From 9c0501c5d04d83ca25ce433138bf64df6a14dc58 Mon Sep 17 00:00:00 2001 From: Yuhao Yang Date: Thu, 30 Jul 2015 08:20:52 -0700 Subject: [PATCH] [SPARK-] [MLLIB] minor fix on tokenizer doc A trivial fix for the comments of RegexTokenizer. Maybe this is too small, yet I just noticed it and think it can be quite misleading. I can create a jira if necessary. Author: Yuhao Yang Closes #7791 from hhbyyh/docFix and squashes the following commits: cdf2542 [Yuhao Yang] minor fix on tokenizer doc --- .../src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala index 0b3af4747e..248288ca73 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala @@ -50,7 +50,7 @@ class Tokenizer(override val uid: String) extends UnaryTransformer[String, Seq[S /** * :: Experimental :: * A regex based tokenizer that extracts tokens either by using the provided regex pattern to split - * the text (default) or repeatedly matching the regex (if `gaps` is true). + * the text (default) or repeatedly matching the regex (if `gaps` is false). * Optional parameters also allow filtering tokens using a minimal length. * It returns an array of strings that can be empty. */