用问号替换无效的 UTF-8 字符，mbstring.substitute_character 似乎被忽略了

You can compare byte directly and avoid preg_match's restriction about byte size by this way.

function replace_invalid_byte_sequence6($str) {

    $size = strlen($str);
    $substitute = "xEFxBFxBD";
    $ret = '';

    $pos = 0;
    $char;
    $char_size;
    $valid;

    while (utf8_get_next_char($str, $size, $pos, $char, $char_size, $valid)) {
        $ret .= $valid ? $char : $substitute;
    }

    return $ret;
}

function utf8_get_next_char($str, $str_size, &$pos, &$char, &$char_size, &$valid)
{
    $valid = false;

    if ($str_size <= $pos) {
        return false;
    }

    if ($str[$pos] < "x80") {

        $valid = true;
        $char_size =  1;

    } else if ($str[$pos] < "xC2") {

        $char_size = 1;

    } else if ($str[$pos] < "xE0")  {

        if (!isset($str[$pos+1]) || $str[$pos+1] < "x80" || "xBF" < $str[$pos+1]) {

            $char_size = 1;

        } else {

            $valid = true;
            $char_size = 2;

        }

    } else if ($str[$pos] < "xF0") {

        $left = "xE0" === $str[$pos] ? "xA0" : "x80";
        $right = "xED" === $str[$pos] ? "x9F" : "xBF";

        if (!isset($str[$pos+1]) || $str[$pos+1] < $left || $right < $str[$pos+1]) {

            $char_size = 1;

        } else if (!isset($str[$pos+2]) || $str[$pos+2] < "x80" || "xBF" < $str[$pos+2]) {

            $char_size = 2;

        } else {

            $valid = true;
            $char_size = 3;

       }

    } else if ($str[$pos] < "xF5") {

        $left = "xF0" === $str[$pos] ? "x90" : "x80";
        $right = "xF4" === $str[$pos] ? "x8F" : "xBF";

        if (!isset($str[$pos+1]) || $str[$pos+1] < $left || $right < $str[$pos+1]) {

            $char_size = 1;

        } else if (!isset($str[$pos+2]) || $str[$pos+2] < "x80" || "xBF" < $str[$pos+2]) {

            $char_size = 2;

        } else if (!isset($str[$pos+3]) || $str[$pos+3] < "x80" || "xBF" < $str[$pos+3]) {

            $char_size = 3;

        } else {

            $valid = true;
            $char_size = 4;

        }

    } else {

        $char_size = 1;

    }

    $char = substr($str, $pos, $char_size);
    $pos += $char_size;

    return true;
}

测试用例在这里.

function run(array $callables, array $arguments)
{
    return array_map(function($callable) use($arguments) {
         return array_map($callable, $arguments);
    }, $callables);
}
    
$data = [
    // Table 3-8. Use of U+FFFD in UTF-8 Conversion
    // http://www.unicode.org/versions/Unicode6.1.0/ch03.pdf)
    "x61"."xF1x80x80"."xE1x80"."xC2"."x62"."x80"."x63"
    ."x80"."xBF"."x64",

    // 'FULL MOON SYMBOL' (U+1F315) and invalid byte sequence
    "xF0x9Fx8Cx95"."xF0x9Fx8C"."xF0x9Fx8C"
];

var_dump(run([
    'replace_invalid_byte_sequence', 
    'replace_invalid_byte_sequence2',
    'replace_invalid_byte_sequence3',
    'replace_invalid_byte_sequence4',
    'replace_invalid_byte_sequence5',
    'replace_invalid_byte_sequence6'
], $data));

请注意，mb_convert_encoding 有一个错误，它会在无效字节序列之后立即中断有效字符，或者在不添加 U+FFFD 的情况下删除有效字符之后的无效字节序列.

$data = [
    // U+20AC
    "xE2x82xAC"."xE2x82xAC"."xE2x82xAC",
    "xE2x82"    ."xE2x82xAC"."xE2x82xAC",

    // U+24B62
    "xF0xA4xADxA2"."xF0xA4xADxA2"."xF0xA4xADxA2",
    "xF0xA4xAD"    ."xF0xA4xADxA2"."xF0xA4xADxA2",
    "xA4xADxA2"."xF0xA4xADxA2"."xF0xA4xADxA2",

    // 'FULL MOON SYMBOL' (U+1F315)
    "xF0x9Fx8Cx95" . "xF0x9Fx8C",
    "xF0x9Fx8Cx95" . "xF0x9Fx8C" . "xF0x9Fx8C"
];

str_repeat('a', 10000)

mb_convert_encoding()
0.19628190994263
htmlspecialchars()
0.082863092422485
UConverter::transcode()
0.15999984741211
UConverter::convert()
0.29843020439148
preg_replace_callback()
0.63967490196228
direct comparision
0.71933102607727

function timer(array $callables, array $arguments, $repeat = 10000)
{

    $ret = [];
    $save = $repeat;

    foreach ($callables as $key => $callable) {

        $start = microtime(true);

        do {
    
            array_map($callable, $arguments);

        } while($repeat -= 1);

        $stop = microtime(true);
        $ret[$key] = $stop - $start;
        $repeat = $save;

    }

    return $ret;
}

$functions = [
    'mb_convert_encoding()' => 'replace_invalid_byte_sequence',
    'htmlspecialchars()' => 'replace_invalid_byte_sequence2',
    'UConverter::transcode()' => 'replace_invalid_byte_sequence3',
    'UConverter::convert()' => 'replace_invalid_byte_sequence4',
    'preg_replace_callback()' => 'replace_invalid_byte_sequence5',
    'direct comparision' => 'replace_invalid_byte_sequence6'
];

foreach (timer($functions, $data) as $description => $time) {

    echo $description, PHP_EOL,
         $time, PHP_EOL;

}