Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4504#discussion_r26665211
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
---
@@ -39,3 +39,67 @@ 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 either by repeatedly
matching the regex(default)
+ * or using it to split the text (set matching to false). Optional
parameters also allow to fold
+ * the text to lowercase prior to it being tokenized and to filer tokens
using a minimal length.
+ * It returns an array of strings that can be empty.
+ * The default parameters are regex = "\\p{L}+|[^\\p{L}\\s]+", matching =
true,
+ * lowercase = false, minTokenLength = 1
+ */
+@AlphaComponent
+class RegexTokenizer extends Tokenizer {
+
+ /**
+ * param for minimum token length, default is one to avoid returning
empty strings
+ * @group param
+ */
+ val minTokenLength = new IntParam(this, "minLength", "minimum token
length", Some(1))
+
+ /** @group setParam */
+ def setMinTokenLength(value: Int) = set(minTokenLength, value)
+
+ /** @group getParam */
+ def getMinTokenLength: Int = get(minTokenLength)
+
+ /**
+ * param sets regex as splitting on gaps(true) or matching tokens (false)
--- End diff --
space before `(true)`
---
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]
