Github user chenghao-intel commented on a diff in the pull request: https://github.com/apache/spark/pull/7208#discussion_r33894754 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala --- @@ -298,3 +299,56 @@ case class StringLength(child: Expression) extends UnaryExpression with ExpectsI override def prettyName: String = "length" } + +/** + * A function that return soundex code of the given string expression. + */ +case class SoundEx(child: Expression) extends UnaryExpression with ExpectsInputTypes { + @transient lazy val so = new Soundex + + override def dataType: DataType = StringType + + override def inputTypes: Seq[DataType] = Seq(StringType) + + override def eval(input: InternalRow): Any = { + val string = child.eval(input) + if (string == null) { + null + } else { + val str: String = string.toString --- End diff -- That's a good catch, but will that be more reasonable if we change the code in `UTF8String.toString()`? An empty string can be always comes from the constant pool, if we found an empty `UTF8String`.
--- 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