From 34ca392da7097a1fbe48cd6c3ebff51453ca26ca Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Tue, 24 Nov 2015 14:51:01 -0800
Subject: [PATCH] Added a line of comment to explain why the extra sort exists
in pivot.
---
sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala b/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala
index ee7150cbbf..abd531c4ba 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala
@@ -304,7 +304,7 @@ class GroupedData protected[sql](
// Get the distinct values of the column and sort them so its consistent
val values = df.select(pivotColumn)
.distinct()
- .sort(pivotColumn)
+ .sort(pivotColumn) // ensure that the output columns are in a consistent logical order
.map(_.get(0))
.take(maxValues + 1)
.toSeq
--
GitLab