KjwString.php

<?php // vim:ts=4:sw=4:noet:fenc=utf8
/*====================================================================== 
Copyright (C) 2006-2009, Walter Doekes
This file is part of KjwLib-php45.
 
KjwLib-php45 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. 

KjwLib-php45 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 KjwLib-php45.  If not, see <http://www.gnu.org/licenses/>. 
======================================================================*/

// TODO: should perhaps remove overlong encoded utf8, but hopefully
// the next user in line ignores the overlong utf8 like it should.
function kjwstring_safe_line($single_line) {
    return preg_replace("/[\x01-\x1f]/", '', str_replace("\t", '        ', str_replace("\x00", '', $single_line)));
}

function kjwstring_remove_western_accents($string) {
        static $a = array(
                'À','Á','Â','Ã','Ä','Å','Æ',
                'Ç','È','É','Ê','Ë','Ì','Í','Î','Ï',
                'Ñ','Ò','Ó','Ô','Õ','Ö','Ø','Ù','Ú','Û','Ü','Ý','Ÿ','Y',
                'ß','à','á','â','ã','ä','å','æ',
                'ç','è','é','ê','ë','ì','í','î','ï',
                'ñ','ò','ó','ô','õ','ö','ø','ù','ú','û','ü','ý','ÿ',
                'Š','Œ','Ž','š','œ','ž'
        );
        static $b = array(
                'A','A','A','A','A','AA','AE',
                'C','E','E','E','E','I','I','I','I',
                'n','O','O','O','O','O','OE','U','U','U','U','Y','Y','Y',
                'ss','a','a','a','a','a','aa','ae',
                'c','e','e','e','e','i','i','i','i',
                'n','o','o','o','o','o','oe','u','u','u','u','y','y',
                'S','OE','Z','s','oe','z'
        );
        return str_replace($a, $b, $string);
}

function kjwstring_urlify($string) {
        return trim(preg_replace('![^A-Za-z0-9-]+!', '_',
                kjwstring_remove_western_accents($string)
        ), '_');
}

?>

---