HyukjinKwon commented on a change in pull request #33323:
URL: https://github.com/apache/spark/pull/33323#discussion_r669261712
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
##########
@@ -956,6 +956,31 @@ class Dataset[T] private[sql](
join(right, Seq(usingColumn))
}
+ /**
+ * (Java-specific) Inner equi-join with another `DataFrame` using the given
columns.
+ *
+ * Different from other join functions, the join columns will only appear
once in the output,
+ * i.e. similar to SQL's `JOIN USING` syntax.
+ *
+ * {{{
+ * // Joining df1 and df2 using the columns "user_id" and "user_name"
+ * df1.join(df2, new String[] {"user_id", "user_name"});
+ * }}}
+ *
+ * @param right Right side of the join operation.
+ * @param usingColumns Names of the columns to join on. This columns must
exist on both sides.
+ *
+ * @note If you perform a self-join using this function without aliasing the
input
+ * `DataFrame`s, you will NOT be able to reference any columns after the
join, since
+ * there is no way to disambiguate which side of the join you would like to
reference.
+ *
+ * @group untypedrel
+ * @since 3.1.3
+ */
+ def join(right: Dataset[_], usingColumns: Array[String]): DataFrame = {
+ join(right, usingColumns.toSeq)
+ }
+
/**
* Inner equi-join with another `DataFrame` using the given columns.
Review comment:
Can you add "(Scala-specific)" here?
--
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
