Github user concretevitamin commented on a diff in the pull request:
https://github.com/apache/spark/pull/1359#discussion_r14782682
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -207,3 +210,64 @@ 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 (str.dataType == BinaryType) str.dataType else StringType
+ }
+
+ def references = children.flatMap(_.references).toSet
+
+ override def children = str :: pos :: len :: Nil
+
+ def slice[T, C <% IndexedSeqOptimized[T,_]](str: C, startPos: Int,
sliceLen: Int): Any = {
+ val len = str.length
+ // Hive and SQL use one-based indexing for SUBSTR arguments but also
accept zero and
+ // negative indices for start positions. If a start index i is greater
than 0, it
+ // refers to element i-1 in the sequence. If a start index i is less
than 0, it refers
+ // to the -ith element before the end of the sequence. If a start
index i is 0, it
+ // refers to the first element.
+
+ val start = startPos match {
+ case pos if pos > 0 => pos - 1
+ case neg if neg < 0 => len + neg
+ case _ => 0
+ }
+
+ val end = sliceLen match {
--- End diff --
The MySQL doc mentions that "If len is less than 1, the result is the empty
string."
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
