Github user QiangCai commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1605#discussion_r155440875
--- Diff: integration/spark2/src/main/scala/org/apache/carbondata/spark/rdd/AggregateDataMapCompactor.scala ---
@@ -0,0 +1,118 @@
+/*
+ * 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.carbondata.spark.rdd
+
+import java.util.concurrent.ExecutorService
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.sql.{CarbonSession, SQLContext}
+import org.apache.spark.sql.execution.command.CompactionModel
+import org.apache.spark.sql.execution.command.management.CarbonLoadDataCommand
+import org.apache.spark.sql.execution.command.preaaggregate.PreAggregateUtil
+import org.apache.spark.sql.parser.CarbonSpark2SqlParser
+
+import org.apache.carbondata.core.constants.CarbonCommonConstants
+import org.apache.carbondata.core.statusmanager.{SegmentStatus, SegmentStatusManager}
+import org.apache.carbondata.core.util.path.CarbonStorePath
+import org.apache.carbondata.processing.loading.model.CarbonLoadModel
+import org.apache.carbondata.processing.merger.{CarbonDataMergerUtil, CompactionType}
+
+/**
+ * Used to perform compaction on Aggregate data map.
+ */
+class AggregateDataMapCompactor(carbonLoadModel: CarbonLoadModel,
+ compactionModel: CompactionModel,
+ executor: ExecutorService,
+ sqlContext: SQLContext,
+ storeLocation: String)
+ extends Compactable(carbonLoadModel, compactionModel, executor, sqlContext, storeLocation) {
+
+ override def executeCompaction(): Unit = {
+ val carbonTable = carbonLoadModel.getCarbonDataLoadSchema.getCarbonTable
+ val loadMetaDataDetails = identifySegmentsToBeMerged()
+ val segments = loadMetaDataDetails.asScala.map(_.getLoadName)
+ if (segments.nonEmpty) {
+ val mergedLoadName = CarbonDataMergerUtil.getMergedLoadName(loadMetaDataDetails).split("_")(1)
+ CarbonSession.threadSet(
+ CarbonCommonConstants.CARBON_INPUT_SEGMENTS +
+ carbonLoadModel.getDatabaseName + "." +
+ carbonLoadModel.getTableName,
+ segments.mkString(","))
+ CarbonSession.threadSet(
+ CarbonCommonConstants.VALIDATE_CARBON_INPUT_SEGMENTS +
+ carbonLoadModel.getDatabaseName + "." +
+ carbonLoadModel.getTableName, "false")
+ val headers = carbonTable.getTableInfo.getFactTable.getListOfColumns.asScala
+ .map(_.getColumnName).mkString(",")
+ // Creating a new query string to insert data into pre-aggregate table from that same table.
+ // For example: To compact preaggtable1 we can fire a query like insert into preaggtable1
+ // select * from preaggtable1
+ // The following code will generate the select query with a load UDF that will be used to
+ // apply DataLoadingRules
+ val childDataFrame = sqlContext.sparkSession.sql(new CarbonSpark2SqlParser()
+ // adding the aggregation load UDF
+ .addPreAggLoadFunction(PreAggregateUtil
+ // creating the select query on the bases on table schema
+ .createChildSelectQuery(carbonTable.getTableInfo.getFactTable))).drop("preAggLoad")
--- End diff --
indentation is incorrect
---
Locked
