/*
* Read a single UTF-8 character starting at @s,
* returning the length, in bytes, of the character read.
*
* This function assumes input is valid UTF-8,
* and that there are enough characters in front of @s.
*/
static int utf8_read_char(const char *s, uchar_t *out)
{
const unsigned char *c = (const unsigned char*) s;
assert(utf8_validate_cz(s));
if (c[0] <= 0x7F) {
/* 00..7F */
*out = c[0];
return 1;
} else if (c[0] <= 0xDF) {
/* C2..DF (unless input is invalid) */
*out = ((uchar_t)c[0] & 0x1F) << 6 |
((uchar_t)c[1] & 0x3F);
return 2;
} else if (c[0] <= 0xEF) {
/* E0..EF */
*out = ((uchar_t)c[0] & 0xF) << 12 |
((uchar_t)c[1] & 0x3F) << 6 |
((uchar_t)c[2] & 0x3F);
return 3;
} else {
/* F0..F4 (unless input is invalid) */
*out = ((uchar_t)c[0] & 0x7) << 18 |
((uchar_t)c[1] & 0x3F) << 12 |
((uchar_t)c[2] & 0x3F) << 6 |
((uchar_t)c[3] & 0x3F);
return 4;
}
}
/* Validate a null-terminated UTF-8 string. */
static bool utf8_validate(const char *s)
{
size_t len;
for (; *s != 0; s += len) {
len = utf8_validate_cz(s);
if (len == 0)
return false;
}
return true;
}
/* Validate a null-terminated UTF-8 string. */
static int utf8_validate(const char *s)
{
int len;
for (; *s != 0; s += len) {
len = utf8_validate_cz(s);
if (len == 0)
return FALSE;
}
return TRUE;
}
