Created
April 25, 2018 14:16
utf-8 decoder
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* decodes next unicode code point in utf-8-encoded buffer. returns number of bytes | |
read so stream can be advanced, -1 if invalid utf-8 sequence. */ | |
size_t decode_next_utf8(const unsigned char *str, size_t len, int *cp) | |
{ | |
*cp = 0; | |
if (*str <= 0x7f) { | |
*cp = (int)*str; | |
return 1; | |
} else if (((*str & 0xe0) == 0xc0) && len > 1) { | |
if ((*(str+1) & 0xc0) != 0x80) { | |
return -1; | |
} | |
*cp |= (*str++ & 0x1f) << 6; | |
*cp |= (*str & 0x3f) << 0; | |
return 2; | |
} else if (((*str & 0xf0) == 0xe0) && len > 2) { | |
if (((*(str+1) & 0xc0) != 0x80) || (*(str+2) & 0xc0) != 0x80) { | |
return -1; | |
} | |
*cp |= (*str++ & 0xf) << 12; | |
*cp |= (*str++ & 0x1f) << 6; | |
*cp |= (*str & 0x3f) << 0; | |
return 3; | |
} else if (((*str & 0xf8) == 0xf0) && len > 3) { | |
if ((((*(str+1) & 0xc0) != 0x80) || (*(str+2) & 0xc0) != 0x80) || (*(str+3) & 0xc0) != 0x80) { | |
return -1; | |
} | |
*cp |= (*str++ & 0x7) << 18; | |
*cp |= (*str++ & 0xf) << 12; | |
*cp |= (*str++ & 0x1f) << 6; | |
*cp |= (*str & 0x3f) << 0; | |
return 4; | |
} | |
return -1; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment