idn_to_ascii - PHP code example

How to Solve a Problem With the PHP Function IDN_To_ASCII

If you are using a PHP version below 5.3 you probably will not have the PECL idn or intl extensions installed. So you may run into problems trying to use the idn_to_ascii function. This article will show you how to solve this problem and get the function working properly.

The idn_to_ascii() function converts a domain name in Unicode to its ASCII-compatible form. It returns either the ACE encoded "xn-" string or FALSE if an error occurs. This function is part of the internationalization (or intl) module of PHP. The intl module provides Unicode and Globalization support to PHP.

You may encounter the "Call to undefined Function idn_to_ascii()" error if you try to use this function without the intl extension installed. You should also avoid encoding the input string in utf8 without a BOM or you will run into other errors. This is because most text editors do not handle the utf8 without BOM encoding properly. For example, the string 'casino' will be interpreted as '??????' and the function will fail.

Another way to solve this is to use the idn_to_ascii() method from the ICU library. This method is similar to the idn_to_utf8() method but does not require any PHP PECL extensions. It is a good choice if you want to keep your PHP code small and simple. You can find this method at: https://github.com/jswitch/idn_to_ascii. This is a very simple class which you can download and include into your code to get the function working correctly.

idn_to_ascii example

if (!defined('IDNA_ERROR_INVALID_ACE_LABEL')) {
    define('IDNA_ERROR_INVALID_ACE_LABEL', 1024);
}
if (!defined('IDNA_ERROR_BIDI')) {
    define('IDNA_ERROR_BIDI', 2048);
}
if (!defined('IDNA_ERROR_CONTEXTJ')) {
    define('IDNA_ERROR_CONTEXTJ', 4096);
}

if (!function_exists('idn_to_ascii')) {
    function idn_to_ascii(?string $domain, ?int $flags = IDNA_DEFAULT, ?int $variant = INTL_IDNA_VARIANT_UTS46, &$idna_info = null): string|false { return p\Idn::idn_to_ascii((string) $domain, (int) $flags, (int) $variant, $idna_info); }
}
if (!function_exists('idn_to_utf8')) {
    function idn_to_utf8(?string $domain, ?int $flags = IDNA_DEFAULT, ?int $variant = INTL_IDNA_VARIANT_UTS46, &$idna_info = null): string|false { return p\Idn::idn_to_utf8((string) $domain, (int) $flags, (int) $variant, $idna_info); }
}

    /** * @param string $host * * @return bool */
    protected function checkDns($host)
    {
        $variant = INTL_IDNA_VARIANT_UTS46;

        $host = rtrim(idn_to_ascii($host, IDNA_DEFAULT, $variant), '.');

        $hostParts = explode('.', $host);
        $host = array_pop($hostParts);

        while (count($hostParts) > 0) {
            $host = array_pop($hostParts) . '.' . $host;

            if ($this->validateDnsRecords($host)) {
                return true;
            }
        }

return json_last_error() === JSON_ERROR_NONE;
    }

    /** * Checks for a correctly formatted email address */
    public function valid_email(?string $str = null): bool
    {
        // @see https://regex101.com/r/wlJG1t/1/         if (function_exists('idn_to_ascii') && defined('INTL_IDNA_VARIANT_UTS46') && preg_match('#\A([^@]+)@(.+)\z#', $str ?? '', $matches)) {
            $str = $matches[1] . '@' . idn_to_ascii($matches[2], 0, INTL_IDNA_VARIANT_UTS46);
        }

        return (bool) filter_var($str, FILTER_VALIDATE_EMAIL);
    }

    /** * Validate a comma-separated list of email addresses. * * Example: * valid_emails[one@example.com,two@example.com] */

static::idnSupported()
        ) {
            $domain = substr($address, ++$pos);
            //Verify CharSet string is a valid one, and domain properly encoded in this CharSet.             if ($this->has8bitChars($domain) && @mb_check_encoding($domain, $this->CharSet)) {
                //Convert the domain from whatever charset it's in to UTF-8                 $domain = mb_convert_encoding($domain, self::CHARSET_UTF8, $this->CharSet);
                //Ignore IDE complaints about this line - method signature changed in PHP 5.4                 $errorcode = 0;
                if (defined('INTL_IDNA_VARIANT_UTS46')) {
                    //Use the current punycode standard (appeared in PHP 7.2)                     $punycode = idn_to_ascii(
                        $domain,
                        \IDNA_DEFAULT | \IDNA_USE_STD3_RULES | \IDNA_CHECK_BIDI |
                            \IDNA_CHECK_CONTEXTJ | \IDNA_NONTRANSITIONAL_TO_ASCII,
                        \INTL_IDNA_VARIANT_UTS46
                    );
                } elseif (defined('INTL_IDNA_VARIANT_2003')) {
                    //Fall back to this old, deprecated/removed encoding                     // phpcs:ignore PHPCompatibility.Constants.RemovedConstants.intl_idna_variant_2003Deprecated                     $punycode = idn_to_ascii($domain, $errorcode, \INTL_IDNA_VARIANT_2003);
                } else {
                    //Fall back to a default we don't know about

        return null;
    }

    /** * @return string|false */
    private static function idnToAsci(string $domain, int $options, ?array &$info = [])
    {
        if (\function_exists('idn_to_ascii') && \defined('INTL_IDNA_VARIANT_UTS46')) {
            return \idn_to_ascii($domain, $options, \INTL_IDNA_VARIANT_UTS46, $info);
        }

        throw new \Error('ext-idn or symfony/polyfill-intl-idn not loaded or too old');
    }
}

            $port = $allowedSchemes[$scheme] === $port ? 0 : $port;
            $scheme .= ':';
        }

        if (null !== $host = $parts['host'] ?? null) {
            if (!\defined('INTL_IDNA_VARIANT_UTS46') && preg_match('/[\x80-\xFF]/', $host)) {
                throw new InvalidArgumentException(sprintf('Unsupported IDN "%s", try enabling the "intl" PHP extension or running "composer require symfony/polyfill-intl-idn".', $host));
            }

            $host = \defined('INTL_IDNA_VARIANT_UTS46') ? idn_to_ascii($host, \IDNA_DEFAULT | \IDNA_USE_STD3_RULES | \IDNA_CHECK_BIDI | \IDNA_CHECK_CONTEXTJ | \IDNA_NONTRANSITIONAL_TO_ASCII, \INTL_IDNA_VARIANT_UTS46) ?: strtolower($host) : strtolower($host);
            $host .= $port ? ':'.$port : '';
        }

        foreach (['user', 'pass', 'path', 'query', 'fragment'] as $part) {
            if (!isset($parts[$part])) {
                continue;
            }

            if (str_contains($parts[$part], '%')) {
                // https://tools.ietf.org/html/rfc3986#section-2.3                 $parts[$part] = preg_replace_callback('/%(?:2[DE]|3[0-9]|[46][1-9A-F]|5F|[57][0-9A]|7E)++/i', fn ($m) => rawurldecode($m[0]), $parts[$part]);
            }

/** * Encodes the domain part of an address using IDN. */
    public function encodeString(string $address): string
    {
        $i = strrpos($address, '@');
        if (false !== $i) {
            $local = substr($address, 0, $i);
            $domain = substr($address, $i + 1);

            if (preg_match('/[^\x00-\x7F]/', $domain)) {
                $address = sprintf('%s@%s', $local, idn_to_ascii($domain, \IDNA_DEFAULT | \IDNA_USE_STD3_RULES | \IDNA_CHECK_BIDI | \IDNA_CHECK_CONTEXTJ | \IDNA_NONTRANSITIONAL_TO_ASCII, \INTL_IDNA_VARIANT_UTS46));
            }
        }

        return $address;
    }
}

define('IDNA_ERROR_INVALID_ACE_LABEL', 1024);
}
if (!defined('IDNA_ERROR_BIDI')) {
    define('IDNA_ERROR_BIDI', 2048);
}
if (!defined('IDNA_ERROR_CONTEXTJ')) {
    define('IDNA_ERROR_CONTEXTJ', 4096);
}

if (\PHP_VERSION_ID < 70400) {
    if (!function_exists('idn_to_ascii')) {
        function idn_to_ascii($domain, $flags = 0, $variant = \INTL_IDNA_VARIANT_2003, &$idna_info = null) { return p\Idn::idn_to_ascii($domain, $flags, $variant, $idna_info); }
    }
    if (!function_exists('idn_to_utf8')) {
        function idn_to_utf8($domain, $flags = 0, $variant = \INTL_IDNA_VARIANT_2003, &$idna_info = null) { return p\Idn::idn_to_utf8($domain, $flags, $variant, $idna_info); }
    }
} else {
    if (!function_exists('idn_to_ascii')) {
        function idn_to_ascii($domain, $flags = 0, $variant = \INTL_IDNA_VARIANT_UTS46, &$idna_info = null) { return p\Idn::idn_to_ascii($domain, $flags, $variant, $idna_info); }
    }
    if (!function_exists('idn_to_utf8')) {
        function idn_to_utf8($domain, $flags = 0, $variant = \INTL_IDNA_VARIANT_UTS46, &$idna_info = null) { return p\Idn::idn_to_utf8($domain, $flags, $variant, $idna_info); }
    }
}

    /** * @param string $email * * @return bool */
    public function isValidEmail($email)
    {
        if (function_exists('idn_to_ascii') && defined('INTL_IDNA_VARIANT_UTS46') && $atpos = strpos($email, '@')) {
            $email = static::substr($email, 0, ++$atpos)
                . idn_to_ascii(static::substr($email, $atpos), 0, INTL_IDNA_VARIANT_UTS46);
        }

        return (bool) filter_var($email, FILTER_VALIDATE_EMAIL);
    }

    /** * @param array|string $email * * @return array|string */
    public function cleanEmail($email)
    {

            $this->label = '';
        }
        $this->label .= $this->lexer->current->value;
        return new ValidEmail();
    }

    private function isLabelTooLong(string $label): bool
    {
        if (preg_match('/[^\x00-\x7F]/', $label)) {
            idn_to_ascii($label, IDNA_DEFAULT, INTL_IDNA_VARIANT_UTS46, $idnaInfo);
            return (bool) ($idnaInfo['errors'] & IDNA_ERROR_LABEL_TOO_LONG);
        }
        return strlen($label) > self::LABEL_MAX_LENGTH;
    }

    private function addTLDWarnings(bool $isTLDMissing): void
    {
        if ($isTLDMissing) {
            $this->warnings[TLD::CODE] = new TLD();
        }
    }