(datafusion-comet) branch main updated: Avoid rewriting join to unsupported join (#1888)

[ag...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git


The following commit(s) were added to refs/heads/main by this push:
     new 9947e8867 Avoid rewriting join to unsupported join (#1888)
9947e8867 is described below

commit 9947e88677fe340702a3f757f14f613819a539d4
Author: Andy Grove <ag...@apache.org>
AuthorDate: Wed Jun 18 15:15:27 2025 -0600

    Avoid rewriting join to unsupported join (#1888)
---
 spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala    | 7 +++----
 spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala | 1 +
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala b/spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala
index 6dd102352..032ace734 100644
--- a/spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala
+++ b/spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala
@@ -20,7 +20,7 @@
 package org.apache.comet.rules
 
 import org.apache.spark.sql.catalyst.optimizer.{BuildLeft, BuildRight, BuildSide, JoinSelectionHelper}
-import org.apache.spark.sql.catalyst.plans.LeftSemi
+import org.apache.spark.sql.catalyst.plans.LeftAnti
 import org.apache.spark.sql.catalyst.plans.logical.Join
 import org.apache.spark.sql.execution.{SortExec, SparkPlan}
 import org.apache.spark.sql.execution.joins.{ShuffledHashJoinExec, SortMergeJoinExec}
@@ -65,9 +65,8 @@ object RewriteJoin extends JoinSelectionHelper {
   def rewrite(plan: SparkPlan): SparkPlan = plan match {
     case smj: SortMergeJoinExec =>
       getSmjBuildSide(smj) match {
-        case Some(BuildRight) if smj.joinType == LeftSemi =>
-          // TODO this was added as a workaround for TPC-DS q14 hanging and needs
-          // further investigation
+        case Some(BuildRight) if smj.joinType == LeftAnti =>
+          // https://github.com/apache/datafusion-comet/issues/457
           plan
         case Some(buildSide) =>
           ShuffledHashJoinExec(
diff --git a/spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala b/spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala
index 229ff032a..462edf91b 100644
--- a/spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala
+++ b/spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala
@@ -2592,6 +2592,7 @@ object QueryPlanSerde extends Logging with CometExprShim {
         }
 
         if (join.buildSide == BuildRight && join.joinType == LeftAnti) {
+          // https://github.com/apache/datafusion-comet/issues/457
           withInfo(join, "BuildRight with LeftAnti is not supported")
           return None
         }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org