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
|
/* $Id$ */
/*
* Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
* Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
#include "config.h"
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
#include "mandoc.h"
#include "libmandoc.h"
int
preconv_encode(struct buf *ib, size_t *ii, struct buf *ob, size_t *oi,
int *filenc)
{
size_t i;
const long one = 1L;
int state, be;
unsigned int accum;
unsigned char cu;
if ( ! (*filenc & MPARSE_UTF8))
goto latin;
state = 0;
accum = 0U;
be = 0;
/* Quick test for big-endian value. */
if ( ! (*((const char *)(&one))))
be = 1;
for (i = *ii; i < ib->sz; i++) {
cu = ib->buf[i];
if (state) {
if ( ! (cu & 128) || (cu & 64)) {
/* Bad sequence header. */
break;
}
/* Accept only legitimate bit patterns. */
if (cu > 191 || cu < 128) {
/* Bad in-sequence bits. */
break;
}
accum |= (cu & 63) << --state * 6;
if (state)
continue;
/*
* Accum is held in little-endian order as
* stipulated by the UTF-8 sequence coding. We
* need to convert to a native big-endian if our
* architecture requires it.
*/
if (be)
accum = (accum >> 24) |
((accum << 8) & 0x00FF0000) |
((accum >> 8) & 0x0000FF00) |
(accum << 24);
if (accum < 0x80)
ob->buf[(*oi)++] = accum;
else
*oi += snprintf(ob->buf + *oi,
11, "\\[u%.4X]", accum);
*ii = i + 1;
*filenc &= ~MPARSE_LATIN1;
return(1);
} else {
/*
* Entering a UTF-8 state: if we encounter a
* UTF-8 bitmask, calculate the expected UTF-8
* state from it.
*/
for (state = 0; state < 7; state++)
if ( ! (cu & (1 << (7 - state))))
break;
/* Accept only legitimate bit patterns. */
switch (state--) {
case (4):
if (cu <= 244 && cu >= 240) {
accum = (cu & 7) << 18;
continue;
}
/* Bad 4-sequence start bits. */
break;
case (3):
if (cu <= 239 && cu >= 224) {
accum = (cu & 15) << 12;
continue;
}
/* Bad 3-sequence start bits. */
break;
case (2):
if (cu <= 223 && cu >= 194) {
accum = (cu & 31) << 6;
continue;
}
/* Bad 2-sequence start bits. */
break;
default:
/* Bad sequence bit mask. */
break;
}
break;
}
}
/* FALLTHROUGH: Invalid or incomplete UTF-8 sequence. */
latin:
if ( ! (*filenc & MPARSE_LATIN1))
return(0);
*oi += snprintf(ob->buf + *oi, 11,
"\\[u%.4X]", (unsigned char)ib->buf[(*ii)++]);
*filenc &= ~MPARSE_UTF8;
return(1);
}
int
preconv_cue(const struct buf *b, size_t offset)
{
const char *ln, *eoln, *eoph;
size_t sz, phsz;
ln = b->buf + offset;
sz = b->sz - offset;
/* Look for the end-of-line. */
if (NULL == (eoln = memchr(ln, '\n', sz)))
eoln = ln + sz;
/* Check if we have the correct header/trailer. */
if ((sz = (size_t)(eoln - ln)) < 10 ||
memcmp(ln, ".\\\" -*-", 7) || memcmp(eoln - 3, "-*-", 3))
return(MPARSE_UTF8 | MPARSE_LATIN1);
/* Move after the header and adjust for the trailer. */
ln += 7;
sz -= 10;
while (sz > 0) {
while (sz > 0 && ' ' == *ln) {
ln++;
sz--;
}
if (0 == sz)
break;
/* Find the end-of-phrase marker (or eoln). */
if (NULL == (eoph = memchr(ln, ';', sz)))
eoph = eoln - 3;
else
eoph++;
/* Only account for the "coding" phrase. */
if ((phsz = eoph - ln) < 7 ||
strncasecmp(ln, "coding:", 7)) {
sz -= phsz;
ln += phsz;
continue;
}
sz -= 7;
ln += 7;
while (sz > 0 && ' ' == *ln) {
ln++;
sz--;
}
if (0 == sz)
return(0);
/* Check us against known encodings. */
if (phsz > 4 && !strncasecmp(ln, "utf-8", 5))
return(MPARSE_UTF8);
if (phsz > 10 && !strncasecmp(ln, "iso-latin-1", 11))
return(MPARSE_LATIN1);
return(0);
}
return(MPARSE_UTF8 | MPARSE_LATIN1);
}
|
