Skip to content

[SPARK-30973][SQL]ScriptTransformationExec should wait for the termination #28098

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
AngersZhuuuu wants to merge 1 commit into from
Closed

[SPARK-30973][SQL]ScriptTransformationExec should wait for the termination #28098

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformationExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,6 +132,7 @@ case class ScriptTransformationExec(
lazy val unwrappers = outputSoi.getAllStructFieldRefs.asScala.map(unwrapperFor)

private def checkFailureAndPropagate(cause: Throwable = null): Unit = {
proc.waitFor()
if (writerThread.exception.isDefined) {
throw writerThread.exception.get
}
Expand Down
22 changes: 22 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/ScriptTransformationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,6 +172,28 @@ class ScriptTransformationSuite extends SparkPlanTest with SQLTestUtils with Tes
assert(uncaughtExceptionHandler.exception.isEmpty)
}


test("SPARK-30973 ScriptTransformationExec should wait for the termination") {
(0 until 10).foreach { index =>
assume(TestUtils.testCommandAvailable("/bin/bash"))

val rowsDf = Seq("a", "b", "c").map(Tuple1.apply).toDF("a")

val e = intercept[SparkException] {
val plan =
new ScriptTransformationExec(
input = Seq(rowsDf.col("a").expr),
script = "some_non_existent_command",
output = Seq(AttributeReference("a", StringType)()),
child = rowsDf.queryExecution.sparkPlan,
ioschema = noSerdeIOSchema)
SparkPlanTest.executePlan(plan, hiveContext)
}
assert(e.getMessage.contains("Subprocess exited with status"))
assert(uncaughtExceptionHandler.exception.isEmpty)
}
}

test("SPARK-24339 verify the result after pruning the unused columns") {
val rowsDf = Seq(
("Bob", 16, 176),
Expand Down