Tag Archives: validate

array(14) {
  ["scheme"]=>
  string(4) "http"
  ["authority"]=>
  string(17) "garry-lachman.com"
  ["userinfo"]=>
  string(0) ""
  ["host"]=>
  string(17) "garry-lachman.com"
  ["IP_literal"]=>
  string(0) ""
  ["IPV6address"]=>
  string(0) ""
  ["ls32"]=>
  string(0) ""
  ["IPvFuture"]=>
  string(0) ""
  ["IPv4address"]=>
  string(0) ""
  ["regname"]=>
  string(17) "garry-lachman.com"
  ["port"]=>
  string(0) ""
  ["path_abempty"]=>
  string(12) "/2011/10/17/"
  ["query"]=>
  string(22) "test_querystring=value"
  ["url"]=>
  string(59) "http://garry-lachman.com/2011/10/17/?test_querystring=value"
}

// function url_valid($url) { Rev:20110423_2000
//
// Return associative array of valid URI components, or FALSE if $url is not
// RFC-3986 compliant. If the passed URL begins with: "www." or "ftp.", then
// "http://" or "ftp://" is prepended and the corrected full-url is stored in
// the return array with a key name "url". This value should be used by the caller.
//
// Return value: FALSE if $url is not valid, otherwise array of URI components:
// e.g.
// Given: "http://www.jmrware.com:80/articles?height=10&width=75#fragone"
// Array(
//    [scheme] => http
//    [authority] => www.jmrware.com:80
//    [userinfo] =>
//    [host] => www.jmrware.com
//    [IP_literal] =>
//    [IPV6address] =>
//    [ls32] =>
//    [IPvFuture] =>
//    [IPv4address] =>
//    [regname] => www.jmrware.com
//    [port] => 80
//    [path_abempty] => /articles
//    [query] => height=10&width=75
//    [fragment] => fragone
//    [url] => http://www.jmrware.com:80/articles?height=10&width=75#fragone
// )
function url_valid($url) {
    if (strpos($url, 'www.') === 0) $url = 'http://'. $url;
    if (strpos($url, 'ftp.') === 0) $url = 'ftp://'. $url;
    if (!preg_match('/# Valid absolute URI having a non-empty, valid DNS host.
        ^
        (?P<scheme>[A-Za-z][A-Za-z0-9+\-.]*):\/\/
        (?P<authority>
          (?:(?P<userinfo>(?:[A-Za-z0-9\-._~!$&\'()*+,;=:]|%[0-9A-Fa-f]{2})*)@)?
          (?P<host>
            (?P<IP_literal>
              \[
              (?:
                (?P<IPV6address>
                  (?:                                                (?:[0-9A-Fa-f]{1,4}:){6}
                  |                                                ::(?:[0-9A-Fa-f]{1,4}:){5}
                  | (?:                          [0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){4}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,1}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){3}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,2}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){2}
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,3}[0-9A-Fa-f]{1,4})?::   [0-9A-Fa-f]{1,4}:
                  | (?:(?:[0-9A-Fa-f]{1,4}:){0,4}[0-9A-Fa-f]{1,4})?::
                  )
                  (?P<ls32>[0-9A-Fa-f]{1,4}:[0-9A-Fa-f]{1,4}
                  | (?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}
                       (?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)
                  )
                |   (?:(?:[0-9A-Fa-f]{1,4}:){0,5}[0-9A-Fa-f]{1,4})?::   [0-9A-Fa-f]{1,4}
                |   (?:(?:[0-9A-Fa-f]{1,4}:){0,6}[0-9A-Fa-f]{1,4})?::
                )
              | (?P<IPvFuture>[Vv][0-9A-Fa-f]+\.[A-Za-z0-9\-._~!$&\'()*+,;=:]+)
              )
              \]
            )
          | (?P<IPv4address>(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}
                               (?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?))
          | (?P<regname>(?:[A-Za-z0-9\-._~!$&\'()*+,;=]|%[0-9A-Fa-f]{2})+)
          )
          (?::(?P<port>[0-9]*))?
        )
        (?P<path_abempty>(?:\/(?:[A-Za-z0-9\-._~!$&\'()*+,;=:@]|%[0-9A-Fa-f]{2})*)*)
        (?:\?(?P<query>       (?:[A-Za-z0-9\-._~!$&\'()*+,;=:@\\/?]|%[0-9A-Fa-f]{2})*))?
        (?:\#(?P<fragment>    (?:[A-Za-z0-9\-._~!$&\'()*+,;=:@\\/?]|%[0-9A-Fa-f]{2})*))?
        $
        /mx', $url, $m)) return FALSE;
    switch ($m['scheme']) {
    case 'https':
    case 'http':
        if ($m['userinfo']) return FALSE; // HTTP scheme does not allow userinfo.
        break;
    case 'ftps':
    case 'ftp':
        break;
    default:
        return FALSE;   // Unrecognized URI scheme. Default to FALSE.
    }
    // Validate host name conforms to DNS "dot-separated-parts".
    if ($m['regname']) { // If host regname specified, check for DNS conformance.
        if (!preg_match('/# HTTP DNS host name.
            ^                      # Anchor to beginning of string.
            (?!.{256})             # Overall host length is less than 256 chars.
            (?:                    # Group dot separated host part alternatives.
              [A-Za-z0-9]\.        # Either a single alphanum followed by dot
            |                      # or... part has more than one char (63 chars max).
              [A-Za-z0-9]          # Part first char is alphanum (no dash).
              [A-Za-z0-9\-]{0,61}  # Internal chars are alphanum plus dash.
              [A-Za-z0-9]          # Part last char is alphanum (no dash).
              \.                   # Each part followed by literal dot.
            )*                     # Zero or more parts before top level domain.
            (?:                    # Explicitly specify top level domains.
              com|edu|gov|int|mil|net|org|biz|
              info|name|pro|aero|coop|museum|
              asia|cat|jobs|mobi|tel|travel|
              [A-Za-z]{2})         # Country codes are exactly two alpha chars.
              \.?                  # Top level domain can end in a dot.
            $                      # Anchor to end of string.
            /ix', $m['host'])) return FALSE;
    }
    $m['url'] = $url;
    for ($i = 0; isset($m[$i]); ++$i) unset($m[$i]);
    return $m; // return TRUE == array of useful named $matches plus the valid $url.
}