1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
|
#include <stdint.h>
#include <stdarg.h>
/* is c the start of a utf8 sequence? */
#define isutf(c) (((c)&0xC0)!=0x80)
/* convert UTF-8 data to wide character */
int u8_toucs(uint32_t *dest, int sz, char *src, int srcsz);
/* the opposite conversion */
int u8_toutf8(char *dest, int sz, uint32_t *src, int srcsz);
/* single character to UTF-8 */
int u8_wc_toutf8(char *dest, uint32_t ch);
/* character number to byte offset */
int u8_offset(char *str, int charnum);
/* byte offset to character number */
int u8_charnum(char *s, int offset);
/* return next character, updating an index variable */
uint32_t u8_nextchar(const char *s, int *i);
/* move to next character */
void u8_inc(char *s, int *i);
/* move to previous character */
void u8_dec(char *s, int *i);
/* returns length of next utf-8 sequence */
int u8_seqlen(char *s);
/* assuming src points to the character after a backslash, read an
escape sequence, storing the result in dest and returning the number of
input characters processed */
int u8_read_escape_sequence(char *src, uint32_t *dest);
/* 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. */
int u8_escape_wchar(char *buf, int sz, uint32_t ch);
/* convert a string "src" containing escape sequences to UTF-8 */
int u8_unescape(char *buf, int sz, char *src);
/* convert UTF-8 "src" to ASCII with escape sequences.
if escape_quotes is nonzero, quote characters will be preceded by
backslashes as well. */
int u8_escape(char *buf, int sz, char *src, int escape_quotes);
/* utility predicates used by the above */
int octal_digit(char c);
int hex_digit(char c);
/* return a pointer to the first occurrence of ch in s, or NULL if not
found. character index of found character returned in *charn. */
char *u8_strchr(char *s, uint32_t ch, int *charn);
/* same as the above, but searches a buffer of a given size instead of
a NUL-terminated string. */
char *u8_memchr(char *s, uint32_t ch, size_t sz, int *charn);
/* count the number of characters in a UTF-8 string */
int u8_strlen(char *s);
int u8_is_locale_utf8(char *locale);
/* printf where the format string and arguments may be in UTF-8.
you can avoid this function and just use ordinary printf() if the current
locale is UTF-8. */
int u8_vprintf(char *fmt, va_list ap);
int u8_printf(char *fmt, ...);
int u8_isvalid(const char *input);
|
