Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/21103#discussion_r204613831
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -3805,3 +3799,331 @@ 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 {
+ override def dataType: DataType =
+ ArrayType(elementType,
left.dataType.asInstanceOf[ArrayType].containsNull)
+
+ var hsInt: OpenHashSet[Int] = _
+ var hsLong: OpenHashSet[Long] = _
+
+ def assignInt(array: ArrayData, idx: Int, resultArray: ArrayData, pos:
Int): Boolean = {
+ val elem = array.getInt(idx)
+ if (!hsInt.contains(elem)) {
+ if (resultArray != null) {
+ resultArray.setInt(pos, elem)
+ }
+ hsInt.add(elem)
+ true
+ } else {
+ false
+ }
+ }
+
+ def assignLong(array: ArrayData, idx: Int, resultArray: ArrayData, pos:
Int): Boolean = {
+ val elem = array.getLong(idx)
+ if (!hsLong.contains(elem)) {
+ if (resultArray != null) {
+ resultArray.setLong(pos, elem)
+ }
+ hsLong.add(elem)
+ true
+ } else {
+ false
+ }
+ }
+
+ def evalIntLongPrimitiveType(
+ array1: ArrayData,
+ array2: ArrayData,
+ resultArray: ArrayData,
+ isLongType: Boolean): Int = {
+ // store elements into resultArray
+ var exceptNullElement = true
--- End diff --
Ah, I mean `nullElement` for Array`except`. I will rename this to a better
name.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
