Cosmetic corrections

Author: tdebatty

nbactions.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<actions>
+        <action>
+            <actionName>run</actionName>
+            <packagings>
+                <packaging>jar</packaging>
+            </packagings>
+            <goals>
+                <goal>process-classes</goal>
+                <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
+            </goals>
+            <properties>
+                <exec.args>-classpath %classpath info.debatty.java.stringsimilarity.Main</exec.args>
+                <exec.executable>java</exec.executable>
+            </properties>
+        </action>
+    </actions>

src/main/java/info/debatty/java/stringsimilarity/CharacterSubstitutionInterface.java

@@ -31,6 +31,7 @@
  * For example, in an OCR application, cost('o', 'a') could be 0.4
  * In a checkspelling application, cost('u', 'i') could be 0.4 because these are
  * next to each other on the keyboard...
+ * 
  * @author Thibault Debatty
  */
 public interface CharacterSubstitutionInterface {

src/main/java/info/debatty/java/stringsimilarity/Cosine.java

@@ -74,6 +74,15 @@ public Cosine() {
      * @return Cosine similarity
      */
     public double similarity(String s1, String s2) {
+        if (s1.equals(s2)) {
+            return 1.0;
+        }
+        
+        
+        if (s1.equals("") || s2.equals("")) {
+            return 0.0;
+        }
+        
         KShingling ks = new KShingling(this.k);
         ks.parse(s1);
         ks.parse(s2);

src/main/java/info/debatty/java/stringsimilarity/Damerau.java

@@ -44,14 +44,25 @@ public class Damerau implements StringSimilarityInterface {
     public static void main(String[] args) {
 
         Damerau d = new Damerau();
+        // 1 switch
         System.out.println(d.absoluteDistance("ABCDEF", "ABDCEF"));
+        
+        // 2 switches
         System.out.println(d.absoluteDistance("ABCDEF", "BACDFE"));
+        
+        // 1 deletion
         System.out.println(d.absoluteDistance("ABCDEF", "ABCDE"));
+        
+        // 1 deletion
         System.out.println(d.absoluteDistance("ABCDEF", "BCDEF"));
         System.out.println(d.absoluteDistance("ABCDEF", "ABCGDEF"));
         System.out.println(d.absoluteDistance("ABCDEF", "BCDAEF"));
 
         System.out.println(d.distance("ABCDEF", "GHABCDE"));
+        
+        // All different
+        System.out.println(d.absoluteDistance("ABCDEF", "POIU"));
+        System.out.println(d.similarity("ABCDEF", "POIU"));
     }
 
     public int absoluteDistance(String s1, String s2) {
@@ -89,7 +100,6 @@ public int absoluteDistance(String s1, String s2) {
 
         }
 
-
         // fill in the distance matrix H
         // look at each character in s1
         for (int i = 1; i <= s1.length(); i++) {
@@ -124,7 +134,7 @@ public double similarity(String s1, String s2) {
     }
 
     public double distance(String s1, String s2) {
-        return (double) absoluteDistance(s1, s2) / (s1.length() + s2.length());
+        return (double) absoluteDistance(s1, s2) / Math.max(s1.length(), s2.length());
     }
 
     protected static int min(int a, int b, int c, int d) {

src/main/java/info/debatty/java/stringsimilarity/Main.java

@@ -37,11 +37,15 @@ public class Main {
      */
     public static void main(String[] args) {
         ArrayList<StringSimilarityInterface> similarities = new ArrayList<StringSimilarityInterface>();
+        similarities.add(new Cosine(4));
+        similarities.add(new Damerau());
+        similarities.add(new Jaccard(4));
         similarities.add(new JaroWinkler());
         similarities.add(new Levenshtein());
         similarities.add(new LongestCommonSubsequence());
         similarities.add(new NGram(4));
         similarities.add(new QGram(4));
+        similarities.add(new SorensenDice(4));
 
         ArrayList<Pair> pairs = new ArrayList<Pair>();
         // adjacent letters switch