Here’s a (hopefully bug-free) implementation of this expression in plain C:
_Bool is_utf8(const char * string)
{
if(!string)
return 0;
const unsigned char * bytes = (const unsigned char *)string;
while(*bytes)
{
if( (// ASCII
// use bytes[0] <= 0x7F to allow ASCII control characters
bytes[0] == 0x09 ||
bytes[0] == 0x0A ||
bytes[0] == 0x0D ||
(0x20 <= bytes[0] && bytes[0] <= 0x7E)
)
) {
bytes += 1;
continue;
}
if( (// non-overlong 2-byte
(0xC2 <= bytes[0] && bytes[0] <= 0xDF) &&
(0x80 <= bytes[1] && bytes[1] <= 0xBF)
)
) {
bytes += 2;
continue;
}
if( (// excluding overlongs
bytes[0] == 0xE0 &&
(0xA0 <= bytes[1] && bytes[1] <= 0xBF) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF)
) ||
(// straight 3-byte
((0xE1 <= bytes[0] && bytes[0] <= 0xEC) ||
bytes[0] == 0xEE ||
bytes[0] == 0xEF) &&
(0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF)
) ||
(// excluding surrogates
bytes[0] == 0xED &&
(0x80 <= bytes[1] && bytes[1] <= 0x9F) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF)
)
) {
bytes += 3;
continue;
}
if( (// planes 1-3
bytes[0] == 0xF0 &&
(0x90 <= bytes[1] && bytes[1] <= 0xBF) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
(0x80 <= bytes[3] && bytes[3] <= 0xBF)
) ||
(// planes 4-15
(0xF1 <= bytes[0] && bytes[0] <= 0xF3) &&
(0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
(0x80 <= bytes[3] && bytes[3] <= 0xBF)
) ||
(// plane 16
bytes[0] == 0xF4 &&
(0x80 <= bytes[1] && bytes[1] <= 0x8F) &&
(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
(0x80 <= bytes[3] && bytes[3] <= 0xBF)
)
) {
bytes += 4;
continue;
}
return 0;
}
return 1;
}
Please note that this is a faithful translation of the regular expression recommended by W3C for form validation, which does indeed reject some valid UTF-8 sequences (in particular those containing ASCII control characters).
Also, even after fixing this by making the change mentioned in the comment, it still assumes zero-termination, which prevents embedding NUL characters, although it should technically be legal.
When I dabbled in creating my own string library, I went with modified UTF-8 (ie encoding NUL as an overlong two-byte sequence) – feel free to use this header as a template for providing a validation routine which doesn’t suffer from the above shortcomings.