Github user chenghao-intel commented on a diff in the pull request: https://github.com/apache/spark/pull/16476#discussion_r95282465 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/conditionalExpressions.scala --- @@ -340,3 +344,102 @@ object CaseKeyWhen { CaseWhen(cases, elseValue) } } + +/** + * A function that returns the index of expr in (expr1, expr2, ...) list or 0 if not found. + * It takes at least 2 parameters, and all parameters should be subtype of AtomicType or NullType. + * It's also acceptable to give parameters of different types. + * If the search string is NULL, the return value is 0 because NULL fails equality comparison with any value. + * When the paramters have different types, comparing will be done based on type firstly, + * for example, ''999'' won't be considered equal with 999, no implicit cast will be done here. + */ +@ExpressionDescription( + usage = "_FUNC_(expr, expr1, expr2, ...) - Returns the index of expr in the expr1, expr2, ... or 0 if not found.", + extended = """ + Examples: + > SELECT _FUNC_(10, 9, 3, 10, 4); + 3 + > SELECT _FUNC_('a', 'b', 'c', 'd', 'a'); + 4 + > SELECT _FUNC_('999', 'a', 999, 9.99, '999'); + 4 + """) +case class Field(children: Seq[Expression]) extends Expression { + + /** Even if expr is not found in (expr1, expr2, ...) list, the value will be 0, not null */ + override def nullable: Boolean = false + override def foldable: Boolean = children.forall(_.foldable) + + private lazy val ordering = TypeUtils.getInterpretedOrdering(children(0).dataType) + + private val dataTypeMatchIndex: Seq[Int] = children.tail.zip(Stream from 1).filter( + _._1.dataType == children.head.dataType).map(_._2) + + override def checkInputDataTypes(): TypeCheckResult = { + if (children.length <= 1) { + TypeCheckResult.TypeCheckFailure(s"FIELD requires at least 2 arguments") + } else if (!children.forall( + e => e.dataType.isInstanceOf[AtomicType] || e.dataType.isInstanceOf[NullType])) { + TypeCheckResult.TypeCheckFailure(s"FIELD requires all arguments to be of AtomicType") + } else + TypeCheckResult.TypeCheckSuccess + } + + override def dataType: DataType = IntegerType + override def eval(input: InternalRow): Any = { + val target = children.head.eval(input) + val targetDataType = children.head.dataType + @tailrec def findEqual(index: Int): Int = { + if (index == dataTypeMatchIndex.size) { --- End diff -- if `dataTypeMatchIndex` is `Array[Int]`, then we'd better use `dataTypeMatchIndex.length` instead.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org