Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21050#discussion_r196654969
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -2355,3 +2356,281 @@ case class ArrayRemove(left: Expression, right:
Expression)
override def prettyName: String = "array_remove"
}
+
+/**
+ * Removes duplicate values from the array.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(array) - Removes duplicate values from the array.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3, null, 3));
+ [1,2,3,null]
+ """, since = "2.4.0")
+case class ArrayDistinct(child: Expression)
+ extends UnaryExpression with ExpectsInputTypes {
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(ArrayType)
+
+ override def dataType: DataType = child.dataType
+
+ @transient lazy val elementType: DataType =
dataType.asInstanceOf[ArrayType].elementType
+
+ @transient private lazy val ordering: Ordering[Any] =
+ TypeUtils.getInterpretedOrdering(elementType)
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ super.checkInputDataTypes() match {
+ case f: TypeCheckResult.TypeCheckFailure => f
+ case TypeCheckResult.TypeCheckSuccess =>
+ TypeUtils.checkForOrderingExpr(elementType, s"function
$prettyName")
+ }
+ }
+
+ @transient private lazy val elementTypeSupportEquals = elementType match
{
+ case BinaryType => false
+ case _: AtomicType => true
+ case _ => false
+ }
+
+ override def nullSafeEval(array: Any): Any = {
+ val data = array.asInstanceOf[ArrayData].toArray[AnyRef](elementType)
+ if (elementTypeSupportEquals) {
+ new GenericArrayData(data.distinct.asInstanceOf[Array[Any]])
+ } else {
+ var foundNullElement = false
+ var pos = 0
+ for(i <- 0 until data.length) {
+ if (data(i) == null) {
+ if (!foundNullElement) {
+ foundNullElement = true
+ pos = pos + 1
+ }
+ } else {
+ var j = 0
+ var done = false
+ while (j <= i && !done) {
+ if (data(j) != null && ordering.equiv(data(j), data(i))) {
+ done = true
+ }
+ j = j + 1
+ }
+ if (i == j-1) {
+ pos = pos + 1
+ }
+ }
+ }
+ new GenericArrayData(data.slice(0, pos))
+ }
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ nullSafeCodeGen(ctx, ev, (array) => {
+ val i = ctx.freshName("i")
+ val j = ctx.freshName("j")
+ val sizeOfDistinctArray = ctx.freshName("sizeOfDistinctArray")
+ val getValue1 = CodeGenerator.getValue(array, elementType, i)
+ val getValue2 = CodeGenerator.getValue(array, elementType, j)
+ val foundNullElement = ctx.freshName("foundNullElement")
+ val openHashSet = classOf[OpenHashSet[_]].getName
+ val hs = ctx.freshName("hs")
+ val classTag = s"scala.reflect.ClassTag$$.MODULE$$.Object()"
+ if(elementTypeSupportEquals) {
--- End diff --
nit: `if (`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
