blob: 6f654e24c4db0a325867a3ffa66ee4d1e5241b49 (
plain)
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
#ifndef NU_UTF8_H
#define NU_UTF8_H
#include <stdint.h>
#include <sys/types.h>
#include <libnu/config.h>
#include <libnu/defines.h>
#include <libnu/utf8_internal.h>
/** @defgroup utf8 UTF-8 support
*
* Note: There is no utf8_string[i] equivalent - it will be slow,
* use nu_utf8_read() and nu_utf8_revread() instead
*
* @example utf8.c
* @example revread.c
*/
#if defined (__cplusplus) || defined (c_plusplus)
extern "C" {
#endif
#ifdef NU_WITH_UTF8_READER
/** Read codepoint from UTF-8 string
*
* @ingroup utf8
* @param utf8 pointer to UTF-8 encoded string
* @param unicode output unicode codepoint or 0
* @return pointer to next codepoint in UTF-8 string
*/
static inline
const char* nu_utf8_read(const char *utf8, uint32_t *unicode) {
uint32_t c = *(unsigned char *)(utf8);
if (c >= 0x80) {
if (c < 0xE0) {
if (unicode != 0) {
utf8_2b(utf8, unicode);
}
return utf8 + 2;
}
else if (c < 0xF0) {
if (unicode != 0) {
utf8_3b(utf8, unicode);
}
return utf8 + 3;
}
else {
if (unicode != 0) {
utf8_4b(utf8, unicode);
}
return utf8 + 4;
}
}
else if (unicode != 0) {
*unicode = c;
}
return utf8 + 1;
}
#ifdef NU_WITH_REVERSE_READ
/** Read codepoint from UTF-8 string in backward direction
*
* Note that it is your responsibility to check that this call
* is not going under beginning of encoded string. Normally you
* shouldn't call it like this: nu_utf8_revread(&u, "hello"); which
* will result in undefined behavior
*
* @ingroup utf8
* @param unicode output unicode codepoint or 0
* @param utf8 pointer to UTF-8 encoded string
* @return pointer to previous codepoint in UTF-8 string
*/
static inline
const char* nu_utf8_revread(uint32_t *unicode, const char *utf8) {
/* valid UTF-8 has either 10xxxxxx (continuation byte)
* or beginning of byte sequence */
const char *p = utf8 - 1;
while (((unsigned char)(*p) & 0xC0) == 0x80) { /* skip every 0b10000000 */
--p;
}
if (unicode != 0) {
nu_utf8_read(p, unicode);
}
return p;
}
#endif /* NU_WITH_REVERSE_READ */
#ifdef NU_WITH_VALIDATION
/** Validate codepoint in string
*
* @ingroup utf8
* @param encoded buffer with encoded string
* @param max_len buffer length
* @return codepoint length or 0 on error
*/
NU_EXPORT
int nu_utf8_validread(const char *encoded, size_t max_len);
#endif /* NU_WITH_VALIDATION */
#endif /* NU_WITH_UTF8_READER */
#ifdef NU_WITH_UTF8_WRITER
/** Write unicode codepoints into UTF-8 encoded string
*
* @ingroup utf8
* @param unicode unicode codepoint
* @param utf8 pointer to buffer to write UTF-8 encoded text to,
* should be large enough to hold encoded value
* @return pointer to byte after last written
*/
NU_EXPORT
char* nu_utf8_write(uint32_t unicode, char *utf8);
#endif /* NU_WITH_UTF8_WRITER */
#if defined (__cplusplus) || defined (c_plusplus)
}
#endif
#endif /* NU_UTF8_H */
|
