PHPのfilter_varのFILTER_VALIDATE_URLとLaravelのurlバリデーションを比較する

PHPFILTER_VALIDATE_URL,filter_var,Laravel,URL,バリデーション

0

以前、phpのfilter_var($url, FILTER_VALIDATE_URL)を調査しましたが、Laravel5.5との比較を行ったのでまとめます。

FILTER_VALIDATE_URLとLaravelのurlバリデーションを比較

比較するコードは下記。

$rules = ['parameter' => 'url'];
use Illuminate\Support\Facades\Validator;

$urls = [
    1,
    "ABC",
    "www.aws.com",
    "http://",
    "http://w",
    "http://ww'",
    "http://www",
    "http://www.aws",
    "http://www.aws.com",
    "https://www.aws.com"
];

foreach ($urls as $url) {
    if (filter_var($url, FILTER_VALIDATE_URL)) {
        echo("'$url' is OK URL\n");
    } else {
        echo("'$url' is NG URL\n");
    }
    if (!Validator::make(['parameter' => $url], $rules)->fails()){
        echo("'$url' is OK URL\n");
    } else {
        echo("'$url' is NG URL\n");
    }
}

比較結果

結果は下記でした。

'1' is NG URL
'1' is NG URL
'ABC' is NG URL
'ABC' is NG URL
'www.aws.com' is NG URL
'www.aws.com' is NG URL
'http://' is NG URL
'http://' is NG URL
'http://w' is OK URL
'http://w' is NG URL
'http://ww'' is NG URL
'http://ww'' is NG URL
'http://www' is OK URL
'http://www' is OK URL
'http://www.aws' is OK URL
'http://www.aws' is OK URL
'http://www.aws.com' is OK URL
'http://www.aws.com' is OK URL
'https://www.aws.com' is OK URL
'https://www.aws.com' is OK URL
'http://w' is OK URL
'http://w' is NG URL

この辺は結果が変わってしまうようです。

FILTER_VALIDATE_URLのソースコード

では、PHPのfilter_varのFILTER_VALIDATE_URLが実際にどんなコードで動いているのでしょうか?

void php_filter_validate_url(PHP_INPUT_FILTER_PARAM_DECL) /* {{{ */
{
	php_url *url;
	size_t old_len = Z_STRLEN_P(value);

	php_filter_url(value, flags, option_array, charset);

	if (Z_TYPE_P(value) != IS_STRING || old_len != Z_STRLEN_P(value)) {
		RETURN_VALIDATION_FAILED
	}

	/* Use parse_url - if it returns false, we return NULL */
	url = php_url_parse_ex(Z_STRVAL_P(value), Z_STRLEN_P(value));

	if (url == NULL) {
		RETURN_VALIDATION_FAILED
	}

	if (url->scheme != NULL &&
		(zend_string_equals_literal_ci(url->scheme, "http") || zend_string_equals_literal_ci(url->scheme, "https"))) {
		char *e, *s, *t;
		size_t l;

		if (url->host == NULL) {
			goto bad_url;
		}

		s = ZSTR_VAL(url->host);
		l = ZSTR_LEN(url->host);
		e = s + l;
		t = e - 1;

		/* An IPv6 enclosed by square brackets is a valid hostname */
		if (*s == '[' && *t == ']' && _php_filter_validate_ipv6((s + 1), l - 2)) {
			php_url_free(url);
			return;
		}

		// Validate domain
		if (!_php_filter_validate_domain(ZSTR_VAL(url->host), l, FILTER_FLAG_HOSTNAME)) {
			php_url_free(url);
			RETURN_VALIDATION_FAILED
		}
	}

	if (
		url->scheme == NULL ||
		/* some schemas allow the host to be empty */
		(url->host == NULL && (!zend_string_equals_literal(url->scheme, "mailto") && !zend_string_equals_literal(url->scheme, "news") && !zend_string_equals_literal(url->scheme, "file"))) ||
		((flags & FILTER_FLAG_PATH_REQUIRED) && url->path == NULL) || ((flags & FILTER_FLAG_QUERY_REQUIRED) && url->query == NULL)
	) {
bad_url:
		php_url_free(url);
		RETURN_VALIDATION_FAILED
	}

	if ((url->user != NULL && !is_userinfo_valid(url->user))
		|| (url->pass != NULL && !is_userinfo_valid(url->pass))
	) {
		php_url_free(url);
		RETURN_VALIDATION_FAILED

	}

	php_url_free(url);
}

まさかのC言語でした。

Laravelのurlバリデーション

次に、Laravelのurlバリデーションは以下。

    /**
     * Validate that an attribute is a valid URL.
     *
     * @param  string  $attribute
     * @param  mixed   $value
     * @return bool
     */
    public function validateUrl($attribute, $value)
    {
        if (! is_string($value)) {
            return false;
        }

        /*
         * This pattern is derived from Symfony\Component\Validator\Constraints\UrlValidator (2.7.4).
         *
         * (c) Fabien Potencier <fabien@symfony.com> http://symfony.com
         */
        $pattern = '~^
            ((aaa|aaas|about|acap|acct|acr|adiumxtra|afp|afs|aim|apt|attachment|aw|barion|beshare|bitcoin|blob|bolo|callto|cap|chrome|chrome-extension|cid|coap|coaps|com-eventbrite-attendee|content|crid|cvs|data|dav|dict|dlna-playcontainer|dlna-playsingle|dns|dntp|dtn|dvb|ed2k|example|facetime|fax|feed|feedready|file|filesystem|finger|fish|ftp|geo|gg|git|gizmoproject|go|gopher|gtalk|h323|ham|hcp|http|https|iax|icap|icon|im|imap|info|iotdisco|ipn|ipp|ipps|irc|irc6|ircs|iris|iris.beep|iris.lwz|iris.xpc|iris.xpcs|itms|jabber|jar|jms|keyparc|lastfm|ldap|ldaps|magnet|mailserver|mailto|maps|market|message|mid|mms|modem|ms-help|ms-settings|ms-settings-airplanemode|ms-settings-bluetooth|ms-settings-camera|ms-settings-cellular|ms-settings-cloudstorage|ms-settings-emailandaccounts|ms-settings-language|ms-settings-location|ms-settings-lock|ms-settings-nfctransactions|ms-settings-notifications|ms-settings-power|ms-settings-privacy|ms-settings-proximity|ms-settings-screenrotation|ms-settings-wifi|ms-settings-workplace|msnim|msrp|msrps|mtqp|mumble|mupdate|mvn|news|nfs|ni|nih|nntp|notes|oid|opaquelocktoken|pack|palm|paparazzi|pkcs11|platform|pop|pres|prospero|proxy|psyc|query|redis|rediss|reload|res|resource|rmi|rsync|rtmfp|rtmp|rtsp|rtsps|rtspu|secondlife|s3|service|session|sftp|sgn|shttp|sieve|sip|sips|skype|smb|sms|smtp|snews|snmp|soap.beep|soap.beeps|soldat|spotify|ssh|steam|stun|stuns|submit|svn|tag|teamspeak|tel|teliaeid|telnet|tftp|things|thismessage|tip|tn3270|turn|turns|tv|udp|unreal|urn|ut2004|vemmi|ventrilo|videotex|view-source|wais|webcal|ws|wss|wtai|wyciwyg|xcon|xcon-userid|xfire|xmlrpc\.beep|xmlrpc.beeps|xmpp|xri|ymsgr|z39\.50|z39\.50r|z39\.50s))://                                 # protocol
            (([\pL\pN-]+:)?([\pL\pN-]+)@)?          # basic auth
            (
                ([\pL\pN\pS\-\.])+(\.?([\pL]|xn\-\-[\pL\pN-]+)+\.?) # a domain name
                    |                                              # or
                \d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}                 # an IP address
                    |                                              # or
                \[
                    (?:(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){6})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:::(?:(?:(?:[0-9a-f]{1,4})):){5})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){4})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,1}(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){3})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,2}(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){2})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,3}(?:(?:[0-9a-f]{1,4})))?::(?:(?:[0-9a-f]{1,4})):)(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,4}(?:(?:[0-9a-f]{1,4})))?::)(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,5}(?:(?:[0-9a-f]{1,4})))?::)(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,6}(?:(?:[0-9a-f]{1,4})))?::))))
                \]  # an IPv6 address
            )
            (:[0-9]+)?                              # a port (optional)
            (/?|/\S+|\?\S*|\#\S*)                   # a /, nothing, a / with something, a query or a fragment
        $~ixu';

        return preg_match($pattern, $value) > 0;
    }

preg_matchしているだけなんですね。

このコードをいちいち比較するのは次元が高すぎるので、今回はやめておきます。。。

0

Posted by riku