beliefer commented on code in PR #40275:
URL: https://github.com/apache/spark/pull/40275#discussion_r1125652836
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/functions.scala:
##########
@@ -1228,6 +1228,22 @@ object functions {
def map_from_arrays(keys: Column, values: Column): Column =
Column.fn("map_from_arrays", keys, values)
+ /**
+ * Marks a DataFrame as small enough for use in broadcast joins.
+ *
+ * The following example marks the right DataFrame for broadcast hash join
using `joinKey`.
+ * {{{
+ * // left and right are DataFrames
+ * left.join(broadcast(right), "joinKey")
+ * }}}
+ *
+ * @group normal_funcs
+ * @since 3.4.0
+ */
+ def broadcast[T](df: Dataset[T]): Dataset[T] = {
+ df.hint("broadcast")
Review Comment:
Yes.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
