function Idn::utf8Decode

Takes a UTF-8 encoded string and converts it into a series of integer code points. Any invalid byte sequences will be replaced by a U+FFFD replacement code point.

Parameters

string $input:

Return value

array<int, int>

See also

https://encoding.spec.whatwg.org/#utf-8-decoder

3 calls to Idn::utf8Decode()

Idn::mapCodePoints in vendor/symfony/polyfill-intl-idn/Idn.php

Idn::punycodeEncode in vendor/symfony/polyfill-intl-idn/Idn.php

Idn::validateLabel in vendor/symfony/polyfill-intl-idn/Idn.php

File

vendor/symfony/polyfill-intl-idn/Idn.php, line 799

Class

Idn

@internal

Namespace

Symfony\Polyfill\Intl\Idn

Code

private static function utf8Decode($input) {
    $bytesSeen = 0;
    $bytesNeeded = 0;
    $lowerBoundary = 0x80;
    $upperBoundary = 0xbf;
    $codePoint = 0;
    $codePoints = [];
    $length = \strlen($input);
    for ($i = 0; $i < $length; ++$i) {
        $byte = \ord($input[$i]);
        if (0 === $bytesNeeded) {
            if ($byte >= 0x0 && $byte <= 0x7f) {
                $codePoints[] = $byte;
                continue;
            }
            if ($byte >= 0xc2 && $byte <= 0xdf) {
                $bytesNeeded = 1;
                $codePoint = $byte & 0x1f;
            }
            elseif ($byte >= 0xe0 && $byte <= 0xef) {
                if (0xe0 === $byte) {
                    $lowerBoundary = 0xa0;
                }
                elseif (0xed === $byte) {
                    $upperBoundary = 0x9f;
                }
                $bytesNeeded = 2;
                $codePoint = $byte & 0xf;
            }
            elseif ($byte >= 0xf0 && $byte <= 0xf4) {
                if (0xf0 === $byte) {
                    $lowerBoundary = 0x90;
                }
                elseif (0xf4 === $byte) {
                    $upperBoundary = 0x8f;
                }
                $bytesNeeded = 3;
                $codePoint = $byte & 0x7;
            }
            else {
                $codePoints[] = 0xfffd;
            }
            continue;
        }
        if ($byte < $lowerBoundary || $byte > $upperBoundary) {
            $codePoint = 0;
            $bytesNeeded = 0;
            $bytesSeen = 0;
            $lowerBoundary = 0x80;
            $upperBoundary = 0xbf;
            --$i;
            $codePoints[] = 0xfffd;
            continue;
        }
        $lowerBoundary = 0x80;
        $upperBoundary = 0xbf;
        $codePoint = $codePoint << 6 | $byte & 0x3f;
        if (++$bytesSeen !== $bytesNeeded) {
            continue;
        }
        $codePoints[] = $codePoint;
        $codePoint = 0;
        $bytesNeeded = 0;
        $bytesSeen = 0;
    }
    // String unexpectedly ended, so append a U+FFFD code point.
    if (0 !== $bytesNeeded) {
        $codePoints[] = 0xfffd;
    }
    return $codePoints;
}