Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/21103#discussion_r205967625 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala --- @@ -3968,3 +3964,242 @@ object ArrayUnion { new GenericArrayData(arrayBuffer) } } + +/** + * Returns an array of the elements in the intersect of x and y, without duplicates + */ +@ExpressionDescription( + usage = """ + _FUNC_(array1, array2) - Returns an array of the elements in array1 but not in array2, + without duplicates. + """, + examples = """ + Examples: + > SELECT _FUNC_(array(1, 2, 3), array(1, 3, 5)); + array(2) + """, + since = "2.4.0") +case class ArrayExcept(left: Expression, right: Expression) extends ArraySetLike + with ComplexTypeMergingExpression { + override def dataType: DataType = { + dataTypeCheck + left.dataType + } + + @transient lazy val evalExcept: (ArrayData, ArrayData) => ArrayData = { + if (elementTypeSupportEquals) { + (array1, array2) => + val hs = new OpenHashSet[Any] --- End diff -- I would be strongly in favor of just using `MemoryBlock` for binary types, or something similar.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org