Merged package contents into module.

9 files changed, 28 insertions, 124 deletions

diff --git a/cli/source/main/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizer.scala b/cli/source/main/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizer.scala
deleted file mode 100755
index cbd33d7..0000000
--- a/cli/source/main/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizer.scala
+++ /dev/null
@@ -1,31 +0,0 @@
-package com.rockymadden.stringmetric.cli.tokenize
-
-import com.rockymadden.stringmetric.cli._
-import com.rockymadden.stringmetric.tokenize.NGramTokenizer
-
-case object ngramtokenizer extends Command(
-	(opts) =>
-		"Returns the N-Gram representation of the passed string." + Ls + Ls +
-		"Syntax:" + Ls +
-		Tab + "ngramtokenizer [Options] string..." + Ls + Ls +
-		"Options:" + Ls +
-		Tab + "-h, --help" + Ls +
-		Tab + Tab + "Outputs description, syntax, and opts." +
-		Tab + "--n" + Ls +
-		Tab + Tab + "The n.",
-	(opts) => opts.contains('dashless) && (opts('dashless): Array[String]).length == 1 &&
-		opts.contains('n) && (opts('n): Int) >= 1,
-	(opts) => NGramTokenizer(opts('n)).tokenize(opts('dashless)) match {
-		case Some(c) => {
-			val sb = new StringBuilder
-
-			Range(0, c.length).foreach { i =>
-				sb.append(c(i))
-				if (i < c.length - 1) sb.append("|")
-			}
-
-			sb.result()
-		}
-		case None => "not computable"
-	}
-)
diff --git a/cli/source/test/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizerSpec.scala b/cli/source/test/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizerSpec.scala
deleted file mode 100755
index 552fcf4..0000000
--- a/cli/source/test/scala/com/rockymadden/stringmetric/cli/tokenize/ngramtokenizerSpec.scala
+++ /dev/null
@@ -1,64 +0,0 @@
-package com.rockymadden.stringmetric.cli.tokenize
-
-import com.rockymadden.stringmetric.ScalaTest
-import org.junit.runner.RunWith
-import org.scalatest.junit.JUnitRunner
-
-@RunWith(classOf[JUnitRunner])
-final class ngramtokenizerSpec extends ScalaTest { "ngramtokenizer" should provide {
-	"main method" when passed {
-		"valid dashless argument and valid n argument" should executes {
-			"print N-Gram representation" in {
-				val out = new java.io.ByteArrayOutputStream()
-
-				Console.withOut(out)(
-					ngramtokenizer.main(
-						Array(
-							"--unitTest",
-							"--debug",
-							"--n=1",
-							"abc"
-						)
-					)
-				)
-
-				out.toString should equal ("a|b|c\n")
-				out.reset()
-
-				Console.withOut(out)(
-					ngramtokenizer.main(
-						Array(
-							"--unitTest",
-							"--debug",
-							"--n=2",
-							"abc"
-						)
-					)
-				)
-
-				out.toString should equal ("ab|bc\n")
-				out.reset()
-			}
-		}
-		"valid dashless argument and invalid n argument" should throws {
-			"IllegalArgumentException" in {
-				evaluating {
-					ngramtokenizer.main(
-						Array(
-							"--unitTest",
-							"abc",
-							"abc"
-						)
-					)
-				} should produce [IllegalArgumentException]
-			}
-		}
-		"no dashless argument" should throws {
-			"IllegalArgumentException" in {
-				evaluating {
-					ngramtokenizer.main(Array("--unitTest", "--debug"))
-				} should produce [IllegalArgumentException]
-			}
-		}
-	}
-}}
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/Tokenize.scala b/core/source/main/scala/com/rockymadden/stringmetric/Tokenize.scala
index 36b7eef..00b173d 100755
--- a/core/source/main/scala/com/rockymadden/stringmetric/Tokenize.scala
+++ b/core/source/main/scala/com/rockymadden/stringmetric/Tokenize.scala
@@ -1,19 +1,36 @@
 package com.rockymadden.stringmetric
 
 object Tokenize {
-	trait Tokenizer[A] {
+	sealed trait Tokenizer[A] {
 		def tokenize(a: A): Option[Array[A]]
 	}
 
 
-	trait StringTokenizer extends Tokenizer[Array[Char]] {
+	sealed trait StringTokenizer extends Tokenizer[Array[Char]] {
 		def tokenize(a: String): Option[Array[String]]
 	}
 
 
 	object StringTokenizer {
-		val NGram = tokenize.NGramTokenizer
+		val NGram = NGramTokenizer
 
 		def tokenizeWithNGram(n: Int)(charArray: Array[Char]) = NGram(n).tokenize(charArray)
 	}
+
+
+	final case class NGramTokenizer(n: Int) extends StringTokenizer {
+		override def tokenize(a: Array[Char]): Option[Array[Array[Char]]] = {
+			if (n <= 0) return None
+
+			if (a.length < n) None
+			else Some(sequence(a, Array.empty[Array[Char]], n))
+		}
+
+		override def tokenize(a: String): Option[Array[String]] = tokenize(a.toCharArray).map(_.map(_.mkString))
+
+		@annotation.tailrec
+		private val sequence: ((Array[Char], Array[Array[Char]], Int) => Array[Array[Char]]) = (i, o, n) =>
+			if (i.length <= n) o :+ i
+			else sequence(i.tail, o :+ i.take(n), n)
+	}
 }
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/similarity/DiceSorensenMetric.scala b/core/source/main/scala/com/rockymadden/stringmetric/similarity/DiceSorensenMetric.scala
index 1e07432..0ad3915 100755
--- a/core/source/main/scala/com/rockymadden/stringmetric/similarity/DiceSorensenMetric.scala
+++ b/core/source/main/scala/com/rockymadden/stringmetric/similarity/DiceSorensenMetric.scala
@@ -7,7 +7,7 @@ import com.rockymadden.stringmetric.Metric.StringMetric
  * Traditionally, the algorithm uses bigrams.
  */
 final case class DiceSorensenMetric(n: Int) extends StringMetric[Double] {
-	import com.rockymadden.stringmetric.tokenize.NGramTokenizer
+	import com.rockymadden.stringmetric.Tokenize.NGramTokenizer
 	import com.rockymadden.stringmetric.MatchTuple
 
 	override def compare(a: Array[Char], b: Array[Char]): Option[Double] =
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/similarity/JaccardMetric.scala b/core/source/main/scala/com/rockymadden/stringmetric/similarity/JaccardMetric.scala
index 629eaa0..6ec5db4 100755
--- a/core/source/main/scala/com/rockymadden/stringmetric/similarity/JaccardMetric.scala
+++ b/core/source/main/scala/com/rockymadden/stringmetric/similarity/JaccardMetric.scala
@@ -3,7 +3,7 @@ package com.rockymadden.stringmetric.similarity
 import com.rockymadden.stringmetric.Metric.StringMetric
 
 final case class JaccardMetric(n: Int) extends StringMetric[Double] {
-	import com.rockymadden.stringmetric.tokenize.NGramTokenizer
+	import com.rockymadden.stringmetric.Tokenize.NGramTokenizer
 
 	override def compare(a: Array[Char], b: Array[Char]): Option[Double] =
 		if (n <= 0 || a.length < n || b.length < n) None // Because length is less than n, it is not possible to compare.
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/similarity/NGramMetric.scala b/core/source/main/scala/com/rockymadden/stringmetric/similarity/NGramMetric.scala
index d712738..8c194ce 100755
--- a/core/source/main/scala/com/rockymadden/stringmetric/similarity/NGramMetric.scala
+++ b/core/source/main/scala/com/rockymadden/stringmetric/similarity/NGramMetric.scala
@@ -4,7 +4,7 @@ import com.rockymadden.stringmetric.Metric.StringMetric
 
 final case class NGramMetric(n: Int) extends StringMetric[Double] {
 	import com.rockymadden.stringmetric.MatchTuple
-	import com.rockymadden.stringmetric.tokenize.NGramTokenizer
+	import com.rockymadden.stringmetric.Tokenize.NGramTokenizer
 	import scala.math
 
 	override def compare(a: Array[Char], b: Array[Char]): Option[Double] =
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/similarity/OverlapMetric.scala b/core/source/main/scala/com/rockymadden/stringmetric/similarity/OverlapMetric.scala
index cc33a26..8f0418b 100755
--- a/core/source/main/scala/com/rockymadden/stringmetric/similarity/OverlapMetric.scala
+++ b/core/source/main/scala/com/rockymadden/stringmetric/similarity/OverlapMetric.scala
@@ -4,7 +4,7 @@ import com.rockymadden.stringmetric.Metric.StringMetric
 
 final case class OverlapMetric(n: Int) extends StringMetric[Double] {
 	import com.rockymadden.stringmetric.MatchTuple
-	import com.rockymadden.stringmetric.tokenize.NGramTokenizer
+	import com.rockymadden.stringmetric.Tokenize.NGramTokenizer
 	import scala.math
 
 	override def compare(a: Array[Char], b: Array[Char]): Option[Double] =
diff --git a/core/source/main/scala/com/rockymadden/stringmetric/tokenize/NGramTokenizer.scala b/core/source/main/scala/com/rockymadden/stringmetric/tokenize/NGramTokenizer.scala
deleted file mode 100755
index aa89b31..0000000
--- a/core/source/main/scala/com/rockymadden/stringmetric/tokenize/NGramTokenizer.scala
+++ /dev/null
@@ -1,19 +0,0 @@
-package com.rockymadden.stringmetric.tokenize
-
-import com.rockymadden.stringmetric.Tokenize.StringTokenizer
-
-final case class NGramTokenizer(n: Int) extends StringTokenizer {
-	override def tokenize(a: Array[Char]): Option[Array[Array[Char]]] = {
-		if (n <= 0) return None
-
-		if (a.length < n) None
-		else Some(sequence(a, Array.empty[Array[Char]], n))
-	}
-
-	override def tokenize(a: String): Option[Array[String]] = tokenize(a.toCharArray).map(_.map(_.mkString))
-
-	@annotation.tailrec
-	private val sequence: ((Array[Char], Array[Array[Char]], Int) => Array[Array[Char]]) = (i, o, n) =>
-		if (i.length <= n) o :+ i
-		else sequence(i.tail, o :+ i.take(n), n)
-}
diff --git a/core/source/test/scala/com/rockymadden/stringmetric/tokenize/NGramTokenizerSpec.scala b/core/source/test/scala/com/rockymadden/stringmetric/TokenizeSpec.scala
index 01636f0..cfba0f7 100755
--- a/core/source/test/scala/com/rockymadden/stringmetric/tokenize/NGramTokenizerSpec.scala
+++ b/core/source/test/scala/com/rockymadden/stringmetric/TokenizeSpec.scala
@@ -1,11 +1,12 @@
-package com.rockymadden.stringmetric.tokenize
+package com.rockymadden.stringmetric
 
-import com.rockymadden.stringmetric.ScalaTest
 import org.junit.runner.RunWith
 import org.scalatest.junit.JUnitRunner
 
 @RunWith(classOf[JUnitRunner])
-final class NGramTokenizerSpec extends ScalaTest { "NGramTokenizer" should provide {
+final class TokenizeSpec extends ScalaTest { "NGramTokenizer" should provide {
+	import Tokenize._
+
 	"tokenize method" when passed {
 		"empty argument" should returns {
 			"None" in {