htmlpurifier update - compatibility issue with language library autoloader

5 files changed, 165 insertions, 92 deletions

diff --git a/library/HTMLPurifier/AttrDef/URI/Email.php b/library/HTMLPurifier/AttrDef/URI/Email.php
index bfee9d166..daf32b764 100644
--- a/library/HTMLPurifier/AttrDef/URI/Email.php
+++ b/library/HTMLPurifier/AttrDef/URI/Email.php
@@ -5,8 +5,11 @@ abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
 
     /**
      * Unpacks a mailbox into its display-name and address
+     * @param string $string
+     * @return mixed
      */
-    function unpack($string) {
+    public function unpack($string)
+    {
         // needs to be implemented
     }
 
diff --git a/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php b/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php
index 94c715ab4..52c0d5968 100644
--- a/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php
+++ b/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php
@@ -7,15 +7,23 @@
 class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
 {
 
-    public function validate($string, $config, $context) {
+    /**
+     * @param string $string
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($string, $config, $context)
+    {
         // no support for named mailboxes i.e. "Bob <bob@example.com>"
         // that needs more percent encoding to be done
-        if ($string == '') return false;
+        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/library/HTMLPurifier/AttrDef/URI/Host.php b/library/HTMLPurifier/AttrDef/URI/Host.php
index 2156c10c6..e7df800b1 100644
--- a/library/HTMLPurifier/AttrDef/URI/Host.php
+++ b/library/HTMLPurifier/AttrDef/URI/Host.php
@@ -7,56 +7,122 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
 {
 
     /**
-     * Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
+     * IPv4 sub-validator.
+     * @type HTMLPurifier_AttrDef_URI_IPv4
      */
     protected $ipv4;
 
     /**
-     * Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
+     * IPv6 sub-validator.
+     * @type HTMLPurifier_AttrDef_URI_IPv6
      */
     protected $ipv6;
 
-    public function __construct() {
+    public function __construct()
+    {
         $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
         $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
     }
 
-    public function validate($string, $config, $context) {
+    /**
+     * @param string $string
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($string, $config, $context)
+    {
         $length = strlen($string);
-        if ($string === '') return '';
-        if ($length > 1 && $string[0] === '[' && $string[$length-1] === ']') {
+        // 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 '['. $valid . ']';
+            if ($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 $ipv4;
+        if ($ipv4 !== false) {
+            return $ipv4;
+        }
 
         // A regular domain name.
 
-        // This breaks I18N domain names, but we don't have proper IRI support,
-        // so force users to insert Punycode. If there's complaining we'll
-        // try to fix things into an international friendly form.
+        // 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-]'; // alphanum | "-"
+        $and = "[a-z0-9-$underscore]"; // alphanum | "-"
         // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
-        $domainlabel   = "$an($and*$an)?";
+        $domainlabel = "$an($and*$an)?";
         // toplabel    = alpha | alpha *( alphanum | "-" ) alphanum
-        $toplabel      = "$a($and*$an)?";
+        $toplabel = "$a($and*$an)?";
         // hostname    = *( domainlabel "." ) toplabel [ "." ]
-        $match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
-        if (!$match) return false;
+        if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
+            return $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/library/HTMLPurifier/AttrDef/URI/IPv4.php b/library/HTMLPurifier/AttrDef/URI/IPv4.php
index ec4cf591b..30ac16c9e 100644
--- a/library/HTMLPurifier/AttrDef/URI/IPv4.php
+++ b/library/HTMLPurifier/AttrDef/URI/IPv4.php
@@ -8,32 +8,38 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
 {
 
     /**
-     * IPv4 regex, protected so that IPv6 can reuse it
+     * IPv4 regex, protected so that IPv6 can reuse it.
+     * @type string
      */
     protected $ip4;
 
-    public function validate($aIP, $config, $context) {
-
-        if (!$this->ip4) $this->_loadRegex();
-
-        if (preg_match('#^' . $this->ip4 . '$#s', $aIP))
-        {
-                return $aIP;
+    /**
+     * @param string $aIP
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($aIP, $config, $context)
+    {
+        if (!$this->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() {
+    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/library/HTMLPurifier/AttrDef/URI/IPv6.php b/library/HTMLPurifier/AttrDef/URI/IPv6.php
index 9454e9be5..f243793ee 100644
--- a/library/HTMLPurifier/AttrDef/URI/IPv6.php
+++ b/library/HTMLPurifier/AttrDef/URI/IPv6.php
@@ -9,91 +9,81 @@
 class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
 {
 
-    public function validate($aIP, $config, $context) {
-
-        if (!$this->ip4) $this->_loadRegex();
+    /**
+     * @param string $aIP
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($aIP, $config, $context)
+    {
+        if (!$this->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
+        $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;
-                }
+        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);
+        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 ($c > 2)
-        {
+        if ($c > 2) {
+            return false;
+        } elseif ($c == 2) {
+            list($first, $second) = $aIP;
+            $first = explode(':', $first);
+            $second = explode(':', $second);
+
+            if (count($first) + count($second) > 8) {
                 return false;
-        }
-        elseif ($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');
-                }
+            while (count($first) < 8) {
+                array_push($first, '0');
+            }
 
-                array_splice($first, 8 - count($second), 8, $second);
-                $aIP = $first;
-                unset($first,$second);
-        }
-        else
-        {
-                $aIP = explode(':', $aIP[0]);
+            array_splice($first, 8 - count($second), 8, $second);
+            $aIP = $first;
+            unset($first, $second);
+        } else {
+            $aIP = explode(':', $aIP[0]);
         }
         $c = count($aIP);
 
-        if ($c != 8)
-        {
-                return false;
+        if ($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', $piece)))
-                {
-                        return false;
-                }
+        foreach ($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