +import org.apache.carbondata.events.OperationContext +import org.apache.carbondata.events.exception.PreEventException +import org.apache.carbondata.processing.loading.TableProcessingOperations +import org.apache.carbondata.processing.loading.exception.NoRetryException +import org.apache.carbondata.processing.loading.model.CarbonLoadModel +import org.apache.carbondata.processing.util.{CarbonDataProcessorUtil, CarbonLoaderUtil} +import org.apache.carbondata.spark.rdd.CarbonDataRDDFactory + +/* +* insert into with df, doesn't use logical plan +* +*/ +case class CarbonInsertIntoWithDf(databaseNameOp: Option[String], + tableName: String, + options: Map[String, String], + isOverwriteTable: Boolean, + var dimFilesPath: Seq[DataLoadTableFileMapping] = Seq(), + var dataFrame: DataFrame, + var inputSqlString: String = null, + var updateModel: Option[UpdateTableModel] = None, + var tableInfoOp: Option[TableInfo] = None, + var internalOptions: Map[String, String] = Map.empty, + var partition: Map[String, Option[String]] = Map.empty, + var operationContext: OperationContext = new OperationContext) { + + var table: CarbonTable = _ + + var logicalPartitionRelation: LogicalRelation = _ + + var sizeInBytes: Long = _ + + var currPartitions: util.List[PartitionSpec] = _ + + var parentTablePath: String = _ + + val LOGGER = LogServiceFactory.getLogService(this.getClass.getName) + + var finalPartition: Map[String, Option[String]] = Map.empty + + var timeStampFormat: SimpleDateFormat = _ + + var dateFormat: SimpleDateFormat = _ + + def process(sparkSession: SparkSession): Seq[Row] = { + ThreadLocalSessionInfo + .setConfigurationToCurrentThread(sparkSession.sessionState.newHadoopConf()) + val (sizeInBytes, table, dbName, logicalPartitionRelation, finalPartition) = CommonLoadUtils + .processMetadataCommon( + sparkSession, + databaseNameOp, + tableName, + tableInfoOp, + partition) + this.sizeInBytes = sizeInBytes + this.table = table + this.logicalPartitionRelation = logicalPartitionRelation + this.finalPartition = finalPartition + val carbonProperty: CarbonProperties = CarbonProperties.getInstance() + val hadoopConf = sparkSession.sessionState.newHadoopConf() + carbonProperty.addProperty("zookeeper.enable.lock", "false") + val factPath = "" + currPartitions = CommonLoadUtils.getCurrentParitions(sparkSession, table) + CommonLoadUtils.setNumberOfCoresWhileLoading(sparkSession, carbonProperty) + val optionsFinal: util.Map[String, String] = + CommonLoadUtils.getFinalLoadOptions( + carbonProperty, table, options) + val carbonLoadModel: CarbonLoadModel = CommonLoadUtils.prepareLoadModel( + hadoopConf, + factPath, + optionsFinal, + parentTablePath, + table, + isDataFrame = true, + internalOptions, + finalPartition, + options) Review comment: Can we have a single map instead of 'options' and 'internalOptions'? Can be fixed in this PR as all Load classes are being refactored ---------------------------------------------------------------- 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] With regards, Apache Git Services
