hvanhovell commented on code in PR #40581:
URL: https://github.com/apache/spark/pull/40581#discussion_r1160142283
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala:
##########
@@ -2468,6 +2470,110 @@ class Dataset[T] private[sql] (
*/
def transform[U](t: Dataset[T] => Dataset[U]): Dataset[U] = t(this)
+ /**
+ * (Scala-specific) Returns a new Dataset that only contains elements where
`func` returns
+ * `true`.
+ *
+ * @group typedrel
+ * @since 3.5.0
+ */
+ def filter(func: T => Boolean): Dataset[T] = {
+ val udf = ScalarUserDefinedFunction(
+ function = func,
+ inputEncoders = encoder :: Nil,
+ outputEncoder = PrimitiveBooleanEncoder)
+ sparkSession.newDataset[T](encoder) { builder =>
+ builder.getFilterBuilder
+ .setInput(plan.getRoot)
+ .setCondition(udf.apply(col("*")).expr)
+ }
+ }
+
+ /**
+ * (Java-specific) Returns a new Dataset that only contains elements where
`func` returns
+ * `true`.
+ *
+ * @group typedrel
+ * @since 3.5.0
+ */
+ def filter(f: FilterFunction[T]): Dataset[T] = {
+ filter(UdfUtils.filterFuncToScalaFunc(f))
+ }
+
+ /**
+ * (Scala-specific) Returns a new Dataset that contains the result of
applying `func` to each
+ * element.
+ *
+ * @group typedrel
+ * @since 3.5.0
+ */
+ def map[U: Encoder](f: T => U): Dataset[U] = {
+ mapPartitions(UdfUtils.mapFuncToMapPartitionsAdaptor(f))
+ }
+
+ /**
+ * (Java-specific) Returns a new Dataset that contains the result of
applying `func` to each
+ * element.
+ *
+ * @group typedrel
+ * @since 3.5.0
+ */
+ def map[U](f: MapFunction[T, U], encoder: Encoder[U]): Dataset[U] = {
+ map(UdfUtils.mapFunctionToScalaFunc(f))(encoder)
+ }
+
+ /**
+ * (Scala-specific) Returns a new Dataset that contains the result of
applying `func` to each
+ * partition.
+ *
+ * @group typedrel
+ * @since 3.5.0
+ */
+ def mapPartitions[U: Encoder](func: Iterator[T] => Iterator[U]): Dataset[U]
= {
+ val outputEncoder = encoderFor[U]
+ val udf = ScalarUserDefinedFunction(
+ function = func,
+ inputEncoders = encoder :: Nil,
+ outputEncoder = outputEncoder)
+ sparkSession.newDataset(outputEncoder) { builder =>
+ builder.getMapPartitionsBuilder
+ .setInput(plan.getRoot)
+ .setFunc(udf.apply().expr.getCommonInlineUserDefinedFunction)
Review Comment:
Nit we should also `col("*")` here to be consistent. I know that on the
server side we ignore this.
--
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]
