Skip to content

[SPARK-1889] [SQL] Apply splitConjunctivePredicates to join condition while finding join ke... #836

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
ueshin wants to merge 1 commit into from
Closed

[SPARK-1889] [SQL] Apply splitConjunctivePredicates to join condition while finding join ke... #836

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
11 changes: 6 additions & 5 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,11 +129,12 @@ object HashFilteredJoin extends Logging with PredicateHelper {
// as join keys.
def splitPredicates(allPredicates: Seq[Expression], join: Join): Option[ReturnType] = {
val Join(left, right, joinType, _) = join
val (joinPredicates, otherPredicates) = allPredicates.partition {
case Equals(l, r) if (canEvaluate(l, left) && canEvaluate(r, right)) ||
(canEvaluate(l, right) && canEvaluate(r, left)) => true
case _ => false
}
val (joinPredicates, otherPredicates) =
allPredicates.flatMap(splitConjunctivePredicates).partition {
case Equals(l, r) if (canEvaluate(l, left) && canEvaluate(r, right)) ||
(canEvaluate(l, right) && canEvaluate(r, left)) => true
case _ => false
}

val joinKeys = joinPredicates.map {
case Equals(l, r) if canEvaluate(l, left) && canEvaluate(r, right) => (l, r)
Expand Down
19 changes: 18 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ import org.scalatest.FunSuite

import org.apache.spark.sql.TestData._
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.logical
import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql.execution
import org.apache.spark.sql.test.TestSQLContext._
import org.apache.spark.sql.test.TestSQLContext.planner._
Expand Down Expand Up @@ -57,4 +57,21 @@ class PlannerSuite extends FunSuite {
val planned = PartialAggregation(query)
assert(planned.isEmpty)
}

test("equi-join is hash-join") {
val x = testData2.as('x)
val y = testData2.as('y)
val join = x.join(y, Inner, Some("x.a".attr === "y.a".attr)).queryExecution.analyzed
val planned = planner.HashJoin(join)
assert(planned.size === 1)
}

test("multiple-key equi-join is hash-join") {
val x = testData2.as('x)
val y = testData2.as('y)
val join = x.join(y, Inner,
Some("x.a".attr === "y.a".attr && "x.b".attr === "y.b".attr)).queryExecution.analyzed
val planned = planner.HashJoin(join)
assert(planned.size === 1)
}
}