Skip to content

[SPARK-32268][SQL][FOLLOWUP] Add RewritePredicateSubquery below the InjectRuntimeFilter #35998

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ulysses-you wants to merge 1 commit into from
Closed

[SPARK-32268][SQL][FOLLOWUP] Add RewritePredicateSubquery below the InjectRuntimeFilter #35998

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,8 @@ class SparkOptimizer(
Batch("PartitionPruning", Once,
PartitionPruning) :+
Batch("InjectRuntimeFilter", FixedPoint(1),
InjectRuntimeFilter) :+
InjectRuntimeFilter,
RewritePredicateSubquery) :+
Batch("Pushdown Filters from PartitionPruning", fixedPoint,
PushDownPredicates) :+
Batch("Cleanup filters that cannot be pushed down", Once,
Expand Down
13 changes: 12 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@ package org.apache.spark.sql

import org.apache.spark.sql.catalyst.expressions.{Alias, BloomFilterMightContain, Literal}
import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, BloomFilterAggregate}
import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Filter, LogicalPlan}
import org.apache.spark.sql.catalyst.plans.LeftSemi
import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Filter, Join, LogicalPlan}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.{SharedSparkSession, SQLTestUtils}
import org.apache.spark.sql.types.{IntegerType, StructType}
Expand Down Expand Up @@ -213,6 +214,15 @@ class InjectRuntimeFilterSuite extends QueryTest with SQLTestUtils with SharedSp
super.afterAll()
}

private def ensureLeftSemiJoinExists(plan: LogicalPlan): Unit = {
assert(
plan.find {
case j: Join if j.joinType == LeftSemi => true
case _ => false
}.isDefined
)
}

def checkWithAndWithoutFeatureEnabled(query: String, testSemiJoin: Boolean,
shouldReplace: Boolean): Unit = {
var planDisabled: LogicalPlan = null
Expand All @@ -234,6 +244,7 @@ class InjectRuntimeFilterSuite extends QueryTest with SQLTestUtils with SharedSp
if (shouldReplace) {
val normalizedEnabled = normalizePlan(normalizeExprIds(planEnabled))
val normalizedDisabled = normalizePlan(normalizeExprIds(planDisabled))
ensureLeftSemiJoinExists(planEnabled)
assert(normalizedEnabled != normalizedDisabled)
} else {
comparePlans(planDisabled, planEnabled)
Expand Down