my %utf8byte = (
0x00, '
single byte ASCII',
0x80, ' | multi-byte continuation',
0xC0, ' | (overl.)',
0xC2, ' | 2-byte sequence start',
0xD0, ' | ',
0xE0, ' | 3-byte sequence start',
0xF0, ' | 4-byte sequence',
0xF5, ' | (overflow)',
0xF8, ' | 5-byte',
0xFC, ' | 6-byte',
0xFE, ' | invalid',
);
sub {
return defined $utf8byte{$_[0]} ? $utf8byte{$_[0]} : ();
}
|