From d4949327efa15b492cab1bef3fe074290a328a17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 21 Feb 2014 15:43:14 +0100 Subject: [add] HTML Purifier added to clean code --- .../htmlpurifier/HTMLPurifier/Injector/Linkify.php | 59 ++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/Injector/Linkify.php (limited to 'inc/3rdparty/htmlpurifier/HTMLPurifier/Injector/Linkify.php') diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/Injector/Linkify.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/Injector/Linkify.php new file mode 100644 index 00000000..5eed3c12 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/Injector/Linkify.php @@ -0,0 +1,59 @@ + array('href')); + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + + if (strpos($token->data, '://') === false) { + // our really quick heuristic failed, abort + // this may not work so well if we want to match things like + // "google.com", but then again, most people don't + return; + } + + // there is/are URL(s). Let's split the string: + // Note: this regex is extremely permissive + $bits = preg_split('#((?:https?|ftp)://[^\s\'",<>()]+)#Su', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + + + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 -- cgit v1.2.3