Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21050#discussion_r185731095
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -1059,3 +1059,96 @@ case class Flatten(child: Expression) extends
UnaryExpression {
override def prettyName: String = "flatten"
}
+
+/**
+ * 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
+
+ override def nullSafeEval(array: Any): Any = {
+ val elementType = child.dataType.asInstanceOf[ArrayType].elementType
+ val data =
array.asInstanceOf[ArrayData].toArray[AnyRef](elementType).distinct
+ new GenericArrayData(data.asInstanceOf[Array[Any]])
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val elementType = dataType.asInstanceOf[ArrayType].elementType
+ nullSafeCodeGen(ctx, ev, (array) => {
+ val arrayClass = classOf[GenericArrayData].getName
+ val distinctArray = ctx.freshName("distinctArray")
+ val i = ctx.freshName("i")
+ val j = ctx.freshName("j")
+ val pos = ctx.freshName("arrayPosition")
+ val getValue1 = CodeGenerator.getValue(array, elementType, i)
+ val getValue2 = CodeGenerator.getValue(array, elementType, j)
+ s"""
+ |int $pos = 0;
+ |for (int $i = 0; $i < $array.numElements(); $i ++) {
--- End diff --
I guess nested loop must be very slow. Can you use a hash table or
something to check duplication? Maybe `OpenHashSet`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
