Skip to content

[SPARK-18147][SQL] do not fail for very complex aggregator result type #15807

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
wants to merge 1 commit into from
Closed

[SPARK-18147][SQL] do not fail for very complex aggregator result type #15807

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
21 changes: 21 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,19 @@ object NullResultAgg extends Aggregator[AggData, AggData, AggData] {
override def outputEncoder: Encoder[AggData] = Encoders.product[AggData]
}

case class ComplexAggData(d1: AggData, d2: AggData)

object VeryComplexResultAgg extends Aggregator[Row, String, ComplexAggData] {
override def zero: String = ""
override def reduce(buffer: String, input: Row): String = buffer + input.getString(1)
override def merge(b1: String, b2: String): String = b1 + b2
override def finish(reduction: String): ComplexAggData = {
ComplexAggData(AggData(reduction.length, reduction), AggData(reduction.length, reduction))
}
override def bufferEncoder: Encoder[String] = Encoders.STRING
override def outputEncoder: Encoder[ComplexAggData] = Encoders.product[ComplexAggData]
}


class DatasetAggregatorSuite extends QueryTest with SharedSQLContext {
import testImplicits._
Expand Down Expand Up @@ -312,4 +325,12 @@ class DatasetAggregatorSuite extends QueryTest with SharedSQLContext {
val ds3 = sql("SELECT 'Some String' AS b, 1279869254 AS a").as[AggData]
assert(ds3.select(NameAgg.toColumn).schema.head.nullable === true)
}

test("SPARK-18147: very complex aggregator result type") {
val df = Seq(1 -> "a", 2 -> "b", 2 -> "c").toDF("i", "j")

checkAnswer(
df.groupBy($"i").agg(VeryComplexResultAgg.toColumn),
Row(1, Row(Row(1, "a"), Row(1, "a"))) :: Row(2, Row(Row(2, "bc"), Row(2, "bc"))) :: Nil)
}
}