Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/20858#discussion_r177007456 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala --- @@ -287,3 +289,152 @@ case class ArrayContains(left: Expression, right: Expression) override def prettyName: String = "array_contains" } + +/** + * Concatenates multiple arrays into one. + */ +@ExpressionDescription( + usage = "_FUNC_(expr, ...) - Concatenates multiple arrays into one.", + examples = """ + Examples: + > SELECT _FUNC_(array(1, 2, 3), array(4, 5), array(6)); + [1,2,3,4,5,6] + """) +case class ConcatArrays(children: Seq[Expression]) extends Expression with NullSafeEvaluation { + + override def checkInputDataTypes(): TypeCheckResult = { + val arrayCheck = checkInputDataTypesAreArrays + if(arrayCheck.isFailure) arrayCheck + else TypeUtils.checkForSameTypeInputExpr(children.map(_.dataType), s"function $prettyName") + } + + private def checkInputDataTypesAreArrays(): TypeCheckResult = + { + val mismatches = children.zipWithIndex.collect { + case (child, idx) if !ArrayType.acceptsType(child.dataType) => + s"argument ${idx + 1} has to be ${ArrayType.simpleString} type, " + + s"however, '${child.sql}' is of ${child.dataType.simpleString} type." + } + + if (mismatches.isEmpty) { + TypeCheckResult.TypeCheckSuccess + } else { + TypeCheckResult.TypeCheckFailure(mismatches.mkString(" ")) + } + } + + override def dataType: ArrayType = + children + .headOption.map(_.dataType.asInstanceOf[ArrayType]) + .getOrElse(ArrayType.defaultConcreteType.asInstanceOf[ArrayType]) --- End diff -- Should we allow empty children? I can't think of a use case for now and we should better disallow it first.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org