-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathunicode.c
277 lines (251 loc) · 7.24 KB
/
unicode.c
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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
/* Unicode module, utf8 encoding */
#include "unicode.h"
#ifdef UNICODE_DEBUG
#include <stdio.h>
#define UNI_DEBUG(x) do { printf x; puts("\n"); } while (0)
#else
#define UNI_DEBUG(x)
#endif
#define INVALID_TAIL(c) ((c & 0xc0) != 0x80)
/* utf8_decode_len - Returns the number of chars needed to
* fully decode an utf8 encoded string starting with [ch].
* -1 is returned in case of error.
*/
int
utf8_decode_len(unsigned char ch)
{
if (ch < 0x80)
return 1;
else if (ch < 0xc0)
return -1;
else if (ch < 0xe0)
return 2;
else if (ch < 0xf0)
return 3;
else if (ch < 0xf8)
return 4;
else
return -1;
}
/* utf8_rune_len - Returns the number of bytes needed to
* encode a given Rune.
*
* -1 is returned in case of error.
*/
int
utf8_rune_len(Rune ucs)
{
if (ucs < 0x80)
return 1;
else if (ucs < 0x800)
return 2;
else if (ucs < 0x10000)
return 3;
else if (ucs < 0x110000)
return 4;
else
return -1;
}
/* utf8_rune_nlen - Returns the number of chars needed to
* encode a given string of Rune of length [len].
*/
int
utf8_rune_nlen(const Rune * ucs, int len)
{
int count = 0, i;
for (i = 0; i < len; i++)
count += utf8_rune_len(ucs[i]);
return count;
}
/* utf8_encode_rune - Encodes a given Rune using the utf8
* encoding scheme in a the string [s], writing, at most
* [len] chars. If [len] is not enough to fully encode the
* Rune, return 0.
*/
int
utf8_encode_rune(Rune ucs, unsigned char *s, int len)
{
if (ucs < 0x80) {
if (len < 1)
return 0;
s[0] = (unsigned char)ucs;
return 1;
} else if (ucs < 0x800) {
if (len < 2)
return 0;
s[0] = (unsigned char)0xc0 | (ucs >> 6);
s[1] = (unsigned char)0x80 | (ucs & 0x3f);
return 2;
} else if (ucs < 0x10000) {
if (len < 3)
return 0;
s[0] = (unsigned char)0xe0 | (ucs >> 12);
s[1] = (unsigned char)0x80 | ((ucs >> 6) & 0x3f);
s[2] = (unsigned char)0x80 | (ucs & 0x3f);
return 3;
} else if (ucs < 0x110000) {
if (len < 4)
return 0;
s[0] = (unsigned char)0xf0 | (ucs >> 18);
s[1] = (unsigned char)0x80 | ((ucs >> 12) & 0x3f);
s[2] = (unsigned char)0x80 | ((ucs >> 6) & 0x3f);
s[3] = (unsigned char)0x80 | (ucs & 0x3f);
return 4;
} else {
UNI_DEBUG(("utf8_encode_rune: invalid rune supplied"));
return -1;
}
}
/* utf8_decode_rune - Decodes one Rune from a utf8 encoded
* string containing at least [len] chars. Returns the
* number of chars processed int [str].
*
* If not enough data is present to decode 0 is returned.
*/
int
utf8_decode_rune(Rune *r, const unsigned char *str, int len)
{
unsigned char c;
int read, n;
Rune ucs;
if (len < 1)
return 0;
c = *str++;
if (c < 0x80) {
*r = c;
return 1;
}
else if (c < 0xc0) {
goto fail;
}
else if (c < 0xe0) {
read = 2;
ucs = c & 0x1f;
}
else if (c < 0xf0) {
read = 3;
ucs = c & 0xf;
}
else if (c < 0xf8) {
read = 4;
ucs = c & 0x7;
}
else {
goto fail;
}
if (len < read)
return 0;
for (n=0; n<read-1; n++) {
c = *str++;
if (INVALID_TAIL(c))
goto fail;
ucs <<= 6;
ucs |= c & 0x3f;
}
if (read == utf8_rune_len(ucs)) {
*r = ucs;
return read;
}
fail:
*r = WRONGRUNE;
return 1;
}
/* Char width determination */
struct interval {
Rune first;
Rune last;
};
static int
bisearch(Rune ucs, const struct interval *table, int max)
{
int min = 0;
int mid;
if (ucs < table[0].first || ucs > table[max].last)
return 0;
while (max >= min) {
mid = (min + max) / 2;
if (ucs > table[mid].last)
min = mid + 1;
else if (ucs < table[mid].first)
max = mid - 1;
else
return 1;
}
return 0;
}
/* unicode_rune_width - Credit goes to Markus Kuhn for this function,
* latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
*/
int
unicode_rune_width(Rune ucs)
{
static const struct interval comb[] = {
{0x0300, 0x036f}, {0x0483, 0x0486}, {0x0488, 0x0489},
{0x0591, 0x05bd}, {0x05bf, 0x05bf}, {0x05c1, 0x05c2},
{0x05c4, 0x05c5}, {0x05c7, 0x05c7}, {0x0600, 0x0603},
{0x0610, 0x0615}, {0x064b, 0x065e}, {0x0670, 0x0670},
{0x06d6, 0x06e4}, {0x06e7, 0x06e8}, {0x06ea, 0x06ed},
{0x070f, 0x070f}, {0x0711, 0x0711}, {0x0730, 0x074a},
{0x07a6, 0x07b0}, {0x07eb, 0x07f3}, {0x0901, 0x0902},
{0x093c, 0x093c}, {0x0941, 0x0948}, {0x094d, 0x094d},
{0x0951, 0x0954}, {0x0962, 0x0963}, {0x0981, 0x0981},
{0x09bc, 0x09bc}, {0x09c1, 0x09c4}, {0x09cd, 0x09cd},
{0x09e2, 0x09e3}, {0x0a01, 0x0a02}, {0x0a3c, 0x0a3c},
{0x0a41, 0x0a42}, {0x0a47, 0x0a48}, {0x0a4b, 0x0a4d},
{0x0a70, 0x0a71}, {0x0a81, 0x0a82}, {0x0abc, 0x0abc},
{0x0ac1, 0x0ac5}, {0x0ac7, 0x0ac8}, {0x0acd, 0x0acd},
{0x0ae2, 0x0ae3}, {0x0b01, 0x0b01}, {0x0b3c, 0x0b3c},
{0x0b3f, 0x0b3f}, {0x0b41, 0x0b43}, {0x0b4d, 0x0b4d},
{0x0b56, 0x0b56}, {0x0b82, 0x0b82}, {0x0bc0, 0x0bc0},
{0x0bcd, 0x0bcd}, {0x0c3e, 0x0c40}, {0x0c46, 0x0c48},
{0x0c4a, 0x0c4d}, {0x0c55, 0x0c56}, {0x0cbc, 0x0cbc},
{0x0cbf, 0x0cbf}, {0x0cc6, 0x0cc6}, {0x0ccc, 0x0ccd},
{0x0ce2, 0x0ce3}, {0x0d41, 0x0d43}, {0x0d4d, 0x0d4d},
{0x0dca, 0x0dca}, {0x0dd2, 0x0dd4}, {0x0dd6, 0x0dd6},
{0x0e31, 0x0e31}, {0x0e34, 0x0e3a}, {0x0e47, 0x0e4e},
{0x0eb1, 0x0eb1}, {0x0eb4, 0x0eb9}, {0x0ebb, 0x0ebc},
{0x0ec8, 0x0ecd}, {0x0f18, 0x0f19}, {0x0f35, 0x0f35},
{0x0f37, 0x0f37}, {0x0f39, 0x0f39}, {0x0f71, 0x0f7e},
{0x0f80, 0x0f84}, {0x0f86, 0x0f87}, {0x0f90, 0x0f97},
{0x0f99, 0x0fbc}, {0x0fc6, 0x0fc6}, {0x102d, 0x1030},
{0x1032, 0x1032}, {0x1036, 0x1037}, {0x1039, 0x1039},
{0x1058, 0x1059}, {0x1160, 0x11ff}, {0x135f, 0x135f},
{0x1712, 0x1714}, {0x1732, 0x1734}, {0x1752, 0x1753},
{0x1772, 0x1773}, {0x17b4, 0x17b5}, {0x17b7, 0x17bd},
{0x17c6, 0x17c6}, {0x17c9, 0x17d3}, {0x17dd, 0x17dd},
{0x180b, 0x180d}, {0x18a9, 0x18a9}, {0x1920, 0x1922},
{0x1927, 0x1928}, {0x1932, 0x1932}, {0x1939, 0x193b},
{0x1a17, 0x1a18}, {0x1b00, 0x1b03}, {0x1b34, 0x1b34},
{0x1b36, 0x1b3a}, {0x1b3c, 0x1b3c}, {0x1b42, 0x1b42},
{0x1b6b, 0x1b73}, {0x1dc0, 0x1dca}, {0x1dfe, 0x1dff},
{0x200b, 0x200f}, {0x202a, 0x202e}, {0x2060, 0x2063},
{0x206a, 0x206f}, {0x20d0, 0x20ef}, {0x302a, 0x302f},
{0x3099, 0x309a}, {0xa806, 0xa806}, {0xa80b, 0xa80b},
{0xa825, 0xa826}, {0xfb1e, 0xfb1e}, {0xfe00, 0xfe0f},
{0xfe20, 0xfe23}, {0xfeff, 0xfeff}, {0xfff9, 0xfffb},
{0x10a01, 0x10a03}, {0x10a05, 0x10a06}, {0x10a0c, 0x10a0f},
{0x10a38, 0x10a3a}, {0x10a3f, 0x10a3f}, {0x1d167, 0x1d169},
{0x1d173, 0x1d182}, {0x1d185, 0x1d18b}, {0x1d1aa, 0x1d1ad},
{0x1d242, 0x1d244}, {0xe0001, 0xe0001}, {0xe0020, 0xe007f},
{0xe0100, 0xe01ef}
};
if (ucs == 0)
return 0;
if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
return -1;
if (bisearch(ucs, comb, sizeof comb / sizeof comb[0] - 1))
return 0;
return 1 +
(ucs >= 0x1100
&& (ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf && ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
}