Kimahriman commented on a change in pull request #33142:
URL: https://github.com/apache/spark/pull/33142#discussion_r661384470
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/EquivalentExpressions.scala
##########
@@ -93,25 +72,36 @@ class EquivalentExpressions {
*/
private def addCommonExprs(
exprs: Seq[Expression],
- addFunc: Expression => Boolean = addExpr): Unit = {
- val exprSetForAll = mutable.Set[Expr]()
- addExprTree(exprs.head, addExprToSet(_, exprSetForAll))
-
- val candidateExprs = exprs.tail.foldLeft(exprSetForAll) { (exprSet, expr)
=>
- val otherExprSet = mutable.Set[Expr]()
- addExprTree(expr, addExprToSet(_, otherExprSet))
- exprSet.intersect(otherExprSet)
+ map: mutable.HashMap[ExpressionEquals, ExpressionStats]): Unit = {
+ assert(exprs.length > 1)
+ var localEquivalenceMap = mutable.HashMap.empty[ExpressionEquals,
ExpressionStats]
+ addExprTree0(exprs.head, localEquivalenceMap)
+
+ exprs.tail.foreach { expr =>
+ val otherLocalEquivalenceMap = mutable.HashMap.empty[ExpressionEquals,
ExpressionStats]
+ addExprTree0(expr, otherLocalEquivalenceMap)
+ localEquivalenceMap = localEquivalenceMap.filter { case (key, _) =>
+ otherLocalEquivalenceMap.contains(key)
+ }
}
- // Not all expressions in the set should be added. We should filter out
the related
- // children nodes.
- val commonExprSet = candidateExprs.filter { candidateExpr =>
- candidateExprs.forall { expr =>
- expr == candidateExpr ||
expr.e.find(_.semanticEquals(candidateExpr.e)).isEmpty
+ localEquivalenceMap.foreach { case (commonExpr, state) =>
+ val possibleParents = localEquivalenceMap.filter { case (_, v) =>
v.height > state.height }
+ val notChild = possibleParents.forall { case (k, _) =>
+ k == commonExpr || k.e.find(_.semanticEquals(commonExpr.e)).isEmpty
+ }
+ if (notChild) {
+ // `commonExpr` appears in every expression in `exprs`, so we need to
call `addExprToMap`
+ // `exprs.length` times, to make `useCount` accurate.
+ exprs.indices.foreach(_ => addExprToMap(commonExpr.e, map))
Review comment:
Won't `a + b + c` only be executed once no matter what? I think that's
why it's not currently considered a subexpression by itself, only if that
expression is also seen elsewhere and executed at least twice
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
