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
|
#ifndef UTF8_UTIL_H
#define UTF8_UTIL_H
/**
* UTF-8 utility functions
*
* (c) 2010 Steve Bennett <steveb@workware.net.au>
*
* See LICENCE for licence details.
*/
#include <jim-config.h>
/* Currently we support unicode points up to 2^22-1 */
#define MAX_UTF8_LEN 4
/**
* Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
* and stores the result at 'p'.
*
* Returns the number of utf-8 characters (up to MAX_UTF8_LEN).
*/
int utf8_fromunicode(char *p, unsigned uc);
#ifndef JIM_UTF8
#include <ctype.h>
/* No utf-8 support. 1 byte = 1 char */
#define utf8_strlen(S, B) ((B) < 0 ? strlen(S) : (B))
#define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
#define utf8_upper(C) toupper(C)
#define utf8_title(C) toupper(C)
#define utf8_lower(C) tolower(C)
#define utf8_index(C, I) (I)
#define utf8_charlen(C) 1
#define utf8_prev_len(S, L) 1
#else
#if !defined(JIM_BOOTSTRAP)
/**
* Returns the length of the utf-8 sequence starting with 'c'.
*
* Returns 1-4, or -1 if this is not a valid start byte.
*
* Note that charlen=4 is not supported by the rest of the API.
*/
int utf8_charlen(int c);
/**
* Returns the number of characters in the utf-8
* string of the given byte length.
*
* Any bytes which are not part of an valid utf-8
* sequence are treated as individual characters.
*
* The string *must* be null terminated.
*
* Does not support unicode code points > \u1fffff
*/
int utf8_strlen(const char *str, int bytelen);
/**
* Returns the byte index of the given character in the utf-8 string.
*
* The string *must* be null terminated.
*
* This will return the byte length of a utf-8 string
* if given the char length.
*/
int utf8_index(const char *str, int charindex);
/**
* Returns the unicode codepoint corresponding to the
* utf-8 sequence 'str'.
*
* Stores the result in *uc and returns the number of bytes
* consumed.
*
* If 'str' is null terminated, then an invalid utf-8 sequence
* at the end of the string will be returned as individual bytes.
*
* If it is not null terminated, the length *must* be checked first.
*
* Does not support unicode code points > \u1fffff
*/
int utf8_tounicode(const char *str, int *uc);
/**
* Returns the number of bytes before 'str' that the previous
* utf-8 character sequence starts (which may be the middle of a sequence).
*
* Looks back at most 'len' bytes backwards, which must be > 0.
* If no start char is found, returns -len
*/
int utf8_prev_len(const char *str, int len);
/**
* Returns the upper-case variant of the given unicode codepoint.
*
* Unicode code points > \uffff are returned unchanged.
*/
int utf8_upper(int uc);
/**
* Returns the title-case variant of the given unicode codepoint.
*
* If none, returns utf8_upper().
*
* Unicode code points > \uffff are returned unchanged.
*/
int utf8_title(int uc);
/**
* Returns the lower-case variant of the given unicode codepoint.
*
* NOTE: Use utf8_upper() in preference for case-insensitive matching.
*
* Unicode code points > \uffff are returned unchanged.
*/
int utf8_lower(int uc);
#endif /* JIM_BOOTSTRAP */
#endif
#endif
|
