Github user huaxingao commented on a diff in the pull request: https://github.com/apache/spark/pull/21050#discussion_r189357494 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala --- @@ -1882,3 +1882,141 @@ case class ArrayRepeat(left: Expression, right: Expression) } } + +/** + * 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 + + lazy val elementType: DataType = dataType.asInstanceOf[ArrayType].elementType + + 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 = { + nullSafeCodeGen(ctx, ev, (array) => { + val i = ctx.freshName("i") + val j = ctx.freshName("j") + val hs = ctx.freshName("hs") + val distinctArrayLen = ctx.freshName("distinctArrayLen") + val getValue = CodeGenerator.getValue(array, elementType, i) + val openHashSet = classOf[OpenHashSet[_]].getName + val classTag = s"scala.reflect.ClassTag$$.MODULE$$.Object()" + s""" + |int $distinctArrayLen = 0; + |$openHashSet $hs = new $openHashSet($classTag); + |for (int $i = 0; $i < $array.numElements(); $i++) { + | if ($array.isNullAt($i)) { + | int $j; --- End diff -- @kiszk Thanks for your comment. I have changed the code.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org