some important stuff we'll need

lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.php

@@ -0,0 +1,17 @@
+<?php
+
+abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
+{
+
+    /**
+     * Unpacks a mailbox into its display-name and address
+     */
+    function unpack($string) {
+        // needs to be implemented
+    }
+
+}
+
+// sub-implementations
+
+// vim: et sw=4 sts=4

lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php

@@ -0,0 +1,21 @@
+<?php
+
+/**
+ * Primitive email validation class based on the regexp found at
+ * http://www.regular-expressions.info/email.html
+ */
+class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
+{
+
+    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;
+        $string = trim($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

lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php

@@ -0,0 +1,101 @@
+<?php
+
+/**
+ * Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
+ */
+class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
+{
+
+    /**
+     * Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
+     */
+    protected $ipv4;
+
+    /**
+     * Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
+     */
+    protected $ipv6;
+
+    public function __construct() {
+        $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
+        $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
+    }
+
+    public function validate($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.
+
+        // The productions describing this are:
+        $a   = '[a-z]';     // alpha
+        $an  = '[a-z0-9]';  // alphanum
+        $and = '[a-z0-9-]'; // 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

lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.php

@@ -0,0 +1,39 @@
+<?php
+
+/**
+ * Validates an IPv4 address
+ * @author Feyd @ forums.devnetwork.net (public domain)
+ */
+class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
+{
+
+    /**
+     * IPv4 regex, protected so that IPv6 can reuse it
+     */
+    protected $ip4;
+
+    public function validate($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() {
+        $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

lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.php

@@ -0,0 +1,99 @@
+<?php
+
+/**
+ * Validates an IPv6 address.
+ * @author Feyd @ forums.devnetwork.net (public domain)
+ * @note This function requires brackets to have been removed from address
+ *       in URI.
+ */
+class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
+{
+
+    public function validate($aIP, $config, $context) {
+
+        if (!$this->ip4) $this->_loadRegex();
+
+        $original = $aIP;
+
+        $hex = '[0-9a-fA-F]';
+        $blk = '(?:' . $hex . '{1,4})';
+        $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))';   // /0 - /128
+
+        //      prefix check
+        if (strpos($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