Improve EliminateOuterJoin performance

Author: wangyum

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala

@@ -170,13 +170,14 @@ abstract class UnaryNode extends LogicalPlan {
    * original constraint expressions with the corresponding alias
    */
   protected def getAllValidConstraints(projectList: Seq[NamedExpression]): Set[Expression] = {
-    var allConstraints = child.constraints.asInstanceOf[Set[Expression]]
+    val childConstraints = child.constraints
+    var allConstraints = childConstraints.asInstanceOf[Set[Expression]]
     projectList.foreach {
       case a @ Alias(l: Literal, _) =>
         allConstraints += EqualNullSafe(a.toAttribute, l)
       case a @ Alias(e, _) =>
         // For every alias in `projectList`, replace the reference in constraints by its attribute.
-        allConstraints ++= allConstraints.map(_ transform {
+        allConstraints ++= childConstraints.map(_ transform {
           case expr: Expression if expr.semanticEquals(e) =>
             a.toAttribute
         })

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/ConstraintPropagationSuite.scala

@@ -135,15 +135,13 @@ class ConstraintPropagationSuite extends SparkFunSuite with PlanTest {
       ExpressionSet(Seq(resolveColumn(aliasedRelation.analyze, "x") > 10,
         IsNotNull(resolveColumn(aliasedRelation.analyze, "x")),
         resolveColumn(aliasedRelation.analyze, "b") <=> resolveColumn(aliasedRelation.analyze, "y"),
-        resolveColumn(aliasedRelation.analyze, "z") <=> resolveColumn(aliasedRelation.analyze, "x"),
         resolveColumn(aliasedRelation.analyze, "z") > 10,
         IsNotNull(resolveColumn(aliasedRelation.analyze, "z")))))
 
     val multiAlias = tr.where('a === 'c + 10).select('a.as('x), 'c.as('y))
     verifyConstraints(multiAlias.analyze.constraints,
       ExpressionSet(Seq(IsNotNull(resolveColumn(multiAlias.analyze, "x")),
-        IsNotNull(resolveColumn(multiAlias.analyze, "y")),
-        resolveColumn(multiAlias.analyze, "x") === resolveColumn(multiAlias.analyze, "y") + 10))
+        IsNotNull(resolveColumn(multiAlias.analyze, "y"))))
     )
   }