jiayuasu commented on code in PR #2871:
URL: https://github.com/apache/sedona/pull/2871#discussion_r3176092054
##########
spark/common/src/main/scala/org/apache/spark/sql/sedona_sql/strategy/join/JoinQueryDetector.scala:
##########
@@ -843,9 +886,33 @@ class JoinQueryDetector(sparkSession: SparkSession)
extends SparkStrategy {
.map { distanceExpr =>
matchDistanceExpressionToJoinSide(distanceExpr, left, right) match {
case Some(side) =>
- if (broadcastSide.get == side) (Some(distanceExpr), None)
- else if (distanceExpr.references.isEmpty) (Some(distanceExpr),
None)
- else (None, Some(distanceExpr))
+ if (geographyShape) {
+ // Geography distance joins read the per-row radius from the
stream-side
+ // GeographyJoinShape inside GeographyDistanceRefiner, so the
radius MUST
+ // be available on the streamed side. The stream-side expression
is later
+ // re-bound against `streamed.output` in BroadcastIndexJoinExec,
so we
+ // can only forward it to the stream side when it is either a
literal
+ // (no references) or already bound to the streamed side.
+ if (distanceExpr.references.isEmpty) {
+ // Literal: keep build-side expansion AND populate stream-side
radius.
+ (Some(distanceExpr), Some(distanceExpr))
Review Comment:
Does this PR expand both sides of the join (double expand)?
--
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]
