Host.php

Go to the documentation of this file.

<?php

class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
{

    protected $ipv4;

    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 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.

        // 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 [ "." ]
        $match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
        if (!$match) return false;

        return $string;
    }

}

// vim: et sw=4 sts=4