natural 0.2.1 → 0.4.0

package/lib/natural/brill_pos_tagger/lib/TF_Parser.pegjs

@@ -0,0 +1,55 @@
+{
+  var TransformationRule = require("./TransformationRule");
+}
+
+transformation_rules = rules: (S transformation_rule S) +
+{
+  var result = [];
+
+  for (var i = 0; i < rules.length; i++) {
+    result.push(rules[i][1]);
+  }
+  return(result);
+}
+
+transformation_rule = c1: category1 c2: category2 pred: predicate par1: parameter par2: parameter ?
+{
+  // Construct rule
+  var result = new TransformationRule(c1, c2, pred, par1, par2);
+  return(result);
+}
+
+category1 = wild_card / identifier
+
+category2 = identifier
+
+predicate = identifier
+
+parameter = identifier
+
+identifier =
+  characters: [a-zA-Z_0-9_\-\.,()]+ S_no_eol
+  {
+   var s = "";
+   for (var i = 0; i < characters.length; i++) {
+     s += characters[i];
+   }
+   return(s);
+  }
+
+wild_card = wc: "*" S_no_eol
+  {
+   return(wc)
+  }
+
+// Blanks
+EOL =
+  '\r\n' / '\n' / '\r'
+Comment =
+  "\/\/" (!EOL .)* (EOL/EOI)
+S =
+  (' ' / '\t' / EOL / Comment)*
+S_no_eol =
+  (' ' / '\t' / Comment)*
+EOI= 
+  !.

package/lib/natural/brill_pos_tagger/lib/TransformationRule.js

@@ -0,0 +1,49 @@
+/*
+    Transformation rules for the Brill tagger
+    Copyright (C) 2015 Hugo W.L. ter Doest
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+var log4js = require('log4js');
+var logger = log4js.getLogger();
+
+var Predicate = require("./Predicate");
+
+logger.setLevel('ERROR');
+
+var category_wild_card = "*";
+
+function TransformationRule(c1, c2, predicate, parameter1, parameter2) {
+  this.literal = [c1, c2, predicate, parameter1, parameter2];
+  this.predicate = new Predicate(predicate, parameter1, parameter2);
+  this.old_category = c1;
+  this.new_category = c2;
+  logger.debug('TransformationRule constructor: ' + this.literal);
+}
+
+TransformationRule.prototype.apply = function(tagged_sentence, position) {
+  if ((tagged_sentence[position][1] === this.old_category) ||
+      (this.old_category === category_wild_card)) {
+    if (this.predicate.evaluate(tagged_sentence, position)) {
+      tagged_sentence[position][1] = this.new_category;
+      logger.debug('TransformationRule.apply: changed category ' + 
+                   this.old_category + ' to ' + this.new_category +
+                   ' at position ' + position);
+    }
+  }
+};
+
+module.exports = TransformationRule;
+  

package/lib/natural/classifiers/bayes_classifier.js

@@ -20,10 +20,9 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 */
 
-var PorterStemmer = require('../stemmers/porter_stemmer'),
-util = require('util'),
-Classifier = require('./classifier'),
-ApparatusBayesClassifier = require('apparatus').BayesClassifier;
+var util = require('util'),
+    Classifier = require('./classifier'),
+    ApparatusBayesClassifier = require('apparatus').BayesClassifier;
 
 var BayesClassifier = function(stemmer, smoothing) {
     var abc = new ApparatusBayesClassifier();
@@ -48,7 +47,9 @@ function load(filename, stemmer, callback) {
         if (err) {
             callback(err);
         }
-        callback(err, restore(classifier, stemmer));
+        else {
+            callback(err, restore(classifier, stemmer));
+        }
     });
 }
 

package/lib/natural/classifiers/classifier.js

@@ -47,8 +47,9 @@ function addDocument(text, classification) {
 	text: text
     });
 
-    for(var i = 0; i < text.length; i++) {
-	this.features[text[i]] = 1;
+    for (var i = 0; i < text.length; i++) {
+        var token = text[i];
+        this.features[token] = (this.features[token] || 0) + 1;
     }
 }
 

package/lib/natural/classifiers/logistic_regression_classifier.js

@@ -20,10 +20,9 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 */
 
-var PorterStemmer = require('../stemmers/porter_stemmer'),
-util = require('util'),
-Classifier = require('./classifier'),
-ApparatusLogisticRegressionClassifier = require('apparatus').LogisticRegressionClassifier;
+var util = require('util'),
+    Classifier = require('./classifier'),
+    ApparatusLogisticRegressionClassifier = require('apparatus').LogisticRegressionClassifier;
 
 var LogisticRegressionClassifier = function(stemmer) {
     Classifier.call(this, new ApparatusLogisticRegressionClassifier(), stemmer);
@@ -41,7 +40,12 @@ function restore(classifier, stemmer) {
 
 function load(filename, stemmer, callback) {
     Classifier.load(filename, function(err, classifier) {
-        callback(err, restore(classifier, stemmer));
+        if (err) {
+            callback(err);
+        }
+        else {
+            callback(err, restore(classifier, stemmer));
+        }
     });
 }
 

package/lib/natural/distance/dice_coefficient.js

@@ -48,22 +48,32 @@ var sanitize = function (str) {
 
 // Compare two strings, and spit out a number from 0-1
 var compare = function (str1, str2) {
-  var pairs1 = wordLetterPairs(sanitize(str1));
-  var pairs2 = wordLetterPairs(sanitize(str2));
+  var sanitized_str1 = sanitize(str1);
+  var sanitized_str2 = sanitize(str2);
+  var pairs1 = wordLetterPairs(sanitized_str1);
+  var pairs2 = wordLetterPairs(sanitized_str2);
   var intersection = 0, union = pairs1.length + pairs2.length;
-  var i, j, pair1, pair2;
-  for (i = 0; i < pairs1.length; i++) {
-    pair1 = pairs1[i];
-    for (j = 0; j < pairs2.length; j++) {
-      pair2 = pairs2[j];
-      if (pair1 == pair2) {
-        intersection ++;
-        delete pairs2[j];
-        break;
+  if (union === 0) {
+      if (sanitized_str1 === sanitized_str2) {
+          return 1;
+      } else {
+          return 0;
+      }
+  } else {
+    var i, j, pair1, pair2;
+    for (i = 0; i < pairs1.length; i++) {
+      pair1 = pairs1[i];
+      for (j = 0; j < pairs2.length; j++) {
+        pair2 = pairs2[j];
+        if (pair1 == pair2) {
+          intersection ++;
+          delete pairs2[j];
+          break;
+        }
       }
     }
+    return 2 * intersection / union;
   }
-  return 2 * intersection / union;
 };
 
 module.exports = compare;

package/lib/natural/index.js

@@ -31,12 +31,14 @@ exports.PorterStemmerRu = require('./stemmers/porter_stemmer_ru');
 exports.PorterStemmerEs = require('./stemmers/porter_stemmer_es');
 exports.PorterStemmerIt = require('./stemmers/porter_stemmer_it');
 exports.PorterStemmerNo = require('./stemmers/porter_stemmer_no');
+exports.PorterStemmerPt = require('./stemmers/porter_stemmer_pt');
 exports.LancasterStemmer = require('./stemmers/lancaster_stemmer');
 exports.StemmerFr = require('./stemmers/stemmer_fr');
 exports.StemmerPl = require('./stemmers/stemmer_pl');
 exports.StemmerJa = require('./stemmers/stemmer_ja');
 exports.AggressiveTokenizerNl = require('./tokenizers/aggressive_tokenizer_nl');
 exports.AggressiveTokenizerFa = require('./tokenizers/aggressive_tokenizer_fa');
+exports.AggressiveTokenizerFr = require('./tokenizers/aggressive_tokenizer_fr');
 exports.AggressiveTokenizerRu = require('./tokenizers/aggressive_tokenizer_ru');
 exports.AggressiveTokenizerEs = require('./tokenizers/aggressive_tokenizer_es');
 exports.AggressiveTokenizerIt = require('./tokenizers/aggressive_tokenizer_it');
@@ -44,11 +46,13 @@ exports.AggressiveTokenizerPl = require('./tokenizers/aggressive_tokenizer_pl');
 exports.AggressiveTokenizerPt = require('./tokenizers/aggressive_tokenizer_pt');
 exports.AggressiveTokenizerNo = require('./tokenizers/aggressive_tokenizer_no');
 exports.AggressiveTokenizer = require('./tokenizers/aggressive_tokenizer');
+exports.CaseTokenizer = require('./tokenizers/tokenizer_case');
 exports.RegexpTokenizer = require('./tokenizers/regexp_tokenizer').RegexpTokenizer;
 exports.WordTokenizer = require('./tokenizers/regexp_tokenizer').WordTokenizer;
 exports.WordPunctTokenizer = require('./tokenizers/regexp_tokenizer').WordPunctTokenizer;
 exports.TreebankWordTokenizer = require('./tokenizers/treebank_word_tokenizer');
 exports.TokenizerJa = require('./tokenizers/tokenizer_ja');
+exports.SentenceTokenizer = require('./tokenizers/sentence_tokenizer');
 exports.BayesClassifier = require('./classifiers/bayes_classifier');
 exports.LogisticRegressionClassifier = require('./classifiers/logistic_regression_classifier');
 exports.NounInflector = require('./inflectors/noun_inflector');
@@ -62,6 +66,7 @@ exports.Trie = require('./trie/trie');
 exports.SentenceAnalyzer = require('./analyzers/sentence_analyzer');
 exports.stopwords = require('./util/stopwords').words;
 exports.ShortestPathTree = require('./util/shortest_path_tree');
+exports.Spellcheck = require('./spellcheck/spellcheck');
 exports.LongestPathTree = require('./util/longest_path_tree');
 exports.EdgeWeightedDigraph = require('./util/edge_weighted_digraph');
 exports.NGrams = require('./ngrams/ngrams');
@@ -73,3 +78,4 @@ exports.normalize = require('./normalizers/normalizer').normalize_tokens;
 exports.normalize_ja = require('./normalizers/normalizer_ja').normalize_ja;
 exports.removeDiacritics = require('./normalizers/remove_diacritics');
 exports.transliterate_ja = require('./transliterators/ja');
+exports.BrillPOSTagger = require('./brill_pos_tagger/lib/Brill_POS_Tagger');

package/lib/natural/ngrams/ngrams.js

@@ -42,6 +42,10 @@ exports.trigrams = function(sequence, startSymbol, endSymbol) {
     return ngrams(sequence, 3, startSymbol, endSymbol);
 }
 
+exports.multrigrams = function(sequence, n, startSymbol, endSymbol) {
+    return ngrams(sequence, n, startSymbol, endSymbol);
+}
+
 var ngrams = function(sequence, n, startSymbol, endSymbol) {
     var result = [];
     

package/lib/natural/stemmers/stemmer.js

@@ -38,14 +38,39 @@ module.exports = function() {
         stopwords.words = stopwords.words.concat(moreStopWords);
     };
 
+    stemmer.removeStopWord = function(stopWord) {
+        this.removeStopWords([stopWord])
+    };
+
+    stemmer.removeStopWords = function(moreStopWords) {
+        moreStopWords.forEach(function(stopWord){
+            var idx = stopwords.words.indexOf(stopWord);
+            if (idx >= 0) {
+                stopwords.words.splice(idx, 1);
+            }
+        });
+
+    };
+
+
     stemmer.tokenizeAndStem = function(text, keepStops) {
         var stemmedTokens = [];
-        
-        new Tokenizer().tokenize(text).forEach(function(token) {
-            if(keepStops || stopwords.words.indexOf(token) == -1)
+        var lowercaseText = text.toLowerCase();
+        var tokens = new Tokenizer().tokenize(lowercaseText);
+
+        if (keepStops) {
+            tokens.forEach(function(token) {
                 stemmedTokens.push(stemmer.stem(token));
-        });
-        
+            });
+        }
+
+        else {
+            tokens.forEach(function(token) {
+                if (stopwords.words.indexOf(token) == -1)
+                    stemmedTokens.push(stemmer.stem(token));
+            });
+        }
+
         return stemmedTokens;
     };
 
@@ -53,7 +78,7 @@ module.exports = function() {
         String.prototype.stem = function() {
             return stemmer.stem(this);
         };
-        
+
         String.prototype.tokenizeAndStem = function(keepStops) {
             return stemmer.tokenizeAndStem(this, keepStops);
         };

package/lib/natural/tokenizers/regexp_tokenizer.js

@@ -62,7 +62,7 @@ exports.RegexpTokenizer = RegexpTokenizer;
  * 
  */
 var WordTokenizer = function(options) {
-    this._pattern = /\W+/;
+    this._pattern = /[^A-Za-zА-Яа-я0-9_]+/;
     RegexpTokenizer.call(this,options)
 };
 
@@ -74,11 +74,11 @@ exports.WordTokenizer = WordTokenizer;
  * non-alphabetic characters.  E.g.:
  *
  *      >>> WordPunctTokenizer().tokenize("She said 'hello'.")
- *      ['She', 'said', "'", 'hello', "'."]
+ *      ["She","said","'","hello","'","."]
  * 
  */
 var WordPunctTokenizer = function(options) {
-    this._pattern = new RegExp(/(\w+|\!|\'|\"")/i);
+    this._pattern = new RegExp(/(\w+|[а-я0-9_]+|\.|\!|\'|\"")/i);
     RegexpTokenizer.call(this,options)
 };
 

package/{examples/inflection/noun.js → lib/natural/tokenizers/sentence_tokenizer.js}

@@ -20,18 +20,22 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 */
 
-var natural = require('natural'),
-    nounInflector = new natural.NounInflector();
+var Tokenizer = require('./tokenizer'),
+    util = require('util');
 
-plural = nounInflector.pluralize('radius');
-console.log(plural);
+var SentenceTokenizer = function() {
+    Tokenizer.call(this);
+};
+util.inherits(SentenceTokenizer, Tokenizer);
 
-plural = nounInflector.pluralize('beer');
-console.log(plural);
+SentenceTokenizer.prototype.tokenize = function(text) {
+    // break string up in to sentences based on punctation and quotation marks
+    var tokens = text.match(/([\"\'\‘\“\'\"\[\(\{\⟨][^\.\?\!]+[\.\?\!][\"\'\’\”\'\"\]\)\}\⟩]|[^\.\?\!]+[\.\?\!])\s?/g);
 
-singular = nounInflector.singularize('radii');
-console.log(singular);
+    // remove unecessary white space
+    tokens = tokens.map(Function.prototype.call, String.prototype.trim);
 
-singular = nounInflector.singularize('beers');
-console.log(singular);
+    return this.trim(tokens);
+};
 
+module.exports = SentenceTokenizer;

package/lib/natural/tokenizers/tokenizer_case.js

@@ -0,0 +1,58 @@
+/*
+ Copyright (c) 2011, Chris Umbel, Alex Langberg
+
+ Permission is hereby granted, free of charge, to any person obtaining a copy
+ of this software and associated documentation files (the "Software"), to deal
+ in the Software without restriction, including without limitation the rights
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ copies of the Software, and to permit persons to whom the Software is
+ furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ THE SOFTWARE.
+ */
+
+var Tokenizer = require('./tokenizer'),
+  util = require('util'),
+  CaseTokenizer = function() {
+    Tokenizer.call(this);
+  };
+
+util.inherits(CaseTokenizer, Tokenizer);
+
+CaseTokenizer.prototype.attach = function() {
+  var self = this;
+
+  String.prototype.tokenize = function(preserveApostrophe) {
+    return self.tokenize(this, preserveApostrophe);
+  }
+};
+
+// Idea from Seagull: http://stackoverflow.com/a/26482650
+CaseTokenizer.prototype.tokenize = function(text, preserveApostrophe) {
+  var whitelist = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'];
+  var lower = text.toLowerCase();
+  var upper = text.toUpperCase();
+  var result = '';
+  var i;
+
+  for (i = 0; i < lower.length; ++i) {
+    if (lower[i] !== upper[i] || whitelist.indexOf(lower[i]) > -1 || (text[i] === '\'' && preserveApostrophe)) {
+      result += text[i];
+    } else {
+      result += ' ';
+    }
+  }
+
+  return this.trim(result.replace(/\s+/g, ' ').split(' '));
+};
+
+module.exports = CaseTokenizer;

package/lib/natural/util/bag.js

@@ -28,6 +28,7 @@ function Bag() {
 
 Bag.prototype.add = function(element) {
     this.dictionary.push(element);
+    this.nElement++;
     return this;
 };
 

package/lib/natural/wordnet/wordnet.js

@@ -137,9 +137,9 @@ function WordNet(dataDir) {
 
   if (!dataDir) {
     try {
-      var WNdb = require('WNdb');
+      var WNdb = require('wordnet-db');
     } catch(e) {
-      console.error("Please 'npm install WNdb' before using WordNet module or specify a dict directory.");
+      console.error("Please 'npm install wordnet-db' before using WordNet module or specify a dict directory.");
       throw e;
     }
     dataDir = WNdb.path;

package/lib/natural/wordnet/wordnet_file.js

@@ -37,7 +37,7 @@ function appendLineChar(fd, pos, buffPos, buff, callback) {
       console.log(err);
     else {
       if(buff[buffPos] == 10 || buffPos == buff.length)
-        callback(buff.slice(0, buffPos).toString('ASCII'));
+        callback(buff.slice(0, buffPos).toString('UTF-8'));
       else {
         appendLineChar(fd, pos + 1, buffPos + 1, buff, callback);
       }

package/lr_classifier.json

@@ -0,0 +1 @@
+{"classifier":{"examples":{"computing":[[1,1,0,0,0,0,0,0,0],[0,0,1,1,0,0,0,0,0],[0,0,0,1,1,1,0,0,0]],"literature":[[0,0,1,0,0,0,1,0,0],[0,0,0,0,0,0,1,1,0],[0,0,0,0,0,0,1,0,1]]},"features":[],"featurePositions":{},"maxFeaturePosition":0,"classifications":["computing","literature"],"exampleCount":6,"theta":[{"elements":[2.0057203693422903,2.0057203693422903,0.0904766662626176,3.447364098636818,0.9696521506748157,0.9696521506748157,-4.840706080886848,-1.2267353995937322,-1.2267353995937322]},{"elements":[-2.00572036934229,-2.00572036934229,-0.09047666626261795,-3.447364098636819,-0.9696521506748155,-0.9696521506748155,4.84070608088685,1.2267353995937313,1.2267353995937313]}]},"docs":[{"label":"computing","text":["fix","box"]},{"label":"computing","text":["write","code"]},{"label":"computing","text":["nasti","script","code"]},{"label":"literature","text":["write","book"]},{"label":"literature","text":["read","book"]},{"label":"literature","text":["studi","book"]}],"features":{"fix":1,"box":1,"write":2,"code":2,"nasti":1,"script":1,"book":3,"read":1,"studi":1},"stemmer":{},"lastAdded":6,"events":{"domain":null,"_events":{},"_maxListeners":10}}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "natural",
   "description": "General natural language (tokenizing, stemming (English, Russian, Spanish), classification, inflection, phonetics, tfidf, WordNet, jaro-winkler, Levenshtein distance, Dice's Coefficient) facilities for node.",
-  "version": "0.2.1",
+  "version": "0.4.0",
   "homepage": "https://github.com/NaturalNode/natural",
   "repository": {
     "type": "git",
@@ -13,7 +13,8 @@
   "dependencies": {
     "sylvester": ">= 0.0.12",
     "apparatus": ">= 0.0.9",
-    "underscore": ">=1.3.1"
+    "underscore": ">=1.3.1",
+    "log4js": "*"
   },
   "devDependencies": {
     "uubench": "0.0.x",
@@ -22,6 +23,7 @@
   "scripts": {
     "test": "NODE_PATH=. node_modules/jasmine-node/bin/jasmine-node spec/"
   },
+  "license": "MIT",
   "author": "Chris Umbel <chris@chrisumbel.com>",
   "keywords": [
     "natural",
@@ -42,7 +44,8 @@
     "double",
     "jaro-winkler",
     "levenshtein",
-    "distance"
+    "distance",
+    "tagger"
   ],
   "main": "./lib/natural/index.js",
   "maintainers": [

package/package.json~

@@ -0,0 +1,66 @@
+{
+  "name": "natural",
+  "description": "General natural language (tokenizing, stemming (English, Russian, Spanish), classification, inflection, phonetics, tfidf, WordNet, jaro-winkler, Levenshtein distance, Dice's Coefficient) facilities for node.",
+  "version": "0.3.0",
+  "homepage": "https://github.com/NaturalNode/natural",
+  "repository": {
+    "type": "git",
+    "url": "git://github.com/NaturalNode/natural.git"
+  },
+  "engines": {
+    "node": ">=0.4.10"
+  },
+  "dependencies": {
+    "sylvester": ">= 0.0.12",
+    "apparatus": ">= 0.0.9",
+    "underscore": ">=1.3.1",
+    "log4js": "*"
+  },
+  "devDependencies": {
+    "uubench": "0.0.x",
+    "jasmine-node": "~1.13.1"
+  },
+  "scripts": {
+    "test": "NODE_PATH=. node_modules/jasmine-node/bin/jasmine-node spec/"
+  },
+  "license": "MIT",
+  "author": "Chris Umbel <chris@chrisumbel.com>",
+  "keywords": [
+    "natural",
+    "language",
+    "porter",
+    "lancaster",
+    "stemmer",
+    "bayes",
+    "classifier",
+    "phonetic",
+    "metaphone",
+    "inflector",
+    "wordnet",
+    "tf-idf",
+    "logistic",
+    "regression",
+    "doublemetaphone",
+    "double",
+    "jaro-winkler",
+    "levenshtein",
+    "distance",
+    "tagger"
+  ],
+  "main": "./lib/natural/index.js",
+  "maintainers": [
+    {
+      "name": "Chris Umbel",
+      "email": "chris@chrisumbel.com",
+      "web": "http://www.chrisumbel.com"
+    },
+    {
+      "name": "Rob Ellis",
+      "email": "rob@silentrob.me"
+    },
+    {
+      "name": "Ken Koch",
+      "email": "kkoch986@gmail.com"
+    }
+  ]
+}

package/benchmarks/index.js

@@ -1,32 +0,0 @@
-
-/**
- * Module dependencies.
- */
-
-var uubench = require('uubench')
-  , natural = require('../');
-
-fs = require('fs');
-metaphone = natural.Metaphone.process;
-soundex = natural.SoundEx.process;
-
-suite = new uubench.Suite({
-  start: function(){
-    console.log();
-  },
-
-  result: function(name, stats){
-    var persec = 1000 / stats.elapsed
-      , ops = stats.iterations * persec;
-    console.log('  \033[90m%s : \033[36m%s \033[90mops/s\033[0m', name, ops | 0);
-  },
-  
-  done: function(){
-    console.log();
-  }
-});
-
-require('./metaphone');
-require('./soundex');
-
-suite.run();

package/benchmarks/metaphone.js

@@ -1,27 +0,0 @@
-
-// single word
-
-suite.bench('metaphone() word', function(next){
-  metaphone('stephen');
-  next();
-});
-
-// small body of text
-
-var words = fs.readFileSync('lib/natural/index.js', 'utf8').split(/\W+/);
-suite.bench('metaphone() small', function(next){
-  for (var i = 0, len = words.length; i < len; ++i) {
-    metaphone(words[i]);
-  }
-  next();
-});
-
-// medium body of text
-
-var words2 = fs.readFileSync('README.md', 'utf8').split(/\W+/);
-suite.bench('metaphone() medium', function(next){
-  for (var i = 0, len = words2.length; i < len; ++i) {
-    metaphone(words2[i]);
-  }
-  next();
-});