Update to 'relevancy'

padolsey · Nov 20, 2011 · 246d1af · 246d1af
1 parent 769ec8e
commit 246d1af
Show file tree

Hide file tree

Showing 6 changed files with 51 additions and 51 deletions.
diff --git a/demos/index.html b/demos/index.html
@@ -2,7 +2,7 @@
 <html>
 <head>
 	<meta charset="UTF-8" />
-	<title>Similarity Sorter Test suite</title>
+	<title>relevancy Sorter Test suite</title>
 </head>
 <body>
 
@@ -16,15 +16,15 @@
 	</div>
 
 	<script src="../test/data.js"></script>
-	<script src="../lib/similarity.js"></script>
+	<script src="../lib/relevancy.js"></script>
 
 	<script>
 
 		var dataSelect = document.getElementById('dataset'),
 			search = document.getElementById('search'),
 			data = document.getElementById('data'),
 
-			sorter = similarity.Sorter({}, countries);
+			sorter = relevancy.Sorter({}, countries);
 
 		search.onkeyup = function() {
 

diff --git a/lib/similarity.js → lib/relevancy.js b/lib/similarity.js → lib/relevancy.js
@@ -1,18 +1,18 @@
 /**
- * Similarity.js v0.1.0dev
+ * relevancy.js v0.1.0dev
  **/
 
 (function(){
 
-	var S = typeof module != 'undefined' && module && module.exports || (this.similarity = {}),
+	var S = typeof module != 'undefined' && module && module.exports || (this.relevancy = {}),
 		toString = Object.prototype.toString,
 		hasOwn = Object.prototype.hasOwnProperty;
 
-	S.sort = function similaritySort(array, subject) {
+	S.sort = function relevancySort(array, subject) {
 		return S.defaultSorter.sort(array, subject);
 	};
 
-	S.weight = function similarityWeight(a, b) {
+	S.weight = function relevancyWeight(a, b) {
 		return S.defaultSorter._calcWeight(b, S.defaultSorter._generateSubjectRegex(a), a);
 	};
 
@@ -92,7 +92,7 @@
 		_generateBoundRegex: function() {
 
 			this.boundRegex = RegExp(this._bounds.join('|'));
-			this.lastBoundRegex = RegExp('.+(?:' + this._bounds.join('|') + ')(?=.+$)');
+			this.lastBoundRegex = RegExp('.+(?:' + this._bounds.join('|') + ')(?=.*$)');
 
 		},
 		setArray: function(array) {
@@ -153,12 +153,12 @@
 
 			if (!match) return null;
 
-			var upTillAndInclMatch = value.slice(0, match.index + match.length),
-				lastBoundIndex = (upTillAndInclMatch.match(this.lastBoundRegex)||[''])[0].length,
+			var upTillMatch = value.slice(0, match.index),
+				lastBoundIndex = (upTillMatch.match(this.lastBoundRegex)||[''])[0].length,
 
 				matchInValueIndexScore = (1 - (
 					((match.index - lastBoundIndex) / (value.length - lastBoundIndex))
-				)) - ((upTillAndInclMatch.split(this.boundRegex).length-1) * .05),
+				)) - ((upTillMatch.split(this.boundRegex).length-1) * .05),
 
 				matchInValueLengthScore = match.length / value.length,
 

diff --git a/package.json b/package.json
@@ -1,16 +1,16 @@
 {
-  "name": "similarity",
-  "description": "Unidirectional string similarity",
+  "name": "relevancy",
+  "description": "Unidirectional string relevancy",
   "version": "0.1.0",
   "author": "James Padolsey https://github.com/jamespadolsey",
   "bugs" : {
-    "url" : "http://github.com/jamespadolsey/similarity.js/issues"
+    "url" : "http://github.com/jamespadolsey/relevancy.js/issues"
   },
   "repository": {
     "type": "git",
-    "url": "http://jamespadolsey@github.com/jamespadolsey/similarity.js.git"
+    "url": "http://jamespadolsey@github.com/jamespadolsey/relevancy.js.git"
   },
-  "main": "lib/similarity",
+  "main": "lib/relevancy",
   "licenses": [],
   "contributors": [
     "James Padolsey <> (http://github.com/jamespadolsey)"

diff --git a/readme.md b/readme.md
@@ -1,11 +1,11 @@
-# Similarity Sorter/Weighter
+# relevancy Sorter/Weighter
 
 ## Objective
 
-The original purpose behind similarity.js was to sort an array of items based on each element's similarity to a single string. This is exactly what autocompletion widgets/scripts claim to do, but many of them suck for the following reasons:
+The original purpose behind relevancy.js was to sort an array of items based on each element's relevancy to a single string. This is exactly what autocompletion widgets/scripts claim to do, but many of them suck for the following reasons:
 
  * They only take into account partial matches at the beginning of the strings. If I type "nited kingdom" (missing a "u") nothing will show up.
- * They don't actually sort the results dependent on similarity -- they just show you where the partial matches have been found, in alphabetical order usually. Match length/position is rarely considered.
+ * They don't actually sort the results dependent on relevancy -- they just show you where the partial matches have been found, in alphabetical order usually. Match length/position is rarely considered.
 
 E.g.
 
@@ -15,31 +15,31 @@ E.g.
 
 The basic partial-matching implemented by most autocompletion scripts can hamper usability.
 
-Hopefully, similarity.js can rectify this with its not-so-complex weighting algorithm.
+Hopefully, relevancy.js can rectify this with its not-so-complex weighting algorithm.
 
 ## Intro
 
 **[Version: 0.1.0dev]**
 
-similarity.js contains a basic sorting/weighting algorithm that can be used to weight a short string relative to another short string. It can gage the similarity between two strings, but only in a unidirectional manner (`"Lon"` is more *similar* to `"London"` than `"London"` is to `"Lon"`). This was intentional as its main use-case is autocompletion -- i.e. matching partial typed words against large data lists.
+relevancy.js contains a basic sorting/weighting algorithm that can be used to weight a short string relative to another short string. It can gage the relevancy between two strings, but only in a unidirectional manner (`"Lon"` is more *similar* to `"London"` than `"London"` is to `"Lon"`). This was intentional as its main use-case is autocompletion -- i.e. matching partial typed words against large data lists.
 
-	similarity.weight('Ame', 'America') > similarity.weight('Ame', 'Armenia'); // => true
+	relevancy.weight('Ame', 'America') > relevancy.weight('Ame', 'Armenia'); // => true
 
 	// Explanation:
-	// "Ame" has a higher similarity weighting to "America" than to "Armenia"
+	// "Ame" has a higher relevancy weighting to "America" than to "Armenia"
 
 The *subject* of a single weighting or sorting operation is the string that is being compared against the target string or array. For example:
 
     var subject = 'G';
     var array = ['Apple', 'Banana', 'Grape', 'Mango'];
 
-    similarity.sort(array, subject); // => ['Grape', 'Mango', 'Apple', 'Banana']
+    relevancy.sort(array, subject); // => ['Grape', 'Mango', 'Apple', 'Banana']
 
-The elements have been sorted by their similarity to the subject "G", taking the following weights into account:
+The elements have been sorted by their relevancy to the subject "G", taking the following weights into account:
 
  * `matchInSubjectLength`: (`0..1`) The proportion of the largest substring match found within the actual subject. So, if the subject is `"Gu"`, but we only match `"G"` (e.g. in `"Grape"`) then proportion would be `0.5`.
  * `matchInSubjectIndex`: (`0..1`) The proximity of the match to the start of the subject. For example, given the subject `"A grape"` against the value `"Grapelicious"`, `"grape"` in `"A grape"` matches the beginning of the value, and it is at an index of `2`. The highest possible index of this is `2` (given the match's length: `5`) so `matchInSubjectIndex`, in this example, gets set as zero.
- * `matchInValueLength`: (`0..1`) The proportion of the largest substring match found within the target value. For example, we matched the substring `"King"` (length:`4`) against the value `"United Kingdom"` (length:`14`), and `4/14 = ~0.29` **This is not used currently.**, although can be set when you pass a configuration object to `similarity.Sorter`.
+ * `matchInValueLength`: (`0..1`) The proportion of the largest substring match found within the target value. For example, we matched the substring `"King"` (length:`4`) against the value `"United Kingdom"` (length:`14`), and `4/14 = ~0.29` **This is not used currently.**, although can be set when you pass a configuration object to `relevancy.Sorter`.
  * `matchInValueIndex`: (`0..1`) The proximity of the match to the start of the target value. E.g., a match of `"dom"` in `"Kingdom"` -- `"dom"` is matched at an index of `4`. `4` divided by the total length of `7` substracted from `1` gives us our `matchInValueIndex` of `~0.43`.
 
 Note that the algorithm will account for spaces and anchor the calculations above accordingly. So `"Banana Milkshake"` will be weighted higher than `"bananamilk"` given the subject `"milk"` because it begins a word in the former `"Banana Milkshake"` but merely forms a part of another word in the latter, `"bananamilk"`.
@@ -48,7 +48,7 @@ The default bound of `\s+` is used to find where the calculations should be anch
 
 ## Example Implementation
 
-	// In this example, we'll also see how similarity.js can
+	// In this example, we'll also see how relevancy.js can
 	// deal with nested arrays. Default operation is `max`,
 	// meaning that it'll get the maximum weight from each sub-array
 	// and use that for comparing to other sub-arrays.
@@ -63,20 +63,20 @@ The default bound of `\s+` is used to find where the calculations should be anch
 		// .......
 	];
 
-	var countrySorter = similarity.Sorter(null, countries);
+	var countrySorter = relevancy.Sorter(null, countries);
 
 	countrySorter.sortBy('Al').slice(0, 5); // => [["AL", "Albania"], ["DZ", "Algeria"]...]
 
 ## Configuration
 
-If you want more control you should create a `similarity.Sorter` instance which can accept a configuration object upon instantiation:
+If you want more control you should create a `relevancy.Sorter` instance which can accept a configuration object upon instantiation:
 
-	var mySorter = new similarity.Sorter({
+	var mySorter = new relevancy.Sorter({
 
 		bounds: ['\\s', '(?=[A-Z])', '-'], // create new bounds (default: ['\\s'])
 
 		comparator: function(a, b) {
-			// When similarity.Sorter finds two items with equal weight
+			// When relevancy.Sorter finds two items with equal weight
 			// it will pass them to this function so you can decide 
 			// what to do. I.e. return -1, 1
 			// Only return 0 if you're prepared for the pain caused 

diff --git a/test/index.html b/test/index.html
@@ -2,15 +2,15 @@
 <html>
 <head>
 	<meta charset="UTF-8" />
-	<title>Similarity Sorter Test suite</title>
+	<title>Relevancy Sorter Test suite</title>
 	<link rel="stylesheet" href="qunit.css" type="text/css" media="screen">
 	<script src="qunit.js"></script>
 	<script src="data.js"></script>
 	<script src="test.js"></script>
-	<script src="../lib/similarity.js"></script>
+	<script src="../lib/relevancy.js"></script>
 </head>
 <body>
-	<h1 id="qunit-header">Similarity Sorter Test suite</h1>
+	<h1 id="qunit-header">Relevancy Sorter Test suite</h1>
 	<h2 id="qunit-banner"></h2>
 	<div id="qunit-testrunner-toolbar"></div>
 	<h2 id="qunit-userAgent"></h2>

diff --git a/test/test.js b/test/test.js
@@ -7,7 +7,7 @@ module('101', {
 test('Basic first-character ordering', function(){
 
 	var unsorted = ['Paul', 'Michael'],
-		sorted = similarity.sort(unsorted.slice(), 'M');
+		sorted = relevancy.sort(unsorted.slice(), 'M');
 
 	deepEqual(sorted, ['Michael', 'Paul']);
 
@@ -16,7 +16,7 @@ test('Basic first-character ordering', function(){
 test('No matching items', function() {
 
 	var unsorted = ['aaa', 'bbb', 'ccc'],
-		sorted = similarity.sort(unsorted.slice(), 'x');
+		sorted = relevancy.sort(unsorted.slice(), 'x');
 
 	deepEqual(sorted, unsorted);
 
@@ -25,7 +25,7 @@ test('No matching items', function() {
 test('Some matching items', function(){
 
 	var unsorted = ['Sarah', 'Julie', 'Michael', 'Paul', 'Amanada'],
-		sorted = similarity.sort(unsorted.slice(), 'M');
+		sorted = relevancy.sort(unsorted.slice(), 'M');
 
 	deepEqual(sorted, ['Michael', 'Amanada', 'Sarah', 'Julie', 'Paul']);
 
@@ -34,7 +34,7 @@ test('Some matching items', function(){
 test('Items containing matches', function(){
 
 	var unsorted = ['AAAA', 'ABBA', 'CCCC', 'CBBC'],
-		sorted = similarity.sort(unsorted.slice(), 'BB');
+		sorted = relevancy.sort(unsorted.slice(), 'BB');
 
 	deepEqual(sorted, ['ABBA', 'CBBC', 'AAAA', 'CCCC']);
 
@@ -43,7 +43,7 @@ test('Items containing matches', function(){
 test('Distance-from-start', function(){
 
 	var unsorted = ['..a', '.a', '....a', 'a', '...a'],
-		sorted = similarity.sort(unsorted.slice(), 'a');
+		sorted = relevancy.sort(unsorted.slice(), 'a');
 
 	deepEqual(sorted, ['a', '.a', '..a', '...a', '....a']);
 
@@ -74,7 +74,7 @@ test('Basic names - ^Ja', function(){
 			'Jan',
 			'George'
 		],
-		sorted = similarity.sort(unsorted.slice(), 'Ja');
+		sorted = relevancy.sort(unsorted.slice(), 'Ja');
 
 	deepEqual(
 		sorted.slice(0, 5),
@@ -101,7 +101,7 @@ test('Full names', function(){
 			'Bob',
 			'Sarah Smith'
 		],
-		sorted = similarity.sort(unsorted.slice(), 'Sm');
+		sorted = relevancy.sort(unsorted.slice(), 'Sm');
 
 	deepEqual(
 		sorted.slice(0, 5),
@@ -118,24 +118,24 @@ test('Full names', function(){
 
 test('Countries - single full', function(){
 
-	deepEqual(similarity.sort(countries, 'GB')[0], ['GB', 'United Kingdom']);
-	deepEqual(similarity.sort(countries, 'United States')[0], ['US', 'United States']);
-	deepEqual(similarity.sort(countries, 'Saint Lucia')[0], ['LC', 'Saint Lucia']);
-	deepEqual(similarity.sort(countries, 'CU')[0], ['CU', 'Cuba']);
+	deepEqual(relevancy.sort(countries, 'GB')[0], ['GB', 'United Kingdom']);
+	deepEqual(relevancy.sort(countries, 'United States')[0], ['US', 'United States']);
+	deepEqual(relevancy.sort(countries, 'Saint Lucia')[0], ['LC', 'Saint Lucia']);
+	deepEqual(relevancy.sort(countries, 'CU')[0], ['CU', 'Cuba']);
 
 });
 
 test('Countries - single partial', function(){
 
-	var sorted = similarity.sort(countries, 'Ukr');
+	var sorted = relevancy.sort(countries, 'Ukr');
 
 	deepEqual(sorted[0], ['UA', 'Ukraine']);
 
 });
 
 test('Countries - single partial - second word', function(){
 
-	var sorted = similarity.sort(countries, 'Poly');
+	var sorted = relevancy.sort(countries, 'Poly');
 
 	deepEqual(sorted[0], ['PF', 'French Polynesia']);
 
@@ -149,7 +149,7 @@ module('subArrayWeightOperations (max, min, avg, custom', {
 
 test('max', function(){
 
-	var sorted = similarity.sort([
+	var sorted = relevancy.sort([
 		['b', 'c', 'a'],
 		['cccc', 'bbbb', 'cccc'],
 		['bb', 'aa', 'cc']
@@ -175,7 +175,7 @@ module('Misc. configs', {
 test('Basic names - Custom secondary comparator (retain index)', function(){
 
 	// It's possible to specify the secondary comparator used when
-	// weights are found to be equal. similarity.js will attempt
+	// weights are found to be equal. relevancy.js will attempt
 	// to retain original positions, but some engines (V8!) don't
 	// have stable sorts... and so this kind of thing can become a necessity.
 
@@ -202,7 +202,7 @@ test('Basic names - Custom secondary comparator (retain index)', function(){
 		indexes[unsorted[i]] = i;
 	}
 
-	var sorted = similarity.Sorter({
+	var sorted = relevancy.Sorter({
 			comparator: function(a, b) {
 				return indexes[a] > indexes[b] ? 1 : -1;
 			}
@@ -234,7 +234,7 @@ test('Custom bound - camelCase', function(){
 	];
 
 	deepEqual(
-		similarity.Sorter({
+		relevancy.Sorter({
 			bounds: ['\\s', '(?=[A-Z])']
 		}).sort(array, 'script'),
 		[