Merge pull request #142 from kinow/TEXT-158

kinow · web-flow · commit 74afb2d933e3 · 2020-07-31T12:23:20.000+12:00
[TEXT-158]: empty strings must have similarity of 1, and distance of 0 (i.e. identical)
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
@@ -45,6 +45,7 @@ The <action> type attribute can be add,update,fix,remove.
   </properties>
   <body>
   <release version="1.9.1" date="202Y-MM-DD" description="Release 1.9.1. Requires Java 8.">
+    <action issue="TEXT-158" type="fix" dev="kinow">Incorrect values for Jaccard similarity with empty strings</action>
     <action issue="TEXT-185" type="add" dev="ggregory" due-to="Larry West, Gary Gregory">Release Notes page hasn't been updated for 1.9 release yet.</action>    
     <action                  type="add" dev="ggregory" due-to="Gary Gregory">Update spotbugs.plugin.version 4.0.0 to 4.0.4.</action>
     <action                  type="add" dev="ggregory" due-to="Dependabot">Update mockito-inline from 3.4.4 to 3.4.6 #143.</action>
diff --git a/src/main/java/org/apache/commons/text/similarity/JaccardSimilarity.java b/src/main/java/org/apache/commons/text/similarity/JaccardSimilarity.java
@@ -64,6 +64,9 @@ public Double apply(final CharSequence left, final CharSequence right) {
     private Double calculateJaccardSimilarity(final CharSequence left, final CharSequence right) {
         final int leftLength = left.length();
         final int rightLength = right.length();
+        if (leftLength == 0 && rightLength == 0) {
+            return 1d;
+        }
         if (leftLength == 0 || rightLength == 0) {
             return 0d;
         }
diff --git a/src/test/java/org/apache/commons/text/similarity/JaccardDistanceTest.java b/src/test/java/org/apache/commons/text/similarity/JaccardDistanceTest.java
@@ -37,7 +37,7 @@ public static void setUp() {
     @Test
     public void testGettingJaccardDistance() {
         // Expected Jaccard distance = 1.0 - (intersect / union)
-        assertEquals(1.0, classBeingTested.apply("", ""));
+        assertEquals(0.0, classBeingTested.apply("", ""));
         assertEquals(1.0, classBeingTested.apply("left", ""));
         assertEquals(1.0, classBeingTested.apply("", "right"));
         assertEquals(1.0 - (3.0 / 4), classBeingTested.apply("frog", "fog"));
diff --git a/src/test/java/org/apache/commons/text/similarity/JaccardSimilarityTest.java b/src/test/java/org/apache/commons/text/similarity/JaccardSimilarityTest.java
@@ -37,7 +37,7 @@ public static void setUp() {
     @Test
     public void testGettingJaccardSimilarity() {
         // Expected Jaccard similarity = (intersect / union)
-        assertEquals(0.0, classBeingTested.apply("", ""));
+        assertEquals(1.0, classBeingTested.apply("", ""));
         assertEquals(0.0, classBeingTested.apply("left", ""));
         assertEquals(0.0, classBeingTested.apply("", "right"));
         assertEquals(3.0 / 4, classBeingTested.apply("frog", "fog"));
