Github user dilipbiswal commented on a diff in the pull request:
https://github.com/apache/spark/pull/17330#discussion_r110977330
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/CachedTableSuite.scala ---
@@ -670,4 +677,139 @@ class CachedTableSuite extends QueryTest with
SQLTestUtils with SharedSQLContext
assert(spark.read.parquet(path).filter($"id" > 4).count() == 15)
}
}
+
+ test("SPARK-19993 simple subquery caching") {
+ withTempView("t1", "t2") {
+ Seq(1).toDF("c1").createOrReplaceTempView("t1")
+ Seq(1).toDF("c1").createOrReplaceTempView("t2")
+
+ sql(
+ """
+ |SELECT * FROM t1
+ |WHERE
+ |NOT EXISTS (SELECT * FROM t1)
+ """.stripMargin).cache()
+
+ val cachedDs =
+ sql(
+ """
+ |SELECT * FROM t1
+ |WHERE
+ |NOT EXISTS (SELECT * FROM t1)
+ """.stripMargin)
+ assert(getNumInMemoryRelations(cachedDs) == 1)
+
+ // Additional predicate in the subquery plan should cause a cache
miss
+ val cachedMissDs =
+ sql(
+ """
+ |SELECT * FROM t1
+ |WHERE
+ |NOT EXISTS (SELECT * FROM t1 where c1 = 0)
+ """.stripMargin)
+ assert(getNumInMemoryRelations(cachedMissDs) == 0)
+ }
+ }
+
+ test("SPARK-19993 subquery caching with correlated predicates") {
+ withTempView("t1", "t2") {
+ Seq(1).toDF("c1").createOrReplaceTempView("t1")
+ Seq(1).toDF("c1").createOrReplaceTempView("t2")
+
+ // Simple correlated predicate in subquery
+ sql(
+ """
+ |SELECT * FROM t1
+ |WHERE
+ |t1.c1 in (SELECT t2.c1 FROM t2 where t1.c1 = t2.c1)
+ """.stripMargin).cache()
+
+ val cachedDs =
+ sql(
+ """
+ |SELECT * FROM t1
+ |WHERE
+ |t1.c1 in (SELECT t2.c1 FROM t2 where t1.c1 = t2.c1)
+ """.stripMargin)
+ assert(getNumInMemoryRelations(cachedDs) == 1)
+ }
+ }
+
+ test("SPARK-19993 subquery with cached underlying relation") {
+ withTempView("t1", "t2") {
+ Seq(1).toDF("c1").createOrReplaceTempView("t1")
+ Seq(1).toDF("c1").createOrReplaceTempView("t2")
--- End diff --
@cloud-fan sorry... actually i had some of these tests combined and when i
split, i forgot to remove this. Will fix it.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
