Optimize levenshtein implementation

levenshtein.js

@@ -1,30 +1,52 @@
 var makeString = require('./helper/makeString');
 
+/**
+ * Based on the implementation here: https://github.com/hiddentao/fast-levenshtein
+ */
 module.exports = function levenshtein(str1, str2) {
+  'use strict';
   str1 = makeString(str1);
   str2 = makeString(str2);
 
-  if (str1 === str2)
-    return 0;
+  // Short cut cases  
+  if (str1 === str2) return 0;
+  if (!str1 || !str2) return Math.max(str1.length, str2.length);
 
-  var current = [],
-    prev, value = 0;
+  // two rows
+  var prevRow = new Array(str2.length + 1);
 
-  for (var i = 0; i <= str2.length; i++) {
-    for (var j = 0; j <= str1.length; j++) {
-      if (i && j) {
-        if (str1.charAt(j - 1) === str2.charAt(i - 1))
-          value = prev;
-        else
-          value = Math.min(current[j], current[j - 1], prev) + 1;
+  // initialise previous row
+  for (var i = 0; i < prevRow.length; ++i) {
+    prevRow[i] = i;
+  }
+
+  // calculate current row distance from previous row
+  for (i = 0; i < str1.length; ++i) {
+    var nextCol = i + 1;
+
+    for (var j = 0; j < str2.length; ++j) {
+      var curCol = nextCol;
+
+      // substution
+      nextCol = prevRow[j] + ( (str1.charAt(i) === str2.charAt(j)) ? 0 : 1 );
+      // insertion
+      var tmp = curCol + 1;
+      if (nextCol > tmp) {
+        nextCol = tmp;
+      }
+      // deletion
+      tmp = prevRow[j + 1] + 1;
+      if (nextCol > tmp) {
+        nextCol = tmp;
       }
-      else
-        value = i + j;
 
-      prev = current[j];
-      current[j] = value;
+      // copy current col value into previous (in preparation for next iteration)
+      prevRow[j] = curCol;
     }
+
+    // copy last col value into previous (in preparation for next iteration)
+    prevRow[j] = nextCol;
   }
 
-  return value;
+  return nextCol;
 };

tests/levenshtein.js

@@ -17,3 +17,6 @@ test('#levenshtein', function() {
   equal(levenshtein(), 0);
 });
 
+test('#levenshtein non-latin', function() {
+  equal(levenshtein('因為我是中國人所以我會說中文', '因為我是英國人所以我會說英文'), 2);
+});