ChenMichael commented on a change in pull request #34036:
URL: https://github.com/apache/spark/pull/34036#discussion_r714473203
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/ExplainSuite.scala
##########
@@ -704,6 +704,31 @@ class ExplainSuiteAE extends ExplainSuiteHelper with
EnableAdaptiveExecutionSuit
"Bucketed: false (bucket column(s) not read)")
}
}
+
+ test("SPARK-36795: Node IDs should not be duplicated when InMemoryRelation
Present") {
+ withTempView("t1", "t2") {
+ Seq(1).toDF("k").write.saveAsTable("t1")
+ Seq(1).toDF("key").write.saveAsTable("t2")
+ spark.sql("SELECT * FROM t1").persist()
+ val query = "SELECT * FROM (SELECT * FROM t1) join t2 " +
+ "ON k = t2.key"
+ val df = sql(query).toDF()
+
+ df.collect()
+ checkKeywordsExistsInExplain(df, FormattedMode,
+ """ * BroadcastHashJoin Inner BuildLeft (12)
+ | :- BroadcastQueryStage (8)
+ | : +- BroadcastExchange (7)
+ | : +- * Filter (6)
+ | : +- * ColumnarToRow (5)
Review comment:
Ok. changed the test to regex that extracts the node ids and asserts
they are different.
--
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]
