Skip to content

[SPARK-30082][SQL][2.4] Depend on Scala type coercion when building replace query #26749

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
johnhany97 wants to merge 1 commit into from
Closed

[SPARK-30082][SQL][2.4] Depend on Scala type coercion when building replace query #26749

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
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/DataFrameNaFunctions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,7 +455,7 @@ final class DataFrameNaFunctions private[sql](df: DataFrame) {
val keyExpr = df.col(col.name).expr
def buildExpr(v: Any) = Cast(Literal(v), keyExpr.dataType)
val branches = replacementMap.flatMap { case (source, target) =>
Seq(buildExpr(source), buildExpr(target))
Seq(Literal(source), buildExpr(target))
}.toSeq
new Column(CaseKeyWhen(keyExpr, branches :+ keyExpr)).as(col.name)
}
Expand Down
44 changes: 44 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DataFrameNaFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,14 @@ class DataFrameNaFunctionsSuite extends QueryTest with SharedSQLContext {
).toDF("name", "age", "height")
}

def createNaNDF(): DataFrame = {
Seq[(java.lang.Integer, java.lang.Long, java.lang.Short,
java.lang.Byte, java.lang.Float, java.lang.Double)](
(1, 1L, 1.toShort, 1.toByte, 1.0f, 1.0),
(0, 0L, 0.toShort, 0.toByte, Float.NaN, Double.NaN)
).toDF("int", "long", "short", "byte", "float", "double")
}

test("drop") {
val input = createDF()
val rows = input.collect()
Expand Down Expand Up @@ -305,4 +313,40 @@ class DataFrameNaFunctionsSuite extends QueryTest with SharedSQLContext {
)).na.drop("name" :: Nil).select("name"),
Row("Alice") :: Row("David") :: Nil)
}

test("replace nan with float") {
checkAnswer(
createNaNDF().na.replace("*", Map(
Float.NaN -> 10.0f
)),
Row(1, 1L, 1.toShort, 1.toByte, 1.0f, 1.0) ::
Row(0, 0L, 0.toShort, 0.toByte, 10.0f, 10.0) :: Nil)
}

test("replace nan with double") {
checkAnswer(
createNaNDF().na.replace("*", Map(
Double.NaN -> 10.0
)),
Row(1, 1L, 1.toShort, 1.toByte, 1.0f, 1.0) ::
Row(0, 0L, 0.toShort, 0.toByte, 10.0f, 10.0) :: Nil)
}

test("replace float with nan") {
checkAnswer(
createNaNDF().na.replace("*", Map(
1.0f -> Float.NaN
)),
Row(0, 0L, 0.toShort, 0.toByte, Float.NaN, Double.NaN) ::
Row(0, 0L, 0.toShort, 0.toByte, Float.NaN, Double.NaN) :: Nil)
}

test("replace double with nan") {
checkAnswer(
createNaNDF().na.replace("*", Map(
1.0 -> Double.NaN
)),
Row(0, 0L, 0.toShort, 0.toByte, Float.NaN, Double.NaN) ::
Row(0, 0L, 0.toShort, 0.toByte, Float.NaN, Double.NaN) :: Nil)
}
}