Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/4504#discussion_r25232692 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala --- @@ -39,3 +39,66 @@ class Tokenizer extends UnaryTransformer[String, Seq[String], Tokenizer] { override protected def outputDataType: DataType = new ArrayType(StringType, false) } + + +/** + * :: AlphaComponent :: + * A regex based tokenizer that extracts tokens using a regex. + * Optional additional parameters include enabling lowercase stabdarization, a minimum character + * size for tokens as well as an array of stop words to remove from the results. + */ +@AlphaComponent +class RegexTokenizer extends UnaryTransformer[String, Seq[String], RegexTokenizer] { + + val lowerCase = new BooleanParam(this, + "lowerCase", + "enable case folding to lower case", + Some(true)) + def setLowercase(value: Boolean) = set(lowerCase, value) + def getLowercase: Boolean = get(lowerCase) + + val minLength = new IntParam(this, + "minLength", + "minimum token length (excluded)", + Some(0)) + def setMinLength(value: Int) = set(minLength, value) + def getMinLength: Int = get(minLength) + + val regEx = new Param(this, + "regEx", + "RegEx used for tokenizing", + Some("\\p{L}+|[^\\p{L}\\s]+".r)) + def setRegex(value: scala.util.matching.Regex) = set(regEx, value) + def getRegex: scala.util.matching.Regex = get(regEx) + + val stopWords = new Param(this, --- End diff -- I would leave this function to a stopword filter.
--- 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