Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/13155#discussion_r63730774 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala --- @@ -1648,16 +1648,56 @@ object RewriteCorrelatedScalarSubquery extends Rule[LogicalPlan] { } /** + * Statically evaluate an expression containing one or more aggregates on an empty input. + */ + private def evalOnZeroTups(expr : Expression) : Option[Any] = { + // AggregateExpressions are Unevaluable, so we need to replace all aggregates + // in the expression with the value they would return for zero input tuples. + val rewrittenExpr = expr transform { + case a @ AggregateExpression(aggFunc, _, _, resultId) => + val resultLit = aggFunc.defaultResult match { + case Some(lit) => lit + case None => Literal.default(NullType) + } + Alias(resultLit, "aggVal") (exprId = resultId) + } + Option(rewrittenExpr.eval()) + } + + /** * Construct a new child plan by left joining the given subqueries to a base plan. */ private def constructLeftJoins( child: LogicalPlan, subqueries: ArrayBuffer[ScalarSubquery]): LogicalPlan = { subqueries.foldLeft(child) { case (currentChild, ScalarSubquery(query, conditions, _)) => + val aggOutputExpr = query.asInstanceOf[Aggregate].aggregateExpressions.head + val origOutput = query.output.head + + // Ensure the rewritten subquery returns the same result when a tuple from the + // outer query block does not join with the subquery block. + // val (outputExpr, rewrittenQuery) = aggFunc.defaultResult match { + val (outputExpr, rewrittenQuery) = evalOnZeroTups(aggOutputExpr) match { + case Some(value) => + val origExprId = origOutput.exprId + val newExprId = NamedExpression.newExprId + + // Renumber the original output, because the outer query refers to its ID. + val newQuery = query transformExpressions { + case Alias(c, n) => Alias(c, n)(exprId = newExprId) --- End diff -- This will give every alias the same id! That is not what we want.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org