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/AttrDef/URI/Email.php | 20 ++++ .../HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php | 29 +++++ .../htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php | 128 +++++++++++++++++++++ .../htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php | 45 ++++++++ .../htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php | 89 ++++++++++++++ 5 files changed, 311 insertions(+) create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php create mode 100644 inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php (limited to 'inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI') diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php new file mode 100644 index 00000000..846d3881 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php @@ -0,0 +1,20 @@ +" + // that needs more percent encoding to be done + if ($string == '') { + return false; + } + $string = trim($string); + $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); + return $result ? $string : false; + } +} + +// vim: et sw=4 sts=4 diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php new file mode 100644 index 00000000..01457785 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php @@ -0,0 +1,128 @@ +ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); + $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $length = strlen($string); + // empty hostname is OK; it's usually semantically equivalent: + // the default host as defined by a URI scheme is used: + // + // If the URI scheme defines a default for host, then that + // default applies when the host subcomponent is undefined + // or when the registered name is empty (zero length). + if ($string === '') { + return ''; + } + if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') { + //IPv6 + $ip = substr($string, 1, $length - 2); + $valid = $this->ipv6->validate($ip, $config, $context); + if ($valid === false) { + return false; + } + return '[' . $valid . ']'; + } + + // need to do checks on unusual encodings too + $ipv4 = $this->ipv4->validate($string, $config, $context); + if ($ipv4 !== false) { + return $ipv4; + } + + // A regular domain name. + + // This doesn't match I18N domain names, but we don't have proper IRI support, + // so force users to insert Punycode. + + // There is not a good sense in which underscores should be + // allowed, since it's technically not! (And if you go as + // far to allow everything as specified by the DNS spec... + // well, that's literally everything, modulo some space limits + // for the components and the overall name (which, by the way, + // we are NOT checking!). So we (arbitrarily) decide this: + // let's allow underscores wherever we would have allowed + // hyphens, if they are enabled. This is a pretty good match + // for browser behavior, for example, a large number of browsers + // cannot handle foo_.example.com, but foo_bar.example.com is + // fairly well supported. + $underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : ''; + + // The productions describing this are: + $a = '[a-z]'; // alpha + $an = '[a-z0-9]'; // alphanum + $and = "[a-z0-9-$underscore]"; // alphanum | "-" + // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum + $domainlabel = "$an($and*$an)?"; + // toplabel = alpha | alpha *( alphanum | "-" ) alphanum + $toplabel = "$a($and*$an)?"; + // hostname = *( domainlabel "." ) toplabel [ "." ] + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + + // If we have Net_IDNA2 support, we can support IRIs by + // punycoding them. (This is the most portable thing to do, + // since otherwise we have to assume browsers support + + if ($config->get('Core.EnableIDNA')) { + $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); + // we need to encode each period separately + $parts = explode('.', $string); + try { + $new_parts = array(); + foreach ($parts as $part) { + $encodable = false; + for ($i = 0, $c = strlen($part); $i < $c; $i++) { + if (ord($part[$i]) > 0x7a) { + $encodable = true; + break; + } + } + if (!$encodable) { + $new_parts[] = $part; + } else { + $new_parts[] = $idna->encode($part); + } + } + $string = implode('.', $new_parts); + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + } catch (Exception $e) { + // XXX error reporting + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php new file mode 100644 index 00000000..bbc8a77e --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php @@ -0,0 +1,45 @@ +ip4) { + $this->_loadRegex(); + } + + if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) { + return $aIP; + } + return false; + } + + /** + * Lazy load function to prevent regex from being stuffed in + * cache. + */ + protected function _loadRegex() + { + $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 + $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; + } +} + +// vim: et sw=4 sts=4 diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php new file mode 100644 index 00000000..67f148bd --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php @@ -0,0 +1,89 @@ +ip4) { + $this->_loadRegex(); + } + + $original = $aIP; + + $hex = '[0-9a-fA-F]'; + $blk = '(?:' . $hex . '{1,4})'; + $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 + + // prefix check + if (strpos($aIP, '/') !== false) { + if (preg_match('#' . $pre . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + unset($find); + } else { + return false; + } + } + + // IPv4-compatiblity check + if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + $ip = explode('.', $find[0]); + $ip = array_map('dechex', $ip); + $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; + unset($find, $ip); + } + + // compression check + $aIP = explode('::', $aIP); + $c = count($aIP); + if ($c > 2) { + return false; + } elseif ($c == 2) { + list($first, $second) = $aIP; + $first = explode(':', $first); + $second = explode(':', $second); + + if (count($first) + count($second) > 8) { + return false; + } + + while (count($first) < 8) { + array_push($first, '0'); + } + + array_splice($first, 8 - count($second), 8, $second); + $aIP = $first; + unset($first, $second); + } else { + $aIP = explode(':', $aIP[0]); + } + $c = count($aIP); + + if ($c != 8) { + return false; + } + + // All the pieces should be 16-bit hex strings. Are they? + foreach ($aIP as $piece) { + if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) { + return false; + } + } + return $original; + } +} + +// vim: et sw=4 sts=4 -- cgit v1.2.3