Github user marmbrus commented on a diff in the pull request: https://github.com/apache/spark/pull/1359#discussion_r14801757 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala --- @@ -207,3 +207,71 @@ case class StartsWith(left: Expression, right: Expression) extends StringCompari case class EndsWith(left: Expression, right: Expression) extends StringComparison { def compare(l: String, r: String) = l.endsWith(r) } + +/** + * A function that takes a substring of its first argument starting at a given position. + * Defined for String and Binary types. + */ +case class Substring(str: Expression, pos: Expression, len: Expression) extends Expression { + + type EvaluatedType = Any + + def nullable: Boolean = true + def dataType: DataType = { + if (!resolved) { + throw new UnresolvedException(this, s"Cannot resolve since $children are not resolved") + } + if (str.dataType == BinaryType) str.dataType else StringType + } + + def references = children.flatMap(_.references).toSet + + override def children = str :: pos :: len :: Nil + + @inline + def slice[T, C <% IndexedSeqOptimized[T,_]](str: C, startPos: Int, sliceLen: Int): Any = { --- End diff -- Would it be possible to do this without view bounds? I think those are going to disappear soon: https://issues.scala-lang.org/browse/SI-7629
--- 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. ---