dtenedor commented on code in PR #49237:
URL: https://github.com/apache/spark/pull/49237#discussion_r1894421035
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:
##########
@@ -229,16 +232,20 @@ case class Uniform(min: Expression, max: Expression,
seedExpression: Expression,
if Seq(first, second).forall(integer) => IntegerType
case (_, ShortType) | (ShortType, _)
if Seq(first, second).forall(integer) => ShortType
+ case (_, ByteType) | (ByteType, _)
+ if Seq(first, second).forall(integer) => ByteType
case (_, DoubleType) | (DoubleType, _) => DoubleType
case (_, FloatType) | (FloatType, _) => FloatType
+ case (_, d: DecimalType) => d
+ case (d: DecimalType, _) => d
case _ =>
throw SparkException.internalError(
s"Unexpected argument data types: ${min.dataType}, ${max.dataType}")
}
}
private def integer(t: DataType): Boolean = t match {
- case _: ShortType | _: IntegerType | _: LongType => true
+ case _: ByteType | _: ShortType | _: IntegerType | _: LongType => true
Review Comment:
I ended up just updating this to use the `ExpectsInputTypes` trait to
simplify this code.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:
##########
@@ -229,16 +232,20 @@ case class Uniform(min: Expression, max: Expression,
seedExpression: Expression,
if Seq(first, second).forall(integer) => IntegerType
case (_, ShortType) | (ShortType, _)
Review Comment:
Good idea, this is done.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:
##########
@@ -229,16 +232,20 @@ case class Uniform(min: Expression, max: Expression,
seedExpression: Expression,
if Seq(first, second).forall(integer) => IntegerType
case (_, ShortType) | (ShortType, _)
if Seq(first, second).forall(integer) => ShortType
+ case (_, ByteType) | (ByteType, _)
+ if Seq(first, second).forall(integer) => ByteType
case (_, DoubleType) | (DoubleType, _) => DoubleType
case (_, FloatType) | (FloatType, _) => FloatType
+ case (_, d: DecimalType) => d
Review Comment:
Good idea, this is done.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:
##########
@@ -229,16 +232,20 @@ case class Uniform(min: Expression, max: Expression,
seedExpression: Expression,
if Seq(first, second).forall(integer) => IntegerType
case (_, ShortType) | (ShortType, _)
if Seq(first, second).forall(integer) => ShortType
+ case (_, ByteType) | (ByteType, _)
+ if Seq(first, second).forall(integer) => ByteType
case (_, DoubleType) | (DoubleType, _) => DoubleType
case (_, FloatType) | (FloatType, _) => FloatType
+ case (_, d: DecimalType) => d
+ case (d: DecimalType, _) => d
Review Comment:
Good idea, this is done.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala:
##########
@@ -49,6 +49,9 @@ trait RDG extends Expression with ExpressionWithRandomSeed {
@transient protected lazy val seed: Long = seedExpression match {
case e if e.dataType == IntegerType => e.eval().asInstanceOf[Int]
case e if e.dataType == LongType => e.eval().asInstanceOf[Long]
+ case e if e.dataType == FloatType => e.eval().asInstanceOf[Float].toLong
+ case e if e.dataType == DoubleType => e.eval().asInstanceOf[Double].toLong
+ case e if e.dataType.isInstanceOf[DecimalType] =>
e.eval().asInstanceOf[Decimal].toLong
Review Comment:
I checked and the existing `RAND` and `RANDN` functions only accept
`IntegerType` or `LongType` for the random seed (but positive, zero, and
negative values are allowed). I updated this PR to be consistent with that.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
