Github user chenghao-intel commented on a diff in the pull request:
https://github.com/apache/spark/pull/1586#discussion_r15501825
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -209,6 +212,81 @@ case class EndsWith(left: Expression, right:
Expression)
}
/**
+ * A function that returns the number of bytes in an expression
+ */
+case class Length(child: Expression) extends UnaryExpression {
+
+ type EvaluatedType = Any
+
+ override def dataType = IntegerType
+
+ override def foldable = child.foldable
+
+ override def nullable = child.nullable
+
+ override def toString = s"Length($child)"
+
+ override def eval(input: Row): EvaluatedType = {
+ val string = child.eval(input)
+ if (string == null) {
+ null
+ } else if (!string.isInstanceOf[String]) {
+ string.toString.length
+ } else {
+ string.toString.getBytes.length
+ }
+ }
+
+}
+
+object StrlenConstants {
+ val DefaultEncoding = "ISO-8859-1"
+}
+
+/**
+ * A function that returns the number of characters in a string expression
+ */
+case class Strlen(child: Expression, encoding : Expression) extends
UnaryExpression
+ with Logging {
+
+ type EvaluatedType = Any
+
+ override def dataType = IntegerType
+
+ override def foldable = child.foldable
+
+ override def nullable = child.nullable
+
+ override def toString = s"Strlen($child, $encoding)"
+
+ override def eval(input: Row): EvaluatedType = {
+ val string = child.eval(input)
+ if (string == null) {
+ null
+ } else if (!string.isInstanceOf[String]) {
+ throw new IllegalArgumentException(s"Non-string value [$string]
provided to strlen")
--- End diff --
@marmbrus do you think it's more reasonable to put the children data type
checking into the `resolved`? I am not sure if we do the right thing for the
existed expressions.
---
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.
---
