A text cleansing function that is useful for preparing strings prior to lexical analysis.

cleanse.php

<?php

function cleanse ($text)
{
    $text = iconv ('UTF-8', 'ASCII//TRANSLIT//IGNORE', $text); // accented character to 'normal'
    $text = preg_replace ('/[\r\n\s\t]+/xms', ' '    , $text); // normalise whitespace to one space
    $text = preg_replace ('/[^\w\s]+/xms'   , ''     , $text); // remove all punctuation
    return strtolower (trim ($text));                          // lowercase and trimmed
}

?>