From 611dbce4bdd6f34ac1fa67d8dfa3d407600a0237 Mon Sep 17 00:00:00 2001
From: Luciano Resende <lresende@apache.org>
Date: Thu, 7 Apr 2016 08:35:00 +0800
Subject: [PATCH] [SPARK-12555][SQL] Result should not be corrupted after input
columns are reordered
This PR add test case described in SPARK-12555 to validate that correct data is returned when input data is reordered and to avoid future regressions.
Author: Luciano Resende <lresende@apache.org>
Closes #11623 from lresende/SPARK-12555.
---
.../spark/sql/DatasetAggregatorSuite.scala | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
index 5430aff6ce..08b3389ad9 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
@@ -84,6 +84,16 @@ object ComplexBufferAgg extends Aggregator[AggData, (Int, AggData), Int] {
(b1._1 + b2._1, b1._2)
}
+object NameAgg extends Aggregator[AggData, String, String] {
+ def zero: String = ""
+
+ def reduce(b: String, a: AggData): String = a.b + b
+
+ def merge(b1: String, b2: String): String = b1 + b2
+
+ def finish(r: String): String = r
+}
+
class DatasetAggregatorSuite extends QueryTest with SharedSQLContext {
import testImplicits._
@@ -176,4 +186,13 @@ class DatasetAggregatorSuite extends QueryTest with SharedSQLContext {
typed.avg(_._2), typed.count(_._2), typed.sum(_._2), typed.sumLong(_._2)),
("a", 2.0, 2L, 4.0, 4L), ("b", 3.0, 1L, 3.0, 3L))
}
+
+ test("SPARK-12555 - result should not be corrupted after input columns are reordered") {
+ val ds = sql("SELECT 'Some String' AS b, 1279869254 AS a").as[AggData]
+
+ checkDataset(
+ ds.groupByKey(_.a).agg(NameAgg.toColumn),
+ (1279869254, "Some String"))
+ }
+
}
--
GitLab