First draft. Seems the right idea if not a final. Probably needs some kind of a "binary truncation" to avoid doing a crap ton of work if given a couple megabytes of character data but only looking for the first 255 bytes.
Update, redacted the update, it was wrong and only up for 30 seconds. :P
use 5.16.0;
use strict;
use utf8;
use open ":std", ":encoding(utf8)";
use Encode;
# my $str = "艾捷克, 萨塔尔, 胡西它尔.";
my $str = "艾捷"; # Shortened string for terse output example.
my $max_bytes = shift || length encode(utf8 => $str);
while ( $max_bytes )
{
my $length;
$str =~ s/.\z// while ( $max_bytes < ( $length = length encode(utf8 => $str) ) );
$length ||= 0;
say <<"";
Max -> $max_bytes
Actual -> $length
String -> $str
$max_bytes--;
}
__END__
Max -> 6
Actual -> 6
String -> 艾捷
Max -> 5
Actual -> 3
String -> 艾
Max -> 4
Actual -> 3
String -> 艾
Max -> 3
Actual -> 3
String -> 艾
Max -> 2
Actual -> 0
String ->
Max -> 1
Actual -> 0
String ->