1
0

[HUDI-4081][HUDI-4472] Addressing Spark SQL vs Spark DS performance gap (#6213)

This commit is contained in:
Alexey Kudinkin
2022-07-28 15:36:03 -07:00
committed by GitHub
parent 70b5cf6dab
commit cfd0c1ee34
14 changed files with 382 additions and 189 deletions

View File

@@ -18,14 +18,22 @@
package org.apache.spark.sql
import org.apache.spark.sql.catalyst.{AliasIdentifier, TableIdentifier}
import org.apache.spark.sql.catalyst.analysis.UnresolvedRelation
import org.apache.spark.sql.catalyst.expressions.{Expression, Like}
import org.apache.spark.sql.catalyst.analysis.{SimpleAnalyzer, UnresolvedRelation}
import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression, Like}
import org.apache.spark.sql.catalyst.plans.JoinType
import org.apache.spark.sql.catalyst.plans.logical.{InsertIntoTable, Join, LogicalPlan}
import org.apache.spark.sql.execution.command.ExplainCommand
import org.apache.spark.sql.internal.SQLConf
object HoodieSpark2CatalystPlanUtils extends HoodieCatalystPlansUtils {
def resolveOutputColumns(tableName: String,
expected: Seq[Attribute],
query: LogicalPlan,
byName: Boolean,
conf: SQLConf): LogicalPlan =
SimpleAnalyzer.ResolveOutputRelation.resolveOutputColumns(tableName, expected, query, byName)
def createExplainCommand(plan: LogicalPlan, extended: Boolean): LogicalPlan =
ExplainCommand(plan, extended = extended)