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
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
|
/*
* unicode.c
*
* PURPOSE
* Routines for converting between UTF-8 and OSTA Compressed Unicode.
* Also handles filename mangling
*
* DESCRIPTION
* OSTA Compressed Unicode is explained in the OSTA UDF specification.
* http://www.osta.org/
* UTF-8 is explained in the IETF RFC XXXX.
* ftp://ftp.internic.net/rfc/rfcxxxx.txt
*
* COPYRIGHT
* This file is distributed under the terms of the GNU General Public
* License (GPL). Copies of the GPL can be obtained from:
* ftp://prep.ai.mit.edu/pub/gnu/GPL
* Each contributing author retains all rights to their own work.
*/
#include "udfdecl.h"
#include <linux/kernel.h>
#include <linux/string.h> /* for memset */
#include <linux/nls.h>
#include <linux/crc-itu-t.h>
#include <linux/slab.h>
#include "udf_sb.h"
#define PLANE_SIZE 0x10000
#define UNICODE_MAX 0x10ffff
#define SURROGATE_MASK 0xfffff800
#define SURROGATE_PAIR 0x0000d800
#define SURROGATE_LOW 0x00000400
#define SURROGATE_CHAR_BITS 10
#define SURROGATE_CHAR_MASK ((1 << SURROGATE_CHAR_BITS) - 1)
#define ILLEGAL_CHAR_MARK '_'
#define EXT_MARK '.'
#define CRC_MARK '#'
#define EXT_SIZE 5
/* Number of chars we need to store generated CRC to make filename unique */
#define CRC_LEN 5
static unicode_t get_utf16_char(const uint8_t *str_i, int str_i_max_len,
int str_i_idx, int u_ch, unicode_t *ret)
{
unicode_t c;
int start_idx = str_i_idx;
/* Expand OSTA compressed Unicode to Unicode */
c = str_i[str_i_idx++];
if (u_ch > 1)
c = (c << 8) | str_i[str_i_idx++];
if ((c & SURROGATE_MASK) == SURROGATE_PAIR) {
unicode_t next;
/* Trailing surrogate char */
if (str_i_idx >= str_i_max_len) {
c = UNICODE_MAX + 1;
goto out;
}
/* Low surrogate must follow the high one... */
if (c & SURROGATE_LOW) {
c = UNICODE_MAX + 1;
goto out;
}
WARN_ON_ONCE(u_ch != 2);
next = str_i[str_i_idx++] << 8;
next |= str_i[str_i_idx++];
if ((next & SURROGATE_MASK) != SURROGATE_PAIR ||
!(next & SURROGATE_LOW)) {
c = UNICODE_MAX + 1;
goto out;
}
c = PLANE_SIZE +
((c & SURROGATE_CHAR_MASK) << SURROGATE_CHAR_BITS) +
(next & SURROGATE_CHAR_MASK);
}
out:
*ret = c;
return str_i_idx - start_idx;
}
static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
int *str_o_idx,
const uint8_t *str_i, int str_i_max_len,
int *str_i_idx,
int u_ch, int *needsCRC,
int (*conv_f)(wchar_t, unsigned char *, int),
int translate)
{
unicode_t c;
int illChar = 0;
int len, gotch = 0;
while (!gotch && *str_i_idx < str_i_max_len) {
if (*str_o_idx >= str_o_max_len) {
*needsCRC = 1;
return gotch;
}
len = get_utf16_char(str_i, str_i_max_len, *str_i_idx, u_ch,
&c);
/* These chars cannot be converted. Replace them. */
if (c == 0 || c > UNICODE_MAX || (conv_f && c > MAX_WCHAR_T) ||
(translate && c == '/')) {
illChar = 1;
if (!translate)
gotch = 1;
} else if (illChar)
break;
else
gotch = 1;
*str_i_idx += len;
}
if (illChar) {
*needsCRC = 1;
c = ILLEGAL_CHAR_MARK;
gotch = 1;
}
if (gotch) {
if (conv_f) {
len = conv_f(c, &str_o[*str_o_idx],
str_o_max_len - *str_o_idx);
} else {
len = utf32_to_utf8(c, &str_o[*str_o_idx],
str_o_max_len - *str_o_idx);
if (len < 0)
len = -ENAMETOOLONG;
}
/* Valid character? */
if (len >= 0)
*str_o_idx += len;
else if (len == -ENAMETOOLONG) {
*needsCRC = 1;
gotch = 0;
} else {
str_o[(*str_o_idx)++] = ILLEGAL_CHAR_MARK;
*needsCRC = 1;
}
}
return gotch;
}
static int udf_name_from_CS0(struct super_block *sb,
uint8_t *str_o, int str_max_len,
const uint8_t *ocu, int ocu_len,
int translate)
{
uint32_t c;
uint8_t cmp_id;
int idx, len;
int u_ch;
int needsCRC = 0;
int ext_i_len, ext_max_len;
int str_o_len = 0; /* Length of resulting output */
int ext_o_len = 0; /* Extension output length */
int ext_crc_len = 0; /* Extension output length if used with CRC */
int i_ext = -1; /* Extension position in input buffer */
int o_crc = 0; /* Rightmost possible output pos for CRC+ext */
unsigned short valueCRC;
uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
uint8_t crc[CRC_LEN];
int (*conv_f)(wchar_t, unsigned char *, int);
if (str_max_len <= 0)
return 0;
if (ocu_len == 0) {
memset(str_o, 0, str_max_len);
return 0;
}
if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
conv_f = UDF_SB(sb)->s_nls_map->uni2char;
else
conv_f = NULL;
cmp_id = ocu[0];
if (cmp_id != 8 && cmp_id != 16) {
memset(str_o, 0, str_max_len);
pr_err("unknown compression code (%u)\n", cmp_id);
return -EINVAL;
}
u_ch = cmp_id >> 3;
ocu++;
ocu_len--;
if (ocu_len % u_ch) {
pr_err("incorrect filename length (%d)\n", ocu_len + 1);
return -EINVAL;
}
if (translate) {
/* Look for extension */
for (idx = ocu_len - u_ch, ext_i_len = 0;
(idx >= 0) && (ext_i_len < EXT_SIZE);
idx -= u_ch, ext_i_len++) {
c = ocu[idx];
if (u_ch > 1)
c = (c << 8) | ocu[idx + 1];
if (c == EXT_MARK) {
if (ext_i_len)
i_ext = idx;
break;
}
}
if (i_ext >= 0) {
/* Convert extension */
ext_max_len = min_t(int, sizeof(ext), str_max_len);
ext[ext_o_len++] = EXT_MARK;
idx = i_ext + u_ch;
while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
ocu, ocu_len, &idx,
u_ch, &needsCRC,
conv_f, translate)) {
if ((ext_o_len + CRC_LEN) < str_max_len)
ext_crc_len = ext_o_len;
}
}
}
idx = 0;
while (1) {
if (translate && (idx == i_ext)) {
if (str_o_len > (str_max_len - ext_o_len))
needsCRC = 1;
break;
}
if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
ocu, ocu_len, &idx,
u_ch, &needsCRC, conv_f, translate))
break;
if (translate &&
(str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
o_crc = str_o_len;
}
if (translate) {
if (str_o_len <= 2 && str_o[0]
|