Created
January 13, 2013 08:21
-
-
Save brianteachman/4522951 to your computer and use it in GitHub Desktop.
A PHP array of common English stop words that can loaded by an include statement.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
//http://www.ranks.nl/resources/stopwords.html | |
return $stop_words = array( | |
'a', | |
'about', | |
'above', | |
'after', | |
'again', | |
'against', | |
'all', | |
'am', | |
'an', | |
'and', | |
'any', | |
'are', | |
"aren't", | |
'as', | |
'at', | |
'be', | |
'because', | |
'been', | |
'before', | |
'being', | |
'below', | |
'between', | |
'both', | |
'but', | |
'by', | |
"can't", | |
'cannot', | |
'could', | |
"couldn't", | |
'did', | |
"didn't", | |
'do', | |
'does', | |
"doesn't", | |
'doing', | |
"don't", | |
'down', | |
'during', | |
'each', | |
'few', | |
'for', | |
'from', | |
'further', | |
'had', | |
"hadn't", | |
'has', | |
"hasn't", | |
'have', | |
"haven't", | |
'having', | |
'he', | |
"he'd", | |
"he'll", | |
"he's", | |
'her', | |
'here', | |
"here's", | |
'hers', | |
'herself', | |
'him', | |
'himself', | |
'his', | |
'how', | |
"how's", | |
'i', | |
"i'd", | |
"i'll", | |
"i'm", | |
"i've", | |
'if', | |
'in', | |
'into', | |
'is', | |
"isn't", | |
'it', | |
"it's", | |
'its', | |
'itself', | |
"let's", | |
'me', | |
'more', | |
'most', | |
"mustn't", | |
'my', | |
'myself', | |
'no', | |
'nor', | |
'not', | |
'of', | |
'off', | |
'on', | |
'once', | |
'only', | |
'or', | |
'other', | |
'ought', | |
'our', | |
'ours', | |
'ourselves', | |
'out', | |
'over', | |
'own', | |
'same', | |
"shan't", | |
'she', | |
"she'd", | |
"she'll", | |
"she's", | |
'should', | |
"shouldn't", | |
'so', | |
'some', | |
'such', | |
'than', | |
'that', | |
"that's", | |
'the', | |
'their', | |
'theirs', | |
'them', | |
'themselves', | |
'then', | |
'there', | |
"there's", | |
'these', | |
'they', | |
"they'd", | |
"they'll", | |
"they're", | |
"they've", | |
'this', | |
'those', | |
'through', | |
'to', | |
'too', | |
'under', | |
'until', | |
'up', | |
'very', | |
'was', | |
"wasn't", | |
'we', | |
"we'd", | |
"we'll", | |
"we're", | |
"we've", | |
'were', | |
"weren't", | |
'what', | |
"what's", | |
'when', | |
"when's", | |
'where', | |
"where's", | |
'which', | |
'while', | |
'who', | |
"who's", | |
'whom', | |
'why', | |
"why's", | |
'with', | |
"won't", | |
'would', | |
"wouldn't", | |
'you', | |
"you'd", | |
"you'll", | |
"you're", | |
"you've", | |
'your', | |
'yours', | |
'yourself', | |
'yourselves', | |
'zero' | |
); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment