urlformatrule.class.php

一个用PHP编写的

             */

            /* Check the protocol */
        if ($url['Protocol'])
        {
            $tmp = preg_replace("/[^a-z0-9+-.]/", '', $url['Protocol']);

            if ($tmp != $url['Protocol'])
            {
                $errArr[EW_ERR_URL_INVALID_PROTOCOL] = EW_ERR_URL_INVALID_PROTOCOL;
            }

            if (count($options['AllowedProtocols']))
                if (!in_array($url['Protocol'], $options['AllowedProtocols']))
                    $errArr[EW_ERR_URL_INVALID_PROTOCOL] = EW_ERR_URL_INVALID_PROTOCOL;

        }

            /* check userinfo */
        if ($url['User'])
        {
                /* Check for % that is NOT an escape sequence */
            if (preg_match('/%[^a-f0-9]/i', $url['User']) || preg_match("/[^a-z0-9;&=+$,_.!~*'()%-]/i", $url['User']))
            {
                $errArr[EW_ERR_URL_INVALID_USER] = EW_ERR_URL_INVALID_USER;
                $url['User'] = urlencode(urldecode($url['User']));
            }
        }
        if ($url['Password'])
        {
                /* Check for % that is NOT an escape sequence */
            if (preg_match('/%[^a-f0-9]/i', $url['Password']) || preg_match("/[^a-z0-9;&=+$,_.!~*'()%-]/i", $url['Password']))
            {
                $errArr[EW_ERR_URL_INVALID_PASSWORD] = EW_ERR_URL_INVALID_PASSWORD;
            }
            $url['Password'] = urlencode(urldecode($url['Password']));
        }

            //      userinfo      = *( unreserved | escaped |
            //                         ";" | ":" | "&" | "=" | "+" | "$" | "," )
            //      unreserved    = alphanum | mark
            //      mark          = "-" | "_" | "." | "!" | "~" | "*" | "'" |
            //                      "(" | ")"

            //      escaped       = "%" hex hex
            /* Check if the server part is an ip */
        if ($url['Server'])
        {
            if (!preg_match('/[^.0-9]/', $url['Server']))
            {
                $ServerIsIP = true;

                $ipErr = false;

                $ipPart = explode('.', $url['Server']);

                if ($ipPart[0] > 224 || $ipPart[0] == 0)
                {
                    $errArr[EW_ERR_URL_INVALID_SERVER] = EW_ERR_URL_INVALID_SERVER;
                }
                else
                {
                    for ($i = 1; $i < 4; $i ++)
                    {
                        $ipPart[$i] = (integer) $ipPart[$i];
                        if ($ipPart[$i] > 255)
                            $errArr[EW_ERR_URL_INVALID_SERVER] = EW_ERR_URL_INVALID_SERVER;
                    }
                }

                    /**
                     * @todo Implement checking for reserved class D and E, and
                     * other reserved addresses such as 0.0.0.0 or 255.255.255.255
                     * and ip-addresses where either the host or the network part
                     * is all binary 0s or all binary 1s
                     * check:
                     * http://www.cisco.com/univercd/cc/td/doc/product/atm/l2020/2020r21x/planning/appndxa.htm#xtocid87496
                     */

                $url['Server'] = join('.', $ipPart);
            }
                /* url is not an ip */
            else
            {
                $ServerIsIP = false;

                $serverParts = explode('.', $url['Server']);

                    /* check serverparts */
                for ($i = 0; $i < count($serverParts); $i ++)
                {
                    $tmp = preg_replace('/[^a-z0-9-]/', '', $serverParts[$i]);
                    
                        /* Check if it is a top-level server */
                    if ($i  && $i == count($serverParts) - 1)
                        $tmp = preg_replace('/^[^a-z]/', '', $tmp);
                    else
                        $tmp = preg_replace('/^[^a-z0-9]/', '', $serverParts[$i]);
                    
                    $tmp = preg_replace('/[^a-z0-9]$/', '', $tmp);

                    if ($serverParts[$i] == '' || $tmp != $serverParts[$i])
                    {
                        if ($tmp != '')
                            $serverParts[$i] = $tmp;
                        else
                            unset($serverParts[$i]);

                        $errArr[EW_ERR_URL_INVALID_SERVER] = EW_ERR_URL_INVALID_SERVER;

                    }
                }

                if (count($serverParts) < 2)
                {
                    if ($Require['TLD'])
                    {
                        $errArr[EW_ERR_URL_MISSING_TLD] = EW_ERR_URL_MISSING_TLD;
                    }
                }
                else
                {

                    $url['TLD'] = $serverParts[count($serverParts) - 1];
                }

                $url['Server'] = join('.', $serverParts);
            }
        }

            /* Check the Port */
        if ($url['Port'])
        {
            $tmp = (integer) $url['Port'];
            if ($url['Port'] != (string) $tmp)
            {
                $errArr[EW_ERR_URL_INVALID_PORT] = EW_ERR_URL_INVALID_PORT;

                $url['Port'] = '';
            }
            else
            {
                $url['Port'] = $tmp;
                if ($url['Port'] > 65535)
                    $errArr[EW_ERR_URL_INVALID_PORT] = EW_ERR_URL_INVALID_PORT;
            }

        }

            /* Check the resource */
            //path          = [ abs_path | opaque_part ]
            //path_segments = segment *( "/" segment )
            //segment       = *pchar *( ";" param )
            //param         = *pchar
            //pchar         = unreserved | escaped |
            //                ":" | "@" | "&" | "=" | "+" | "$" | ","

        if ($url['Resource'])
        {
            $resourceParts = explode('/', $url['Resource']);

            if ($resourceParts[count($resourceParts) - 1] == '')
                array_pop($resourceParts);

            if ($resourceParts[0] == '')
                unset($resourceParts[0]);

            foreach ($resourceParts as $key => $part)
            {
                if ($part == '')
                {
                    $errArr[EW_ERR_URL_INVALID_RESOURCE] = EW_ERR_URL_INVALID_RESOURCE;
                    unset($resourceParts[$key]);
                }

                    /* Check for % that is NOT an escape sequence || invalid chars*/
                elseif (preg_match('/%[^a-f0-9]/i', $part) || preg_match("/[^@a-z0-9_.!~*'()$+&,%:=;?-]/i", $part))
                {
                    $errArr[EW_ERR_URL_INVALID_RESOURCE] = EW_ERR_URL_INVALID_RESOURCE;
                    $resourceParts[$key] = urlencode(urldecode($part));
                }

                    /* check for invalid chars */

            }
            $url['Resource'] = join('/', $resourceParts);
        }

        if ($url['QueryString'])
        {

                /* Check for % NOT part of an escape sequence || invalid chars */
            $tmp = $options['AllowBracks'] ? /**/
                "^a-z0-9_.!~*'()%;\/?:@&=+$,\[\]-" : /**/
                "^a-z0-9_.!~*'()%;\/?:@&=+$,-"; /**/

            if (preg_match('/%[^a-f0-9]/i', $url['QueryString']) || preg_match("/[$tmp]+/i", $url['QueryString']))
            {
                $errArr[EW_ERR_URL_INVALID_QUERYSTRING] = EW_ERR_URL_INVALID_QUERYSTRING;
                $url['QueryString'] = $url['QueryString'];
            }

        }
        if ($url['Anchor'])
        {
            if (preg_match('/%[^a-f0-9][a-f0-9]?/i', $url['Anchor']) || //
                preg_match("/[^a-z0-9-_.!~*'()%;\/?:@&=+$,]/i", $url['Anchor']))
            {
                $errArr[EW_ERR_URL_INVALID_ANCHOR] = EW_ERR_URL_INVALID_ANCHOR;
                $url['Anchor'] = $url['Anchor'];
            }

        }
        foreach ($url as $partName => $notused)
        {
            if ($partName == 'TLD' && $ServerIsIP)
                continue;

            if ($Require[$partName] && !$url[$partName])
                $errArr[$errCodeMissing[$partName]] = $errCodeMissing[$partName];

            if ($Forbid[$partName] && $url[$partName])
                $errArr[$errCodeMissing[$partName]] = $errCodeInvalid[$partName];
        }

            /* Construct an estimate of what the value should've been */
        if ($options['AssumeProtocol'] && !$url['Protocol'] && ($url['Server'] || (!$url['Server'] && !$url['Resource'])))
            $url['Protocol'] = $options['AssumeProtocol'];

        $value = $url['Protocol'];

        if ($url['Protocol'])
        {
            if ($url['Protocol'] == 'mailto' | $url['Protocol'] == 'mailto')
                $value.= ':';
            else
                $value.= '://';
        }

        if ($url['User'])
        {
            if ($url['Password'])
                $value.= "{$url['User']}:{$url['Password']}";
            else
                $value.= "{$url['User']}";

            if ($url['Server'])
                $value.= '@';
        }

        $value.= $url['Server'];

        if ($url['Port'])
            $value.= ":{$url['Port']}";

        if ($url['Server'] && $url['Resource'])
            $value.= "/";

        $value.= $url['Resource'];

        if ($url['QueryString'])
            $value.= "?{$url['QueryString']}";

        if ($url['Anchor'])
            $value.= "#{$url['Anchor']}";

        $r = array('Result' => count($errArr) ? $errArr : EW_OK, 'Value' => $value, 'URLParts' => $url);

        return $r;

    }

}
?>