[GitHub] [carbondata] vikramahuja1001 opened a new pull request #4141: [CARBONDATA-4190] Integrate Carbondata with Spark 3.1.1 version

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644556501



##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/CarbonToSparkAdapter.scala
##########
@@ -0,0 +1,735 @@
+/*
+ * 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
+
+import java.net.URI
+import java.sql.{Date, Timestamp}
+import java.time.ZoneId
+
+import javax.xml.bind.DatatypeConverter
+
+import scala.annotation.tailrec
+import scala.collection.mutable
+import scala.collection.mutable.ArrayBuffer
+
+import org.antlr.v4.runtime.tree.TerminalNode
+import org.apache.spark.{SparkContext, TaskContext}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.scheduler.{SparkListener, SparkListenerApplicationEnd}
+import org.apache.spark.serializer.Serializer
+import org.apache.spark.sql.carbondata.execution.datasources.CarbonFileIndexReplaceRule
+import org.apache.spark.sql.catalyst.{CarbonParserUtil, InternalRow, QueryPlanningTracker, TableIdentifier}
+import org.apache.spark.sql.catalyst.analysis.{Analyzer, UnresolvedRelation}
+import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, ExternalCatalogWithListener, SessionCatalog}
+import org.apache.spark.sql.catalyst.encoders.RowEncoder
+import org.apache.spark.sql.catalyst.expressions.{Alias, Attribute, AttributeMap, AttributeReference, AttributeSeq, AttributeSet, ExprId, Expression, ExpressionSet, NamedExpression, Predicate, ScalaUDF, SortOrder, SubqueryExpression}
+import org.apache.spark.sql.catalyst.expressions.codegen._
+import org.apache.spark.sql.catalyst.expressions.codegen.Block._
+import org.apache.spark.sql.catalyst.optimizer.{BuildLeft, BuildRight, BuildSide, Optimizer}
+import org.apache.spark.sql.catalyst.parser.ParserUtils.operationNotAllowed
+import org.apache.spark.sql.catalyst.parser.SqlBaseParser.{BucketSpecContext, ColTypeListContext, CreateTableHeaderContext, LocationSpecContext, PartitionFieldListContext, QueryContext, SkewSpecContext, TablePropertyListContext}
+import org.apache.spark.sql.catalyst.plans.{JoinType, QueryPlan, logical}
+import org.apache.spark.sql.catalyst.plans.logical.{ColumnStat, InsertIntoStatement, Join, JoinHint, LogicalPlan, OneRowRelation, QualifiedColType, Statistics, SubqueryAlias}
+import org.apache.spark.sql.catalyst.plans.physical.SinglePartition
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.catalyst.trees.{CurrentOrigin, TreeNode}
+import org.apache.spark.sql.catalyst.util.{DateTimeUtils, TimestampFormatter}
+import org.apache.spark.sql.execution.{ExplainMode, QueryExecution, SQLExecution, ShuffledRowRDD, SimpleMode, SparkPlan, UnaryExecNode}
+import org.apache.spark.sql.execution.command.{ExplainCommand, Field, PartitionerField, RefreshTableCommand, TableModel, TableNewProcessor}
+import org.apache.spark.sql.execution.command.table.{CarbonCreateTableAsSelectCommand, CarbonCreateTableCommand}
+import org.apache.spark.sql.execution.datasources.{DataSourceStrategy, FilePartition, PartitionedFile}
+import org.apache.spark.sql.execution.exchange.ShuffleExchangeExec
+import org.apache.spark.sql.execution.metric.SQLShuffleWriteMetricsReporter
+import org.apache.spark.sql.execution.strategy.CarbonDataSourceScan
+import org.apache.spark.sql.hive.HiveExternalCatalog
+import org.apache.spark.sql.internal.{SessionState, SharedState}
+import org.apache.spark.sql.optimizer.{CarbonIUDRule, CarbonUDFTransformRule, MVRewriteRule}
+import org.apache.spark.sql.parser.CarbonSpark2SqlParser
+import org.apache.spark.sql.parser.CarbonSparkSqlParserUtil.{checkIfDuplicateColumnExists, convertDbNameToLowerCase, validateStreamingProperty}
+import org.apache.spark.sql.secondaryindex.optimizer.CarbonSITransformationRule
+import org.apache.spark.sql.sources.Filter
+import org.apache.spark.sql.streaming.Trigger
+import org.apache.spark.sql.types.{AbstractDataType, CharType, DataType, Metadata, StringType, StructField, VarcharType}
+import org.apache.spark.sql.util.SparkSQLUtil
+import org.apache.spark.unsafe.types.UTF8String
+
+import org.apache.carbondata.common.exceptions.DeprecatedFeatureException
+import org.apache.carbondata.common.exceptions.sql.MalformedCarbonCommandException
+import org.apache.carbondata.core.constants.CarbonCommonConstants
+import org.apache.carbondata.core.datastore.impl.FileFactory
+import org.apache.carbondata.core.metadata.AbsoluteTableIdentifier
+import org.apache.carbondata.core.metadata.datatype.DataTypes
+import org.apache.carbondata.core.metadata.schema.SchemaReader
+import org.apache.carbondata.core.util.{CarbonProperties, ThreadLocalSessionInfo}
+import org.apache.carbondata.core.util.path.CarbonTablePath
+import org.apache.carbondata.geo.{InPolygonJoinUDF, ToRangeListAsStringUDF}
+import org.apache.carbondata.mv.plans.modular.{GroupBy, ModularPlan, Select}
+import org.apache.carbondata.spark.CarbonOption
+import org.apache.carbondata.spark.util.CarbonScalaUtil
+
+object CarbonToSparkAdapter {
+
+  def addSparkSessionListener(sparkSession: SparkSession): Unit = {
+    sparkSession.sparkContext.addSparkListener(new SparkListener {
+      override def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit = {
+        CarbonEnv.carbonEnvMap.remove(sparkSession)
+        ThreadLocalSessionInfo.unsetAll()
+      }
+    })
+  }
+
+  def addSparkListener(sparkContext: SparkContext): Unit = {
+    sparkContext.addSparkListener(new SparkListener {
+      override def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit = {
+        SparkSession.setDefaultSession(null)
+      }
+    })
+  }
+
+  def createAttributeReference(
+      name: String,
+      dataType: DataType,
+      nullable: Boolean,
+      metadata: Metadata,
+      exprId: ExprId,
+      qualifier: Option[String],
+      attrRef : NamedExpression = null): AttributeReference = {
+    val qf = if (qualifier.nonEmpty) Seq(qualifier.get) else Seq.empty
+    AttributeReference(
+      name,
+      dataType,
+      nullable,
+      metadata)(exprId, qf)
+  }
+
+  def createAttributeReference(
+      name: String,
+      dataType: DataType,
+      nullable: Boolean,
+      metadata: Metadata,
+      exprId: ExprId,
+      qualifier: Seq[String]): AttributeReference = {
+    AttributeReference(
+      name,
+      dataType,
+      nullable,
+      metadata)(exprId, qualifier)
+  }
+
+  def lowerCaseAttribute(expression: Expression): Expression = expression.transform {
+    case attr: AttributeReference =>
+      CarbonToSparkAdapter.createAttributeReference(
+        attr.name.toLowerCase,
+        attr.dataType,
+        attr.nullable,
+        attr.metadata,
+        attr.exprId,
+        attr.qualifier)
+  }
+
+  def createAttributeReference(attr: AttributeReference,
+      attrName: String,
+      newSubsume: String): AttributeReference = {
+    AttributeReference(attrName, attr.dataType)(
+      exprId = attr.exprId,
+      qualifier = newSubsume.split("\n").map(_.trim))
+  }
+
+  def createScalaUDF(s: ScalaUDF, reference: AttributeReference): ScalaUDF = {
+    s.copy(children = Seq(reference))
+  }
+
+  def createExprCode(code: String, isNull: String, value: String, dataType: DataType): ExprCode = {
+    ExprCode(
+      code"$code",
+      JavaCode.isNullVariable(isNull),
+      JavaCode.variable(value, dataType))
+  }
+
+  def createAliasRef(
+      child: Expression,
+      name: String,
+      exprId: ExprId = NamedExpression.newExprId,
+      qualifier: Seq[String] = Seq.empty,
+      explicitMetadata: Option[Metadata] = None,
+      namedExpr: Option[NamedExpression] = None) : Alias = {

Review comment:
       done

##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/avro/AvroFileFormatFactory.scala
##########
@@ -0,0 +1,48 @@
+/*
+ * 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.avro

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644556914



##########
File path: mv/plan/src/main/spark2.3/org/apache/carbondata/mv/plans/modular/ExpressionHelper.scala
##########
@@ -47,4 +55,110 @@ object ExpressionHelper {
     reference.qualifier.head
   }
 
+  def getStatisticsObj(outputList: Seq[NamedExpression],
+      plan: LogicalPlan, stats: Statistics,
+      aliasMap: Option[AttributeMap[Attribute]] = None): Statistics = {
+    val output = outputList.map(_.toAttribute)
+    val mapSeq = plan.collect { case n: logical.LeafNode => n }.map {
+      table => AttributeMap(table.output.zip(output))
+    }
+    val rewrites = mapSeq.head
+    val attributes: AttributeMap[ColumnStat] = stats.attributeStats
+    var attributeStats = AttributeMap(attributes.iterator
+      .map { pair => (rewrites(pair._1), pair._2) }.toSeq)
+    if (aliasMap.isDefined) {
+      attributeStats = AttributeMap(
+        attributeStats.map(pair => (aliasMap.get(pair._1), pair._2)).toSeq)
+    }
+    Statistics(stats.sizeInBytes, stats.rowCount, attributeStats, stats.hints)
+  }
+
+  def getOptimizedPlan(s: SubqueryExpression): LogicalPlan = {
+    val Subquery(newPlan) = BirdcageOptimizer.execute(Subquery(s.plan))
+    newPlan
+  }
+
+  def normalizeExpressions(r: NamedExpression, attrs: AttributeSeq): NamedExpression = {
+    QueryPlan.normalizeExprId(r, attrs)
+  }
+
+  def attributeMap(rAliasMap: AttributeMap[Attribute]) : AttributeMap[Expression] = {
+    rAliasMap.asInstanceOf[AttributeMap[Expression]]
+  }
+
+  def seqOfRules : Seq[Rule[LogicalPlan]] = {
+    Seq(
+      // Operator push down
+      PushProjectionThroughUnion,
+      ReorderJoin,
+      EliminateOuterJoin,
+      PushPredicateThroughJoin,
+      PushDownPredicate,
+      ColumnPruning,
+      // Operator combine
+      CollapseRepartition,
+      CollapseProject,
+      CollapseWindow,
+      CombineFilters,
+      CombineLimits,
+      CombineUnions,
+      // Constant folding and strength reduction
+      NullPropagation,
+      FoldablePropagation,
+      ConstantFolding,
+      ReorderAssociativeOperator,
+      // No need to apply LikeSimplification rule while creating MV
+      // as modular plan asCompactSql will be set in schema
+      //        LikeSimplification,
+      BooleanSimplification,
+      SimplifyConditionals,
+      RemoveDispensableExpressions,
+      SimplifyBinaryComparison,
+      EliminateSorts,
+      SimplifyCasts,
+      SimplifyCaseConversionExpressions,
+      RewriteCorrelatedScalarSubquery,
+      EliminateSerialization,
+      RemoveRedundantAliases,
+      RemoveRedundantProject)
+  }
+}
+
+trait getVerboseString extends LeafNode {
+}
+
+trait groupByUnaryNode extends UnaryNode {
+}
+
+trait selectModularPlan extends ModularPlan {
+}
+
+trait unionModularPlan extends ModularPlan {
+}
+
+trait oneRowTableLeafNode extends LeafNode {
+}
+
+object MatchJoin {
+  def unapply(plan : LogicalPlan): Option[(LogicalPlan, LogicalPlan, JoinType, Option[Expression],
+    Option[Any])] = {
+    plan match {
+      case j@Join(left, right, joinType, condition) =>
+        val a = Some(left, right, joinType, condition, None)
+        a

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644557146



##########
File path: integration/spark/src/main/scala/org/apache/spark/sql/secondaryindex/joins/BroadCastSIFilterPushJoin.scala
##########
@@ -147,13 +152,15 @@ object BroadCastSIFilterPushJoin {
       inputCopy: Array[InternalRow],
       leftKeys: Seq[Expression],
       rightKeys: Seq[Expression],
-      buildSide: BuildSide,
+      buildSide: CarbonBuildSideType,
       isIndexTable: Boolean = false): Unit = {
 
+    val carbonBuildSide = CarbonBuildSide(buildSide)

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644557581



##########
File path: integration/spark/src/main/scala/org/apache/spark/sql/secondaryindex/rdd/CarbonSIRebuildRDD.scala
##########
@@ -214,9 +214,7 @@ class CarbonSIRebuildRDD[K, V](
           new SparkDataTypeConverterImpl)
 
         // add task completion listener to clean up the resources
-        context.addTaskCompletionListener { _ =>
-          close()
-        }
+        CarbonToSparkAdapter.addTaskCompletionListener(close())

Review comment:
       addTaskCompletionListener API changed in Spark 3.1




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644557814



##########
File path: integration/spark/src/main/spark2.3/org/apache/spark/sql/CarbonToSparkAdapter.scala
##########
@@ -185,8 +224,390 @@ object CarbonToSparkAdapter {
   def getHiveExternalCatalog(sparkSession: SparkSession): HiveExternalCatalog = {
     sparkSession.sessionState.catalog.externalCatalog.asInstanceOf[HiveExternalCatalog]
   }
+
+  def createFilePartition(index: Int, files: ArrayBuffer[PartitionedFile]) = {
+    FilePartition(index, files.toArray.toSeq)
+  }
+
+  def stringToTimestamp(timestamp: String): Option[Long] = {
+    DateTimeUtils.stringToTimestamp(UTF8String.fromString(timestamp))
+  }
+
+  def getTableIdentifier(u: UnresolvedRelation): Some[TableIdentifier] = {
+    Some(u.tableIdentifier)
+  }
+
+  def dateToString(date: Int): String = {
+    DateTimeUtils.dateToString(date.toString.toInt)
+  }
+
+  def timeStampToString(timeStamp: Long): String = {
+    DateTimeUtils.timestampToString(timeStamp)
+  }

Review comment:
       done, added to common2.3and2.4




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644561121



##########
File path: integration/spark/src/main/spark2.3/org/apache/spark/sql/CarbonToSparkAdapter.scala
##########
@@ -185,8 +224,390 @@ object CarbonToSparkAdapter {
   def getHiveExternalCatalog(sparkSession: SparkSession): HiveExternalCatalog = {
     sparkSession.sessionState.catalog.externalCatalog.asInstanceOf[HiveExternalCatalog]
   }
+
+  def createFilePartition(index: Int, files: ArrayBuffer[PartitionedFile]) = {
+    FilePartition(index, files.toArray.toSeq)
+  }
+
+  def stringToTimestamp(timestamp: String): Option[Long] = {
+    DateTimeUtils.stringToTimestamp(UTF8String.fromString(timestamp))
+  }
+
+  def getTableIdentifier(u: UnresolvedRelation): Some[TableIdentifier] = {
+    Some(u.tableIdentifier)
+  }
+
+  def dateToString(date: Int): String = {
+    DateTimeUtils.dateToString(date.toString.toInt)
+  }
+
+  def timeStampToString(timeStamp: Long): String = {
+    DateTimeUtils.timestampToString(timeStamp)
+  }
+
+  def stringToTime(value: String): java.util.Date = {
+    DateTimeUtils.stringToTime(value)
+  }
+
+  def getProcessingTime: String => Trigger = {
+    Trigger.ProcessingTime
+  }
+
+  def addTaskCompletionListener[U](f: => U) {
+    TaskContext.get().addTaskCompletionListener { context =>
+      f
+    }
+  }
+
+  def createShuffledRowRDD(sparkContext: SparkContext, localTopK: RDD[InternalRow],
+      child: SparkPlan, serializer: Serializer): ShuffledRowRDD = {
+    new ShuffledRowRDD(
+      ShuffleExchangeExec.prepareShuffleDependency(
+        localTopK, child.output, SinglePartition, serializer))
+  }
+
+  def getInsertIntoCommand(table: LogicalPlan,
+      partition: Map[String, Option[String]],
+      query: LogicalPlan,
+      overwrite: Boolean,
+      ifPartitionNotExists: Boolean): InsertIntoTable = {
+    InsertIntoTable(
+      table,
+      partition,
+      query,
+      overwrite,
+      ifPartitionNotExists)
+  }
+
+  def getExplainCommandObj(logicalPlan: LogicalPlan = OneRowRelation(),
+      mode: Option[String]) : ExplainCommand = {
+    ExplainCommand(logicalPlan, mode.isDefined)
+  }
+
+  def getExplainCommandObj(mode: Option[String]) : ExplainCommand = {
+    ExplainCommand(OneRowRelation(), mode.isDefined)
+  }
+
+  def invokeAnalyzerExecute(analyzer: Analyzer,
+      plan: LogicalPlan): LogicalPlan = {
+    analyzer.executeAndCheck(plan)
+  }
+
+  def normalizeExpressions(r: NamedExpression, attrs: AttributeSeq): NamedExpression = {
+    QueryPlan.normalizeExprId(r, attrs)
+  }
+
+  def getBuildRight: BuildSide = {
+    BuildRight
+  }
+
+  def getBuildLeft: BuildSide = {
+    BuildLeft
+  }
+
+  type CarbonBuildSideType = BuildSide
+  type InsertIntoStatementWrapper = InsertIntoTable
+
+  def withNewExecutionId[T](sparkSession: SparkSession, queryExecution: QueryExecution): T => T = {
+    SQLExecution.withNewExecutionId(sparkSession, queryExecution)(_)
+  }
+
+  def getTableIdentifier(parts: TableIdentifier): TableIdentifier = {
+    parts
+  }
+
+  def createJoinNode(child: LogicalPlan,
+      targetTable: LogicalPlan,
+      joinType: JoinType,
+      condition: Option[Expression]): Join = {
+    Join(child, targetTable, joinType, condition)
+  }
+
+  def getPartitionsFromInsert(x: InsertIntoStatementWrapper): Map[String, Option[String]] = {
+    x.partition
+  }
+
+  def getStatisticsObj(outputList: Seq[NamedExpression],

Review comment:
       yes removed




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644561823



##########
File path: integration/spark/src/main/spark2.3/org/apache/spark/sql/hive/execution/command/CarbonResetCommand.scala
##########
@@ -17,7 +17,7 @@
 
 package org.apache.spark.sql.hive.execution.command
 
-import org.apache.spark.sql.{CarbonEnv, Row, SparkSession}
+import org.apache.spark.sql.{CarbonEnv, CarbonToSparkAdapter, Row, SparkSession}

Review comment:
       removed




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644562441



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/CarbonToSparkAdapter.scala
##########
@@ -229,8 +270,388 @@ object CarbonToSparkAdapter {
       .unwrapped
       .asInstanceOf[HiveExternalCatalog]
   }
+
+  def createFilePartition(index: Int, files: ArrayBuffer[PartitionedFile]): FilePartition = {
+    FilePartition(index, files.toArray)
+  }
+
+  def stringToTimestamp(timestamp: String): Option[Long] = {
+    DateTimeUtils.stringToTimestamp(UTF8String.fromString(timestamp))
+  }
+
+  def stringToTime(value: String): java.util.Date = {
+    DateTimeUtils.stringToTime(value)
+  }
+
+  def timeStampToString(timeStamp: Long): String = {
+    DateTimeUtils.timestampToString(timeStamp)
+  }
+
+  def getTableIdentifier(u: UnresolvedRelation): Some[TableIdentifier] = {
+    Some(u.tableIdentifier)
+  }
+
+  def dateToString(date: Int): String = {
+    DateTimeUtils.dateToString(date.toString.toInt)
+  }
+
+  def getProcessingTime: String => Trigger = {
+    Trigger.ProcessingTime
+  }
+
+  def addTaskCompletionListener[U](f: => U) {
+    TaskContext.get().addTaskCompletionListener { context =>
+      f
+    }
+  }
+
+  def createShuffledRowRDD(sparkContext: SparkContext, localTopK: RDD[InternalRow],
+      child: SparkPlan, serializer: Serializer): ShuffledRowRDD = {
+    new ShuffledRowRDD(
+      ShuffleExchangeExec.prepareShuffleDependency(
+        localTopK, child.output, SinglePartition, serializer))
+  }
+
+  def getInsertIntoCommand(table: LogicalPlan,
+      partition: Map[String, Option[String]],
+      query: LogicalPlan,
+      overwrite: Boolean,
+      ifPartitionNotExists: Boolean): InsertIntoTable = {
+    InsertIntoTable(
+      table,
+      partition,
+      query,
+      overwrite,
+      ifPartitionNotExists)
+  }
+
+  def getExplainCommandObj(logicalPlan: LogicalPlan = OneRowRelation(),
+      mode: Option[String]) : ExplainCommand = {
+    ExplainCommand(logicalPlan, mode.isDefined)
+  }
+
+  def invokeAnalyzerExecute(analyzer: Analyzer,
+      plan: LogicalPlan): LogicalPlan = {
+    analyzer.executeAndCheck(plan)
+  }
+
+  def normalizeExpressions(r: NamedExpression, attrs: AttributeSeq): NamedExpression = {
+    QueryPlan.normalizeExprId(r, attrs)
+  }
+
+  def getBuildRight: BuildSide = {
+    BuildRight
+  }
+
+  def getBuildLeft: BuildSide = {
+    BuildLeft
+  }
+
+  type CarbonBuildSideType = BuildSide
+  type InsertIntoStatementWrapper = InsertIntoTable
+
+  def withNewExecutionId[T](sparkSession: SparkSession, queryExecution: QueryExecution): T => T = {
+    SQLExecution.withNewExecutionId(sparkSession, queryExecution)(_)
+  }
+
+  def createJoinNode(child: LogicalPlan,
+      targetTable: LogicalPlan,
+      joinType: JoinType,
+      condition: Option[Expression]): Join = {
+    Join(child, targetTable, joinType, condition)
+  }
+
+  def getPartitionsFromInsert(x: InsertIntoStatementWrapper): Map[String, Option[String]] = {
+    x.partition
+  }
+
+  def getTableIdentifier(parts: TableIdentifier): TableIdentifier = {
+    parts
+  }
+
+  def getStatisticsObj(outputList: Seq[NamedExpression],
+      plan: LogicalPlan, stats: Statistics,
+      aliasMap: Option[AttributeMap[Attribute]] = None): Statistics = {
+    val output = outputList.map(_.toAttribute)
+    val mapSeq = plan.collect { case n: logical.LeafNode => n }.map {
+      table => AttributeMap(table.output.zip(output))
+    }
+    val rewrites = mapSeq.head
+    val attributes: AttributeMap[ColumnStat] = stats.attributeStats
+    var attributeStats = AttributeMap(attributes.iterator
+      .map { pair => (rewrites(pair._1), pair._2) }.toSeq)
+    if (aliasMap.isDefined) {
+      attributeStats = AttributeMap(
+        attributeStats.map(pair => (aliasMap.get(pair._1), pair._2)).toSeq)
+    }
+    Statistics(stats.sizeInBytes, stats.rowCount, attributeStats, stats.hints)
+  }
+
+  def createRefreshTableCommand(tableIdentifier: TableIdentifier): RefreshTable = {
+    RefreshTable(tableIdentifier)
+  }
+
+  type RefreshTables = RefreshTable

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644562741



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/execution/CarbonCodegenSupport.scala
##########
@@ -0,0 +1,23 @@
+/*
+ * 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
+
+import org.apache.spark.sql.execution.joins.HashJoin
+
+trait CarbonCodegenSupport extends SparkPlan with HashJoin {

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644563014



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/execution/strategy/CarbonDataSourceScan.scala
##########
@@ -0,0 +1,182 @@
+/*
+ * 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.strategy
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.CarbonInputMetrics
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.CarbonDatasourceHadoopRelation
+import org.apache.spark.sql.carbondata.execution.datasources.CarbonSparkDataSourceUtil
+import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, SortOrder, UnsafeProjection}
+import org.apache.spark.sql.catalyst.expressions.{Expression => SparkExpression}
+import org.apache.spark.sql.catalyst.plans.QueryPlan
+import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partitioning, UnknownPartitioning}
+import org.apache.spark.sql.execution.{ColumnarBatchScan, DataSourceScanExec, WholeStageCodegenExec}
+import org.apache.spark.sql.optimizer.CarbonFilters
+import org.apache.spark.sql.types.AtomicType
+
+import org.apache.carbondata.core.index.IndexFilter
+import org.apache.carbondata.core.indexstore.PartitionSpec
+import org.apache.carbondata.core.metadata.schema.BucketingInfo
+import org.apache.carbondata.core.readcommitter.ReadCommittedScope
+import org.apache.carbondata.core.scan.expression.Expression
+import org.apache.carbondata.core.scan.expression.logical.AndExpression
+import org.apache.carbondata.hadoop.CarbonProjection
+import org.apache.carbondata.spark.rdd.CarbonScanRDD
+
+/**
+ *  Physical plan node for scanning data. It is applied for both tables
+ *  USING carbondata and STORED AS carbondata.
+ */
+case class CarbonDataSourceScan(

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644563223



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/hive/CarbonAnalyzer.scala
##########
@@ -0,0 +1,50 @@
+/*
+ * 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.hive
+
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.analysis.Analyzer
+import org.apache.spark.sql.catalyst.catalog.SessionCatalog
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.util.CarbonReflectionUtils
+
+class CarbonAnalyzer(catalog: SessionCatalog,

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644563505



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/hive/CarbonSqlAstBuilder.scala
##########
@@ -0,0 +1,52 @@
+/*
+ * 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.hive
+
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.parser.ParserUtils.string
+import org.apache.spark.sql.catalyst.parser.SqlBaseParser.{AddTableColumnsContext, CreateHiveTableContext}
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.SparkSqlAstBuilder
+import org.apache.spark.sql.internal.SQLConf

Review comment:
       done

##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/hive/SqlAstBuilderHelper.scala
##########
@@ -0,0 +1,90 @@
+/*
+ * 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.hive
+
+import org.apache.spark.sql.CarbonToSparkAdapter

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644563696



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/hive/execution/command/CarbonResetCommand.scala
##########
@@ -0,0 +1,46 @@
+/*
+ * 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.hive.execution.command
+
+import org.apache.spark.sql.{CarbonEnv, CarbonToSparkAdapter, Row, SparkSession}

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644563841



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/parser/CarbonExtensionSqlParser.scala
##########
@@ -0,0 +1,81 @@
+/*
+ * 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.parser
+

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644564060



##########
File path: integration/spark/src/main/spark2.4/org/apache/spark/sql/parser/CarbonSparkSqlParser.scala
##########
@@ -0,0 +1,153 @@
+/*
+ * 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.
+ */

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644572609



##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/CarbonBoundReference.scala
##########
@@ -0,0 +1,45 @@
+/*
+ * 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
+
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.{Attribute, ExprId, LeafExpression, NamedExpression}
+import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
+import org.apache.spark.sql.types.DataType
+
+import org.apache.carbondata.core.scan.expression.ColumnExpression
+
+case class CarbonBoundReference(colExp: ColumnExpression, dataType: DataType, nullable: Boolean)

Review comment:
       common in 2.3 and 2.4, added to common code




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644573460



##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/SparkSqlAdapter.scala
##########
@@ -0,0 +1,49 @@
+/*
+ * 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
+
+import org.apache.spark.sql.catalyst.TableIdentifier
+import org.apache.spark.sql.catalyst.expressions.{Attribute, EmptyRow, Expression}
+import org.apache.spark.sql.execution.FileSourceScanExec
+import org.apache.spark.sql.execution.datasources.HadoopFsRelation
+import org.apache.spark.sql.types.StructType
+
+object SparkSqlAdapter {
+
+  def initSparkSQL(): Unit = {
+  }
+
+  def getScanForSegments(
+      @transient relation: HadoopFsRelation,

Review comment:
        FileSourceScanExec API is different in spark2.3, 2.4 and 3.1. Different number of arguments in all 3.




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644576944



##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/parser/SparkSqlAstBuilderWrapper.scala
##########
@@ -0,0 +1,30 @@
+/*
+ * 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.parser
+
+import org.apache.spark.sql.catalyst.parser.SqlBaseParser._
+import org.apache.spark.sql.execution.SparkSqlAstBuilder
+import org.apache.spark.sql.internal.SQLConf
+
+/**
+ * use this wrapper to adapter multiple spark versions
+ */
+abstract class SparkSqlAstBuilderWrapper(conf: SQLConf) extends SparkSqlAstBuilder {

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r644577121



##########
File path: integration/spark/src/main/spark3.1/org/apache/spark/sql/parser/CarbonExtensionSqlParser.scala
##########
@@ -0,0 +1,81 @@
+/*
+ * 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.parser
+
+import org.apache.spark.sql.{CarbonEnv, CarbonThreadUtil, SparkSession}
+import org.apache.spark.sql.catalyst.parser.ParserInterface
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.SparkSqlParser
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.util.CarbonException
+
+import org.apache.carbondata.common.exceptions.sql.MalformedCarbonCommandException
+import org.apache.carbondata.spark.util.CarbonScalaUtil
+
+/**
+ * parser order: carbon parser => spark parser
+ */
+class CarbonExtensionSqlParser(

Review comment:
       done




--
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:
[hidden email]

[GitBox]

vikramahuja1001 commented on a change in pull request #4141:
URL: https://github.com/apache/carbondata/pull/4141#discussion_r645296443



##########
File path: integration/spark/src/main/scala/org/apache/spark/sql/execution/command/mutation/DeleteExecution.scala
##########
@@ -321,7 +321,7 @@ object DeleteExecution {
           deleteStatus = SegmentStatus.SUCCESS
         } catch {
           case e : MultipleMatchingException =>
-            LOGGER.error(e.getMessage)
+          LOGGER.error(e.getMessage)

Review comment:
       done




--
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:
[hidden email]