Created
June 10, 2011 21:12
-
-
Save freretuc/1019787 to your computer and use it in GitHub Desktop.
Couper une phrase par mots et sélectionner les mots clés
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
$rejet = explode(' ', (file_get_contents('bad_words.txt'))); | |
$interdits = array(',',';','.',':','!','(',')','[',']','-','+','_',"'","\n", "«","»"); | |
// on retire les caractères spéciaux -> espaces | |
$s = strtolower(str_ireplace($interdits,' ', utf8_encode($texte_a_traiter))); | |
// on découpe par espaces | |
$s = explode(' ',$s); | |
foreach($s as $w) { | |
$w = utf8_decode($w); | |
// si le mot fait plus de 2 caractères et qu'il n'appartient pas à la liste des interdits | |
if(strlen(trim($w)) > 2 && !in_array($w,$rejet)) { | |
// traitement à faire sur le mot clé ($w) | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment