Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/21103#discussion_r205310335
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -3805,3 +3799,330 @@ 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 = left.dataType
+
+ 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 notFoundNullElement = true
+ var i = 0
+ while (i < array2.numElements()) {
+ if (array2.isNullAt(i)) {
+ notFoundNullElement = false
+ } else {
+ val assigned = if (!isLongType) {
+ hsInt.add(array2.getInt(i))
+ } else {
+ hsLong.add(array2.getLong(i))
+ }
+ }
+ i += 1
+ }
+ var pos = 0
+ i = 0
+ while (i < array1.numElements()) {
+ if (array1.isNullAt(i)) {
+ if (notFoundNullElement) {
+ if (resultArray != null) {
+ resultArray.setNullAt(pos)
+ }
+ pos += 1
+ notFoundNullElement = false
+ }
+ } else {
+ val assigned = if (!isLongType) {
+ assignInt(array1, i, resultArray, pos)
+ } else {
+ assignLong(array1, i, resultArray, pos)
+ }
+ if (assigned) {
+ pos += 1
+ }
+ }
+ i += 1
+ }
+ pos
+ }
+
+ override def nullSafeEval(input1: Any, input2: Any): Any = {
+ val array1 = input1.asInstanceOf[ArrayData]
+ val array2 = input2.asInstanceOf[ArrayData]
+
+ if (elementTypeSupportEquals) {
+ elementType match {
+ case IntegerType =>
+ // avoid boxing of primitive int array elements
+ // calculate result array size
+ hsInt = new OpenHashSet[Int]
+ val elements = evalIntLongPrimitiveType(array1, array2, null,
false)
+ // allocate result array
+ hsInt = new OpenHashSet[Int]
+ val resultArray = if (UnsafeArrayData.shouldUseGenericArrayData(
+ IntegerType.defaultSize, elements)) {
+ new GenericArrayData(new Array[Any](elements))
+ } else {
+ UnsafeArrayData.forPrimitiveArray(
+ Platform.INT_ARRAY_OFFSET, elements, IntegerType.defaultSize)
+ }
+ // assign elements into the result array
+ evalIntLongPrimitiveType(array1, array2, resultArray, false)
+ resultArray
+ case LongType =>
+ // avoid boxing of primitive long array elements
+ // calculate result array size
+ hsLong = new OpenHashSet[Long]
+ val elements = evalIntLongPrimitiveType(array1, array2, null,
true)
+ // allocate result array
+ hsLong = new OpenHashSet[Long]
+ val resultArray = if (UnsafeArrayData.shouldUseGenericArrayData(
+ LongType.defaultSize, elements)) {
+ new GenericArrayData(new Array[Any](elements))
+ } else {
+ UnsafeArrayData.forPrimitiveArray(
+ Platform.LONG_ARRAY_OFFSET, elements, LongType.defaultSize)
+ }
+ // assign elements into the result array
+ evalIntLongPrimitiveType(array1, array2, resultArray, true)
+ resultArray
+ case _ =>
+ val hs = new OpenHashSet[Any]
+ var exceptNullElement = true
--- End diff --
Good catch, thanks
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
