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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
|
/**
* 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 <assert.h>
#include "utf8.h"
/* This one is always implemented */
int utf8_fromunicode(char *p, unsigned uc)
{
if (uc <= 0x7f) {
*p = uc;
return 1;
}
else if (uc <= 0x7ff) {
*p++ = 0xc0 | ((uc & 0x7c0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 2;
}
else if (uc <= 0xffff) {
*p++ = 0xe0 | ((uc & 0xf000) >> 12);
*p++ = 0x80 | ((uc & 0xfc0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 3;
}
/* Note: We silently truncate to 21 bits here: 0x1fffff */
else {
*p++ = 0xf0 | ((uc & 0x1c0000) >> 18);
*p++ = 0x80 | ((uc & 0x3f000) >> 12);
*p++ = 0x80 | ((uc & 0xfc0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 4;
}
}
#if defined(JIM_UTF8) && !defined(JIM_BOOTSTRAP)
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_prev_len(const char *str, int len)
{
int n = 1;
assert(len > 0);
/* Look up to len chars backward for a start-of-char byte */
while (--len) {
if ((str[-n] & 0x80) == 0) {
/* Start of a 1-byte char */
break;
}
if ((str[-n] & 0xc0) == 0xc0) {
/* Start of a multi-byte char */
break;
}
n++;
}
return n;
}
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;
}
}
else if (s[0] < 0xf8) {
if (((str[1] & 0xc0) == 0x80) && ((str[2] & 0xc0) == 0x80) && ((str[3] & 0xc0) == 0x80)) {
*uc = ((s[0] & ~0xf0) << 18) | ((s[1] & ~0x80) << 12) | ((s[2] & ~0x80) << 6) | (s[3] & ~0x80);
return 4;
}
}
/* Invalid sequence, so just return the byte */
*uc = *s;
return 1;
}
struct casemap {
unsigned short code; /* code point */
unsigned short altcode; /* alternate case code point */
};
/* Generated mapping tables */
#include "_unicode_mapping.c"
#define ARRAYSIZE(A) sizeof(A) / sizeof(*(A))
static int cmp_casemap(const void *key, const void *cm)
{
return *(int *)key - (int)((const struct casemap *)cm)->code;
}
static int utf8_map_case(const struct casemap *mapping, int num, int ch)
{
/* We only support 16 bit case mapping */
if (ch <= 0xffff) {
const struct casemap *cm =
bsearch(&ch, mapping, num, sizeof(*mapping), cmp_casemap);
if (cm) {
return cm->altcode;
}
}
return ch;
}
/* Some platforms don't have isascii */
#ifndef isascii
#define isascii(C) (!((C) & ~0x7f))
#endif
int utf8_upper(int ch)
{
if (isascii(ch)) {
return toupper(ch);
}
return utf8_map_case(unicode_case_mapping_upper, ARRAYSIZE(unicode_case_mapping_upper), ch);
}
int utf8_lower(int ch)
{
if (isascii(ch)) {
return tolower(ch);
}
return utf8_map_case(unicode_case_mapping_lower, ARRAYSIZE(unicode_case_mapping_lower), ch);
}
int utf8_title(int ch)
{
int newch = utf8_map_case(unicode_case_mapping_title, ARRAYSIZE(unicode_case_mapping_title), ch);
if (newch != ch) {
return newch ? newch : ch;
}
return utf8_upper(ch);
}
#endif /* JIM_BOOTSTRAP */
|
