Merge pull request #27 from rbart/sentenced

Break out Sentencer from Sentenced
knowitall · Oct 17, 2013 · daca5e9 · daca5e9
2 parents 5534ea4 + 6b15ca2
commit daca5e9
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 2 deletions.
diff --git a/core/src/main/scala/edu/knowitall/repr/document/Sentenced.scala b/core/src/main/scala/edu/knowitall/repr/document/Sentenced.scala
@@ -8,10 +8,16 @@ case class DocumentSentence[S <: Sentence](sentence: S, offset: Int)
 trait Sentenced[S <: Sentence] {
   this: Document =>
 
+  def sentences: Stream[DocumentSentence[S]]
+}
+
+trait Sentencer[S <: Sentence] extends Sentenced[S] {
+  this: Document =>
+
   def constructor(text: String): S
   def sentencer: Segmenter
 
-  lazy val sentences: Stream[DocumentSentence[S]] =
+  override lazy val sentences: Stream[DocumentSentence[S]] =
     sentencer(text).toStream.map { segment =>
       DocumentSentence(constructor(segment.text), segment.offset)
     }

diff --git a/typer/stanford/src/main/scala/edu/knowitall/tool/typer/StanfordNer.scala b/typer/stanford/src/main/scala/edu/knowitall/tool/typer/StanfordNer.scala
@@ -13,7 +13,11 @@ import java.io.BufferedInputStream
 import java.io.FileInputStream
 import java.util.zip.GZIPInputStream
 
-class StanfordNer(private val classifier: AbstractSequenceClassifier[_]) extends Typer[Token]("Stanford", "Stanford") {
+class StanfordNer(private val classifier: AbstractSequenceClassifier[_]) extends Typer[Token] {
+
+  override def name = "Stanford"
+  override def source = "Stanford"
+
   def apply(seq: Seq[Token]) = {
     val text = Tokenizer.originalText(seq)
     import scala.collection.JavaConverters._