blob: 746fde4ad8f671c09fa722c9b91f71aa7fec3e9b (
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
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
|
/*
See license.txt in the root of this project.
*/
# include "luametatex.h"
/*tex
The 5- and 6-byte UTF-8 sequences generate integers that are outside of the valid UCS range,
and therefore unsupported. We recover from an error with |0xFFFD|.
*/
// unsigned xaux_str2uni(const unsigned char *k)
// {
// const unsigned char *text = k;
// int ch = *text++;
// if (ch < 0x80) {
// return (unsigned) ch;
// } else if (ch <= 0xbf) {
// return 0xFFFD;
// } else if (ch <= 0xdf) {
// if (text[0] >= 0x80 && text[0] < 0xc0) {
// return (unsigned) (((ch & 0x1f) << 6) | (text[0] & 0x3f));
// }
// } else if (ch <= 0xef) {
// if (text[0] >= 0x80 && text[0] < 0xc0 && text[1] >= 0x80 && text[1] < 0xc0) {
// return (unsigned) (((ch & 0xf) << 12) | ((text[0] & 0x3f) << 6) | (text[1] & 0x3f));
// }
// } else if (ch <= 0xf7) {
// if (text[0] < 0x80 || text[1] < 0x80 || text[2] < 0x80 ||
// text[0] >= 0xc0 || text[1] >= 0xc0 || text[2] >= 0xc0) {
// return 0xFFFD;
// } else {
// int w1 = (((ch & 0x7) << 2) | ((text[0] & 0x30) >> 4)) - 1;
// int w2 = ((text[1] & 0xf) << 6) | (text[2] & 0x3f);
// w1 = (w1 << 6) | ((text[0] & 0xf) << 2) | ((text[1] & 0x30) >> 4);
// return (unsigned) (w1 * 0x400 + w2 + 0x10000);
// }
// }
// return 0xFFFD;
// }
unsigned aux_str2uni(const unsigned char *text)
{
if (text[0] < 0x80) {
return (unsigned) text[0];
} else if (text[0] <= 0xbf) {
return 0xFFFD;
} else if (text[0] <= 0xdf) {
if (text[1] >= 0x80 && text[1] < 0xc0) {
return (unsigned) (((text[0] & 0x1f) << 6) | (text[1] & 0x3f));
}
} else if (text[0] <= 0xef) {
if (text[1] >= 0x80 && text[1] < 0xc0 && text[2] >= 0x80 && text[2] < 0xc0) {
return (unsigned) (((text[0] & 0xf) << 12) | ((text[1] & 0x3f) << 6) | (text[2] & 0x3f));
}
} else if (text[0] <= 0xf7) {
if (text[1] < 0x80 || text[2] < 0x80 || text[3] < 0x80 ||
text[1] >= 0xc0 || text[2] >= 0xc0 || text[3] >= 0xc0) {
return 0xFFFD;
} else {
int w1 = (((text[0] & 0x7) << 2) | ((text[1] & 0x30) >> 4)) - 1;
int w2 = ((text[2] & 0xf) << 6) | (text[3] & 0x3f);
w1 = (w1 << 6) | ((text[1] & 0xf) << 2) | ((text[2] & 0x30) >> 4);
return (unsigned) (w1 * 0x400 + w2 + 0x10000);
}
}
return 0xFFFD;
}
unsigned aux_str2uni_len(const unsigned char *text, int *len)
{
if (text[0] < 0x80) {
*len = 1;
return (unsigned) text[0];
} else if (text[0] <= 0xbf) {
*len = 1;
return 0xFFFD;
} else if (text[0] <= 0xdf) {
if (text[1] >= 0x80 && text[1] < 0xc0) {
*len = 2;
return (unsigned) (((text[0] & 0x1f) << 6) | (text[1] & 0x3f));
}
} else if (text[0] <= 0xef) {
if (text[1] >= 0x80 && text[1] < 0xc0 && text[2] >= 0x80 && text[2] < 0xc0) {
*len = 3;
return (unsigned) (((text[0] & 0xf) << 12) | ((text[1] & 0x3f) << 6) | (text[2] & 0x3f));
}
} else if (text[0] <= 0xf7) {
if (text[1] < 0x80 || text[2] < 0x80 || text[3] < 0x80 ||
text[1] >= 0xc0 || text[2] >= 0xc0 || text[3] >= 0xc0) {
*len = 4;
return 0xFFFD;
} else {
*len = 4;
int w1 = (((text[0] & 0x7) << 2) | ((text[1] & 0x30) >> 4)) - 1;
int w2 = ((text[2] & 0xf) << 6) | (text[3] & 0x3f);
w1 = (w1 << 6) | ((text[1] & 0xf) << 2) | ((text[2] & 0x30) >> 4);
return (unsigned) (w1 * 0x400 + w2 + 0x10000);
}
}
*len = 1;
return 0xFFFD;
}
unsigned char *aux_uni2str(unsigned unic)
{
unsigned char *buf = lmt_memory_malloc(5);
if (buf) {
if (unic < 0x80) {
buf[0] = (unsigned char) unic;
buf[1] = '\0';
} else if (unic < 0x800) {
buf[0] = (unsigned char) (0xc0 | (unic >> 6));
buf[1] = (unsigned char) (0x80 | (unic & 0x3f));
buf[2] = '\0';
} else if (unic < 0x10000) {
buf[0] = (unsigned char) (0xe0 | (unic >> 12));
buf[1] = (unsigned char) (0x80 | ((unic >> 6) & 0x3f));
buf[2] = (unsigned char) (0x80 | (unic & 0x3f));
buf[3] = '\0';
} else if (unic < 0x110000) {
int u;
unic -= 0x10000;
u = (int) (((unic & 0xf0000) >> 16) + 1);
buf[0] = (unsigned char) (0xf0 | (u >> 2));
buf[1] = (unsigned char) (0x80 | ((u & 3) << 4) | ((unic & 0x0f000) >> 12));
buf[2] = (unsigned char) (0x80 | ((unic & 0x00fc0) >> 6));
buf[3] = (unsigned char) (0x80 | (unic & 0x0003f));
buf[4] = '\0';
}
}
return buf;
}
/*tex
Function |buffer_to_unichar| converts a sequence of bytes in the |buffer| into a \UNICODE\
character value. It does not check for overflow of the |buffer|, but it is careful to check
the validity of the \UTF-8 encoding. For historical reasons all these small helpers look a bit
different but that has a certain charm so we keep it.
*/
char *aux_uni2string(char *utf8_text, unsigned unic)
{
/*tex Increment and deposit character: */
if (unic <= 0x7f) {
*utf8_text++ = (char) unic;
} else if (unic <= 0x7ff) {
*utf8_text++ = (char) (0xc0 | (unic >> 6));
*utf8_text++ = (char) (0x80 | (unic & 0x3f));
} else if (unic <= 0xffff) {
*utf8_text++ = (char) (0xe0 | (unic >> 12));
*utf8_text++ = (char) (0x80 | ((unic >> 6) & 0x3f));
*utf8_text++ = (char) (0x80 | (unic & 0x3f));
} else if (unic < 0x110000) {
unsigned u;
unic -= 0x10000;
u = ((unic & 0xf0000) >> 16) + 1;
*utf8_text++ = (char) (0xf0 | (u >> 2));
*utf8_text++ = (char) (0x80 | ((u & 3) << 4) | ((unic & 0x0f000) >> 12));
*utf8_text++ = (char) (0x80 | ((unic & 0x00fc0) >> 6));
*utf8_text++ = (char) (0x80 | (unic & 0x0003f));
}
return (utf8_text);
}
unsigned aux_splitutf2uni(unsigned int *ubuf, const char *utf8buf)
{
int len = (int) strlen(utf8buf);
unsigned int *upt = ubuf;
unsigned int *uend = ubuf + len;
const unsigned char *pt = (const unsigned char *) utf8buf;
const unsigned char *end = pt + len;
while (pt < end && *pt != '\0' && upt < uend) {
if (*pt <= 127) {
*upt = *pt++;
} else if (*pt <= 0xdf) {
*upt = (unsigned int) (((*pt & 0x1f) << 6) | (pt[1] & 0x3f));
pt += 2;
} else if (*pt <= 0xef) {
*upt = (unsigned int) (((*pt & 0xf) << 12) | ((pt[1] & 0x3f) << 6) | (pt[2] & 0x3f));
pt += 3;
} else {
int w1 = (((*pt & 0x7) << 2) | ((pt[1] & 0x30) >> 4)) - 1;
int w2 = ((pt[2] & 0xf) << 6) | (pt[3] & 0x3f);
w1 = (w1 << 6) | ((pt[1] & 0xf) << 2) | ((pt[2] & 0x30) >> 4);
*upt = (unsigned int) (w1 * 0x400 + w2 + 0x10000);
pt += 4;
}
++upt;
}
*upt = '\0';
return (unsigned int) (upt - ubuf);
}
size_t aux_utf8len(const char *text, size_t size)
{
size_t ind = 0;
size_t num = 0;
while (ind < size) {
unsigned char i = (unsigned char) *(text + ind);
if (i < 0x80) {
ind += 1;
} else if (i >= 0xF0) {
ind += 4;
} else if (i >= 0xE0) {
ind += 3;
} else if (i >= 0xC0) {
ind += 2;
} else {
ind += 1;
}
num += 1;
}
return num;
}
|
