Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/21109#discussion_r188264496
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
---
@@ -131,13 +134,101 @@ object ExtractEquiJoinKeys extends Logging with
PredicateHelper {
if (joinKeys.nonEmpty) {
val (leftKeys, rightKeys) = joinKeys.unzip
- logDebug(s"leftKeys:$leftKeys | rightKeys:$rightKeys")
- Some((joinType, leftKeys, rightKeys,
otherPredicates.reduceOption(And), left, right))
+
+ // Find any simple range expressions between two columns
+ // (and involving only those two columns)
+ // of the two tables being joined,
+ // which are not used in the equijoin expressions,
+ // and which can be used for secondary sort optimizations.
+ val rangePreds: mutable.Set[Expression] = mutable.Set.empty
+ var rangeConditions: Seq[BinaryComparison] =
+ if (SQLConf.get.useSmjInnerRangeOptimization) { // &&
SQLConf.get.wholeStageEnabled) {
+ otherPredicates.flatMap {
+ case p@LessThan(l, r) => isValidRangeCondition(l, r, left,
right, joinKeys) match {
+ case "asis" => rangePreds.add(p); Some(LessThan(l, r))
+ case "vs" => rangePreds.add(p); Some(GreaterThan(r, l))
+ case _ => None
+ }
+ case p@LessThanOrEqual(l, r) =>
+ isValidRangeCondition(l, r, left, right, joinKeys) match {
+ case "asis" => rangePreds.add(p);
Some(LessThanOrEqual(l, r))
+ case "vs" => rangePreds.add(p);
Some(GreaterThanOrEqual(r, l))
+ case _ => None
+ }
+ case p@GreaterThan(l, r) => isValidRangeCondition(l, r,
left, right, joinKeys) match {
+ case "asis" => rangePreds.add(p); Some(GreaterThan(l, r))
+ case "vs" => rangePreds.add(p); Some(LessThan(r, l))
+ case _ => None
+ }
+ case p@GreaterThanOrEqual(l, r) =>
+ isValidRangeCondition(l, r, left, right, joinKeys) match {
+ case "asis" => rangePreds.add(p);
Some(GreaterThanOrEqual(l, r))
+ case "vs" => rangePreds.add(p); Some(LessThanOrEqual(r,
l))
+ case _ => None
+ }
+ case _ => None
+ }
+ }
--- End diff --
nit: `} else {`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
