ref: bbfee60f6716dce8cf7a802c044cf7d0fe8bb6f2
dir: /src/utf8.h/
#pragma once
/* is c the start of a utf8 sequence? */
#define isutf(c) (((c)&0xC0) != 0x80)
/* byte offset to character number */
usize u8_charnum(const char *s, usize offset) sl_purefn;
/* next character without NUL character terminator */
Rune u8_nextmemchar(const char *s, usize *i);
/* returns length of next utf-8 sequence */
usize u8_seqlen(const char *s) sl_purefn;
/* length of a utf-8 string in runes */
usize u8_runelen(const char *s, usize nb) sl_purefn;
char read_escape_control_char(char c) sl_constfn;
/* given a wide character, convert it to an ASCII escape sequence stored in
buf, where buf is "sz" bytes. returns the number of characters output.
sz must be at least 3. */
int u8_escape_rune(char *buf, usize sz, Rune ch);
/* convert UTF-8 "src" to escape sequences.
sz is buf size in bytes. must be at least 12.
if escape_quotes is nonzero, quote characters will be escaped.
if ascii is nonzero, the output is 7-bit ASCII, no UTF-8 survives.
starts at src[*pi], updates *pi to point to the first unprocessed
byte of the input.
end is one more than the last allowable value of *pi.
returns number of bytes placed in buf, including a NUL terminator.
*/
usize u8_escape(char *buf, usize sz, const char *src, usize *pi, usize end,
bool escape_quotes, bool ascii);
/* utility predicates used by the above */
bool octal_digit(char c) sl_constfn;
bool hex_digit(char c) sl_constfn;
/* same as the above, but searches a buffer of a given size instead of
a NUL-terminated string. */
char *u8_memchr(char *s, Rune ch, usize sz, usize *charn);
/* number of columns occupied by a string */
ssize u8_strwidth(const char *s, ssize n) sl_purefn;
/* determine whether a sequence of bytes is valid UTF-8. length is in bytes */
bool u8_isvalid(const char *str, int length) sl_purefn;
/* reverse a UTF-8 string. len is length in bytes. dest and src must both
be allocated to at least len+1 bytes. returns 1 for error, 0 otherwise */
void u8_reverse(char *dest, char *src, usize len);