bugfixes

.versions

@@ -0,0 +1,24 @@
+anonyfox:tags@0.0.1
+application-configuration@1.0.4
+base64@1.0.2
+binary-heap@1.0.2
+callback-hook@1.0.2
+check@1.0.4
+coffeescript@1.0.5
+ddp@1.0.14
+ejson@1.0.5
+follower-livedata@1.0.3
+geojson-utils@1.0.2
+id-map@1.0.2
+json@1.0.2
+local-test:anonyfox:tags@0.0.1
+logging@1.0.6
+meteor@1.1.4
+minimongo@1.0.6
+mongo@1.0.11
+ordered-dict@1.0.2
+random@1.0.2
+retry@1.0.2
+tinytest@1.0.4
+tracker@1.0.5
+underscore@1.0.2

package.js

@@ -9,7 +9,7 @@ Package.describe({
 Package.onUse(function(api) {
   api.versionsFrom('1.0');
   // api.addFiles('anonyfox:tags.js');
-  api.use(['tinytest','coffeescript','underscore'],['client','server']);
+  api.use(['coffeescript','underscore'],['client','server']);
   api.addFiles([
 	  'stopwords/stopwords_de.coffee',
 	  'stopwords/stopwords_en.coffee',
@@ -20,7 +20,13 @@ Package.onUse(function(api) {
 });
 
 Package.onTest(function(api) {
-  // api.use(['tinytest','coffeescript'],['client','server']);
-  // api.addFiles(['tags.coffee'],['client','server']);
-  // api.addFiles('anonyfox:tags-tests.js');
+  api.use(['tinytest','coffeescript','underscore'],['client','server']);
+  api.addFiles([
+	  'stopwords/stopwords_de.coffee',
+	  'stopwords/stopwords_en.coffee',
+	  'porter-stemmer.js',
+	  'tags.coffee.md',
+	  'globals.js'
+  ],['client','server']);
+  api.addFiles('tests.coffee');
 });

porter-stemmer.js

@@ -0,0 +1,209 @@
+// Porter stemmer in Javascript. Few comments, but it's easy to follow against
+// the rules in the original paper, in
+//
+//  Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14, no. 3,
+//  pp 130-137,
+//
+// see also http://www.tartarus.org/~martin/PorterStemmer
+
+// Release 1 be 'andargor', Jul 2004
+// Release 2 (substantially revised) by Christopher McKenzie, Aug 2009
+//
+// CommonJS tweak by jedp
+
+(function() {
+  var step2list = {
+      "ational" : "ate",
+      "tional" : "tion",
+      "enci" : "ence",
+      "anci" : "ance",
+      "izer" : "ize",
+      "bli" : "ble",
+      "alli" : "al",
+      "entli" : "ent",
+      "eli" : "e",
+      "ousli" : "ous",
+      "ization" : "ize",
+      "ation" : "ate",
+      "ator" : "ate",
+      "alism" : "al",
+      "iveness" : "ive",
+      "fulness" : "ful",
+      "ousness" : "ous",
+      "aliti" : "al",
+      "iviti" : "ive",
+      "biliti" : "ble",
+      "logi" : "log"
+    };
+
+  var step3list = {
+      "icate" : "ic",
+      "ative" : "",
+      "alize" : "al",
+      "iciti" : "ic",
+      "ical" : "ic",
+      "ful" : "",
+      "ness" : ""
+    };
+
+  var c = "[^aeiou\u00e4\u00f6\u00fc]";          // consonant
+  var v = "[aeiouy\u00e4\u00f6\u00fc]";          // vowel
+  var C = c + "[^aeiouy\u00e4\u00f6\u00fc]*";    // consonant sequence
+  var V = v + "[aeiou\u00e4\u00f6\u00fc]*";      // vowel sequence
+
+  var mgr0 = "^(" + C + ")?" + V + C;               // [C]VC... is m>0
+  var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$";  // [C]VC[V] is m=1
+  var mgr1 = "^(" + C + ")?" + V + C + V + C;       // [C]VCVC... is m>1
+  var s_v = "^(" + C + ")?" + v;                   // vowel in stem
+
+  function stemmer(w) {
+    var stem;
+    var suffix;
+    var firstch;
+    var re;
+    var re2;
+    var re3;
+    var re4;
+    var origword = w;
+
+    if (w.length < 3) { return w; }
+
+    firstch = w.substr(0,1);
+    if (firstch == "y") {
+      w = firstch.toUpperCase() + w.substr(1);
+    }
+
+    // Step 1a
+    re = /^(.+?)(ss|i)es$/;
+    re2 = /^(.+?)([^s])s$/;
+
+    if (re.test(w)) { w = w.replace(re,"$1$2"); }
+    else if (re2.test(w)) {  w = w.replace(re2,"$1$2"); }
+
+    // Step 1b
+    re = /^(.+?)eed$/;
+    re2 = /^(.+?)(ed|ing)$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      re = new RegExp(mgr0);
+      if (re.test(fp[1])) {
+        re = /.$/;
+        w = w.replace(re,"");
+      }
+    } else if (re2.test(w)) {
+      var fp = re2.exec(w);
+      stem = fp[1];
+      re2 = new RegExp(s_v);
+      if (re2.test(stem)) {
+        w = stem;
+        re2 = /(at|bl|iz)$/;
+        re3 = new RegExp("([^aeiouylsz])\\1$");
+        re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
+        if (re2.test(w)) { w = w + "e"; }
+        else if (re3.test(w)) { re = /.$/; w = w.replace(re,""); }
+        else if (re4.test(w)) { w = w + "e"; }
+      }
+    }
+
+    // Step 1c
+    re = /^(.+?)y$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      stem = fp[1];
+      re = new RegExp(s_v);
+      if (re.test(stem)) { w = stem + "i"; }
+    }
+
+    // Step 2
+    re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      stem = fp[1];
+      suffix = fp[2];
+      re = new RegExp(mgr0);
+      if (re.test(stem)) {
+        w = stem + step2list[suffix];
+      }
+    }
+
+    // Step 3
+    re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      stem = fp[1];
+      suffix = fp[2];
+      re = new RegExp(mgr0);
+      if (re.test(stem)) {
+        w = stem + step3list[suffix];
+      }
+    }
+
+    // Step 4
+    re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
+    re2 = /^(.+?)(s|t)(ion)$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      stem = fp[1];
+      re = new RegExp(mgr1);
+      if (re.test(stem)) {
+        w = stem;
+      }
+    } else if (re2.test(w)) {
+      var fp = re2.exec(w);
+      stem = fp[1] + fp[2];
+      re2 = new RegExp(mgr1);
+      if (re2.test(stem)) {
+        w = stem;
+      }
+    }
+
+    // Step 5
+    re = /^(.+?)e$/;
+    if (re.test(w)) {
+      var fp = re.exec(w);
+      stem = fp[1];
+      re = new RegExp(mgr1);
+      re2 = new RegExp(meq1);
+      re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
+      if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) {
+        w = stem;
+      }
+    }
+
+    re = /ll$/;
+    re2 = new RegExp(mgr1);
+    if (re.test(w) && re2.test(w)) {
+      re = /.$/;
+      w = w.replace(re,"");
+    }
+
+    // and turn initial Y back to y
+
+    if (firstch == "y") {
+      w = firstch.toLowerCase() + w.substr(1);
+    }
+
+    return w;
+  }
+
+  // memoize at the module level
+  var memo = {};
+  var memoizingStemmer = function(w) {
+    if (!memo[w]) {
+      memo[w] = stemmer(w);
+    }
+    return memo[w];
+  }
+
+  if (typeof exports != 'undefined' && exports != null) {
+    exports.stemmer = stemmer;
+    exports.memoizingStemmer = memoizingStemmer;
+  } else if (typeof window != 'undefined' && window != null) {
+	window.stemmer = stemmer;
+	window.memoizingStemmer = memoizingStemmer;
+  } else {
+  	this.stemmer = stemmer;
+  	this.memoizingStemmer = memoizingStemmer;
+  }
+
+})();

tags.coffee.md

@@ -72,7 +72,7 @@ A simple function that cleans up an array of words.
       tags = _.uniq _.compact _.filter list, (t) ->
         (t.length > 1) and
         (t.length < 30) and
-        ($.trim(t.replace(/\d+/gi,"")).length > 1)
+        ((t.replace(/\d+/gi,"")).trim().length > 1)
       tags = _.map tags, (t) -> t.toLowerCase()
       tags = _.without(tags, stopwords...)
       if excludes?.length

tests.coffee

@@ -0,0 +1,11 @@
+Tinytest.add 'example', (test) ->
+  test.equal true, true
+  str = """
+  	Google spins out Project Tango from its Advanced Technology and Projects group - 
+	At the moment, it’s not quite clear what’s happening to Project Tango, Google’s ambitious plan to 
+	put 3D mapping technology inside your smartphone. Today Google’s Advanced Technology and Projects 
+	group (ATAP) announced that, “after two fast-paced years in ATAP, and many technical successes, the 
+	Tango team is transitioning from ATAP to a new home within Google.”
+  """
+  tags = Tags.findFrom str
+  test.equal tags, ["google","spins","project","tango","advanced","technology","group","moment","clear","happening","ambitious","plan","mapping","inside","smartphone","today","atap","announced","two","paced","years","technical","successes","team","transitioning","within"]