Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/18046#discussion_r118838313
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
---
@@ -1180,6 +1182,60 @@ case class Length(child: Expression) extends
UnaryExpression with ImplicitCastIn
}
/**
+ * A function that return the bit length of the given string or binary
expression.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(expr) - Returns the bit length of `expr` or number of
bits in binary data.",
+ extended = """
+ Examples:
+ > SELECT _FUNC_('Spark SQL');
+ 72
+ """)
+case class BitLength(child: Expression) extends UnaryExpression with
ImplicitCastInputTypes {
+ override def dataType: DataType = IntegerType
+ override def inputTypes: Seq[AbstractDataType] =
Seq(TypeCollection(StringType, BinaryType))
+
+ protected override def nullSafeEval(value: Any): Any = child.dataType
match {
+ case StringType => value.asInstanceOf[UTF8String].numBytes * 8
+ case BinaryType => value.asInstanceOf[Array[Byte]].length * 8
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ child.dataType match {
+ case StringType => defineCodeGen(ctx, ev, c => s"($c).numBytes() *
8")
+ case BinaryType => defineCodeGen(ctx, ev, c => s"($c).length * 8")
+ }
+ }
+}
+
+/**
+ * A function that return the byte length of the given string or binary
expression.
--- End diff --
ditto
---
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.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
