Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/18810#discussion_r132611289
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala
---
@@ -149,4 +150,56 @@ class WholeStageCodegenSuite extends SparkPlanTest
with SharedSQLContext {
assert(df.collect() === Array(Row(1), Row(2)))
}
}
+
+ def genGroupByCodeGenContext(caseNum: Int, maxLinesPerFunction: Int):
CodegenContext = {
+ val caseExp = (1 to caseNum).map { i =>
+ s"case when id > $i and id <= ${i + 1} then 1 else 0 end as v$i"
+ }.toList
+
+ spark.conf.set("spark.sql.codegen.maxLinesPerFunction",
maxLinesPerFunction)
+
+ val keyExp = List(
+ "id",
+ "(id & 1023) as k1",
+ "cast(id & 1023 as double) as k2",
+ "cast(id & 1023 as int) as k3"
+ )
+
+ val ds = spark.range(10)
+ .selectExpr(keyExp:::caseExp: _*)
+ .groupBy("k1", "k2", "k3")
+ .sum()
+ val plan = ds.queryExecution.executedPlan
+
+ val wholeStageCodeGenExec = plan.find(p => p match {
+ case wp: WholeStageCodegenExec => wp.child match {
+ case hp: HashAggregateExec if (hp.child.isInstanceOf[ProjectExec])
=> true
+ case _ => false
+ }
+ case _ => false
+ })
+
+ assert(wholeStageCodeGenExec.isDefined)
+
wholeStageCodeGenExec.get.asInstanceOf[WholeStageCodegenExec].doCodeGen()._1
+ }
+
+ test("SPARK-21603 check there is a too long generated function") {
+ val ctx = genGroupByCodeGenContext(30, 1500)
+ assert(ctx.isTooLongGeneratedFunction === true)
+ }
+
+ test("SPARK-21603 check there is not a too long generated function") {
+ val ctx = genGroupByCodeGenContext(1, 1500)
+ assert(ctx.isTooLongGeneratedFunction === false)
+ }
+
+ test("SPARK-21603 check there is not a too long generated function when
threshold is Int.Max") {
+ val ctx = genGroupByCodeGenContext(30, Int.MaxValue)
+ assert(ctx.isTooLongGeneratedFunction === false)
+ }
+
+ test("SPARK-21603 check there is not a too long generated function when
threshold is 0") {
--- End diff --
`there is not a ...` -> `there is a`
---
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
