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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
/**
* UTF-8 utility functions
*
* (c) 2010 Steve Bennett <steveb@workware.net.au>
*
* See LICENCE for licence details.
*/
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include "utf8.h"
/* This one is always implemented */
int utf8_fromunicode(char *p, unsigned short uc)
{
if (uc <= 0x7f) {
*p = uc;
return 1;
}
else if (uc <= 0x7ff) {
*p++ = 0xc0 | ((uc & 0x7c0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 2;
}
else {
*p++ = 0xe0 | ((uc & 0xf000) >> 12);
*p++ = 0x80 | ((uc & 0xfc0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 3;
}
}
#ifdef JIM_UTF8
int utf8_charlen(int c)
{
if ((c & 0x80) == 0) {
return 1;
}
if ((c & 0xe0) == 0xc0) {
return 2;
}
if ((c & 0xf0) == 0xe0) {
return 3;
}
if ((c & 0xf8) == 0xf0) {
return 4;
}
/* Invalid sequence */
return -1;
}
int utf8_strlen(const char *str, int bytelen)
{
int charlen = 0;
if (bytelen < 0) {
bytelen = strlen(str);
}
while (bytelen) {
int c;
int l = utf8_tounicode(str, &c);
charlen++;
str += l;
bytelen -= l;
}
return charlen;
}
int utf8_index(const char *str, int index)
{
const char *s = str;
while (index--) {
int c;
s += utf8_tounicode(s, &c);
}
return s - str;
}
int utf8_charequal(const char *s1, const char *s2)
{
int c1, c2;
utf8_tounicode(s1, &c1);
utf8_tounicode(s2, &c2);
return c1 == c2;
}
int utf8_tounicode(const char *str, int *uc)
{
unsigned const char *s = (unsigned const char *)str;
if (s[0] < 0xc0) {
*uc = s[0];
return 1;
}
if (s[0] < 0xe0) {
if ((s[1] & 0xc0) == 0x80) {
*uc = ((s[0] & ~0xc0) << 6) | (s[1] & ~0x80);
return 2;
}
}
else if (s[0] < 0xf0) {
if (((str[1] & 0xc0) == 0x80) && ((str[2] & 0xc0) == 0x80)) {
*uc = ((s[0] & ~0xe0) << 12) | ((s[1] & ~0x80) << 6) | (s[2] & ~0x80);
return 3;
}
}
/* Invalid sequence, so just return the byte */
*uc = *s;
return 1;
}
struct casemap {
unsigned short code; /* code point */
signed char lowerdelta; /* add for lowercase, or if -128 use the ext table */
signed char upperdelta; /* add for uppercase, or offset into the ext table */
};
/* Extended table for codepoints where |delta| > 127 */
struct caseextmap {
unsigned short lower;
unsigned short upper;
};
/* Generated mapping tables */
#include "unicode_mapping.c"
#define NUMCASEMAP sizeof(unicode_case_mapping) / sizeof(*unicode_case_mapping)
static int cmp_casemap(const void *key, const void *cm)
{
return *(int *)key - (int)((const struct casemap *)cm)->code;
}
int utf8_upper(int uc)
{
const struct casemap *cm;
if (isascii(uc)) {
return toupper(uc);
}
cm = bsearch(&uc, unicode_case_mapping, NUMCASEMAP, sizeof(*unicode_case_mapping), cmp_casemap);
if (cm) {
if (cm->lowerdelta == -128) {
uc = unicode_extmap[cm->upperdelta].upper;
}
else {
uc += cm->upperdelta;
}
}
return uc;
}
int utf8_lower(int uc)
{
const struct casemap *cm;
if (isascii(uc)) {
return tolower(uc);
}
cm = bsearch(&uc, unicode_case_mapping, NUMCASEMAP, sizeof(*unicode_case_mapping), cmp_casemap);
if (cm) {
if (cm->lowerdelta == -128) {
uc = unicode_extmap[cm->upperdelta].lower;
}
else {
uc += cm->lowerdelta;
}
}
return uc;
}
#endif
|
