maropu commented on a change in pull request #25666: [SPARK-28962][SQL] Provide
index argument to filter lambda functions
URL: https://github.com/apache/spark/pull/25666#discussion_r330358827
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala
##########
@@ -369,6 +383,9 @@ case class ArrayFilter(
var i = 0
while (i < arr.numElements) {
elementVar.value.set(arr.get(i, elementVar.dataType))
+ if (indexVar.isDefined) {
Review comment:
I thought code like this;
```
@transient lazy val (elementVar, mayFillIndex) = function match {
case LambdaFunction(_, Seq(elemVar: NamedLambdaVariable), _) =>
(elemVar, (_: Int) => {})
case LambdaFunction(_, Seq(elemVar: NamedLambdaVariable, idxVar:
NamedLambdaVariable), _) =>
(elemVar, (i: Int) => idxVar.value.set(i))
}
override def nullSafeEval(inputRow: InternalRow, argumentValue: Any): Any
= {
val arr = argumentValue.asInstanceOf[ArrayData]
val f = functionForEval
val buffer = new mutable.ArrayBuffer[Any](arr.numElements)
var i = 0
while (i < arr.numElements) {
elementVar.value.set(arr.get(i, elementVar.dataType))
mayFillIndex(i)
if (f.eval(inputRow).asInstanceOf[Boolean]) {
buffer += elementVar.value.get
}
i += 1
}
new GenericArrayData(buffer)
}
```
----------------------------------------------------------------
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.
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]
