asfgit closed pull request #23349: [SPARK-26403][SQL] Support pivoting using
array column for `pivot(column)` API
URL: https://github.com/apache/spark/pull/23349
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
index 34d252886ffb0..48beffa18a551 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
@@ -67,6 +67,7 @@ object Literal {
case t: Timestamp => Literal(DateTimeUtils.fromJavaTimestamp(t),
TimestampType)
case d: Date => Literal(DateTimeUtils.fromJavaDate(d), DateType)
case a: Array[Byte] => Literal(a, BinaryType)
+ case a: collection.mutable.WrappedArray[_] => apply(a.array)
case a: Array[_] =>
val elementType = componentTypeToDataType(a.getClass.getComponentType())
val dataType = ArrayType(elementType)
diff --git
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/LiteralExpressionSuite.scala
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/LiteralExpressionSuite.scala
index 3ea6bfac9ddca..133aaa449ea44 100644
---
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/LiteralExpressionSuite.scala
+++
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/LiteralExpressionSuite.scala
@@ -179,6 +179,8 @@ class LiteralExpressionSuite extends SparkFunSuite with
ExpressionEvalHelper {
checkArrayLiteral(Array("a", "b", "c"))
checkArrayLiteral(Array(1.0, 4.0))
checkArrayLiteral(Array(CalendarInterval.MICROS_PER_DAY,
CalendarInterval.MICROS_PER_HOUR))
+ val arr = collection.mutable.WrappedArray.make(Array(1.0, 4.0))
+ checkEvaluation(Literal(arr), toCatalyst(arr))
}
test("seq") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFramePivotSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFramePivotSuite.scala
index b52ca58c07d27..8c2c11be9b6fd 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFramePivotSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFramePivotSuite.scala
@@ -333,4 +333,15 @@ class DataFramePivotSuite extends QueryTest with
SharedSQLContext {
}
assert(exception.getMessage.contains("Unsupported literal type"))
}
+
+ test("SPARK-26403: pivoting by array column") {
+ val df = Seq(
+ (2, Seq.empty[String]),
+ (2, Seq("a", "x")),
+ (3, Seq.empty[String]),
+ (3, Seq("a", "x"))).toDF("x", "s")
+ val expected = Seq((3, 1, 1), (2, 1, 1)).toDF
+ val actual = df.groupBy("x").pivot("s").count()
+ checkAnswer(actual, expected)
+ }
}
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
