Skip to content

Commit

Permalink
Adding stop words.
Browse files Browse the repository at this point in the history
  • Loading branch information
vesln committed Jan 20, 2012
1 parent e8d4106 commit 324fe10
Show file tree
Hide file tree
Showing 4 changed files with 86 additions and 0 deletions.
48 changes: 48 additions & 0 deletions lib/stop_words.js
@@ -0,0 +1,48 @@
/*!
* Bot - Feeling lonely? You personal bot is here.
*
* Veselin Todorov <hi@vesln.com>
* MIT License.
*/

/**
* Exposing the stop words.
*/
module.exports = [
'a', 'about', 'above', 'above', 'across', 'after', 'afterwards',
'again', 'against', 'all', 'almost', 'alone', 'along',
'already', 'also','although','always','am','among', 'amongst',
'amoungst', 'amount', 'an', 'and', 'another', 'any','anyhow',
'anyone','anything','anyway', 'anywhere', 'are', 'around',
'as', 'at', 'back','be','became', 'because','become','becomes',
'becoming', 'been', 'before', 'beforehand', 'behind', 'being', 'below',
'beside', 'besides', 'between', 'beyond', 'bill', 'both', 'bottom','but',
'by', 'call', 'can', 'cannot', 'cant', 'co', 'con', 'could', 'couldnt', 'cry',
'de', 'describe', 'detail', 'do', 'done', 'down', 'due', 'during', 'each',
'eg', 'eight', 'either', 'eleven','else', 'elsewhere', 'empty', 'enough',
'etc', 'even', 'ever', 'every', 'everyone', 'everything', 'everywhere',
'except', 'few', 'fifteen', 'fify', 'fill', 'find', 'fire', 'first', 'five',
'for', 'former', 'formerly', 'forty', 'found', 'four', 'from', 'front', 'full',
'further', 'get', 'give', 'go', 'had', 'has', 'hasnt', 'have', 'he', 'hence',
'her', 'here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers', 'herself',
'him', 'himself', 'his', 'how', 'however', 'hundred', 'ie', 'if', 'in', 'inc',
'indeed', 'interest', 'into', 'is', 'it', 'its', 'itself', 'keep', 'last', 'latter',
'latterly', 'least', 'less', 'ltd', 'made', 'many', 'may', 'me', 'meanwhile', 'might',
'mill', 'mine', 'more', 'moreover', 'most', 'mostly', 'move', 'much', 'must', 'my',
'myself', 'name', 'namely', 'neither', 'never', 'nevertheless', 'next', 'nine', 'no',
'nobody', 'none', 'noone', 'nor', 'not', 'nothing', 'now', 'nowhere', 'of', 'off', 'often',
'on', 'once', 'one', 'only', 'onto', 'or', 'other', 'others', 'otherwise', 'our', 'ours',
'ourselves', 'out', 'over', 'own','part', 'per', 'perhaps', 'please', 'put', 'rather', 're',
'same', 'see', 'seem', 'seemed', 'seeming', 'seems', 'serious', 'several', 'she',
'should', 'show', 'side', 'since', 'sincere', 'six', 'sixty', 'so', 'some', 'somehow',
'someone', 'something', 'sometime', 'sometimes', 'somewhere', 'still', 'such', 'system',
'take', 'ten', 'than', 'that', 'the', 'their', 'them', 'themselves', 'then', 'thence',
'there', 'thereafter', 'thereby', 'therefore', 'therein', 'thereupon', 'these', 'they',
'thickv', 'thin', 'third', 'this', 'those', 'though', 'three', 'through', 'throughout',
'thru', 'thus', 'to', 'together', 'too', 'top', 'toward', 'towards', 'twelve', 'twenty',
'two', 'un', 'under', 'until', 'up', 'upon', 'us', 'very', 'via', 'was', 'we', 'well',
'were', 'what', 'whatever', 'when', 'whence', 'whenever', 'where', 'whereafter', 'whereas',
'whereby', 'wherein', 'whereupon', 'wherever', 'whether', 'which', 'while',
'whither', 'who', 'whoever', 'whole', 'whom', 'whose', 'why', 'will', 'with',
'within', 'without', 'would', 'yet', 'you', 'your', 'yours', 'yourself', 'yourselves', 'the'
];
25 changes: 25 additions & 0 deletions lib/text.js
Expand Up @@ -5,6 +5,13 @@
* MIT License.
*/

/**
* Stop words.
*
* @type {Array}
*/
var stopWords = require('./stop_words');

/**
* Text constructor.
*
Expand All @@ -23,6 +30,7 @@ function Text(text) {
*/
Text.prototype.analyze = function(text) {
var type = null;
var words = [];

switch (text.charAt(text.length -1)) {
case '!':
Expand All @@ -36,6 +44,14 @@ Text.prototype.analyze = function(text) {
}

this._type = type;

text.split(/\s+/).forEach(function(word) {
word = word.toLowerCase().replace(/\W+/g, '');
if (~stopWords.indexOf(word)) return;
words.push(word);
});

this._words = words;
};

/**
Expand All @@ -47,6 +63,15 @@ Text.prototype.type = function() {
return this._type;
};

/**
* Returns text words.
*
* @returns {Array}
*/
Text.prototype.words = function() {
return this._words;
};

/**
* Exposing `Text`.
*/
Expand Down
6 changes: 6 additions & 0 deletions test/bot.test.js
Expand Up @@ -36,4 +36,10 @@ describe('Bot', function() {
});
});
});

describe('.words()', function() {
it('should remove pointless words for the unnecessary words', function() {

});
});
});
7 changes: 7 additions & 0 deletions test/text.test.js
Expand Up @@ -47,4 +47,11 @@ describe('Text', function() {
});
});
});

describe('.words()', function() {
it('should remove stop words', function() {
var text = new Text('I love her. Am I an idiot?');
text.words().should.eql(['i', 'love', 'i', 'idiot']);
});
});
});

0 comments on commit 324fe10

Please sign in to comment.