summaryrefslogtreecommitdiffstats
path: root/fs/ntfs/unistr.c
blob: 19c42e231b4411ca270d48e2b6b3fac927190554 (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
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
/*
 * unistr.c - NTFS Unicode string handling. Part of the Linux-NTFS project.
 *
 * Copyright (c) 2001-2004 Anton Altaparmakov
 *
 * This program/include file is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file is distributed in the hope that it will be
 * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program (in the main directory of the Linux-NTFS
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include "types.h"
#include "debug.h"
#include "ntfs.h"

/*
 * IMPORTANT
 * =========
 *
 * All these routines assume that the Unicode characters are in little endian
 * encoding inside the strings!!!
 */

/*
 * This is used by the name collation functions to quickly determine what
 * characters are (in)valid.
 */
static const u8 legal_ansi_char_array[0x40] = {
	0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,

	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,

	0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
	0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,

	0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
	0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
};

/**
 * ntfs_are_names_equal - compare two Unicode names for equality
 * @s1:			name to compare to @s2
 * @s1_len:		length in Unicode characters of @s1
 * @s2:			name to compare to @s1
 * @s2_len:		length in Unicode characters of @s2
 * @ic:			ignore case bool
 * @upcase:		upcase table (only if @ic == IGNORE_CASE)
 * @upcase_size:	length in Unicode characters of @upcase (if present)
 *
 * Compare the names @s1 and @s2 and return TRUE (1) if the names are
 * identical, or FALSE (0) if they are not identical. If @ic is IGNORE_CASE,
 * the @upcase table is used to performa a case insensitive comparison.
 */
BOOL ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
		const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic,
		const ntfschar *upcase, const u32 upcase_size)
{
	if (s1_len != s2_len)
		return FALSE;
	if (ic == CASE_SENSITIVE)
		return !ntfs_ucsncmp(s1, s2, s1_len);
	return !ntfs_ucsncasecmp(s1, s2, s1_len, upcase, upcase_size);
}

/**
 * ntfs_collate_names - collate two Unicode names
 * @name1:	first Unicode name to compare
 * @name2:	second Unicode name to compare
 * @err_val:	if @name1 contains an invalid character return this value
 * @ic:		either CASE_SENSITIVE or IGNORE_CASE
 * @upcase:	upcase table (ignored if @ic is CASE_SENSITIVE)
 * @upcase_len:	upcase table size (ignored if @ic is CASE_SENSITIVE)
 *
 * ntfs_collate_names collates two Unicode names and returns:
 *
 *  -1 if the first name collates before the second one,
 *   0 if the names match,
 *   1 if the second name collates before the first one, or
 * @err_val if an invalid character is found in @name1 during the comparison.
 *
 * The following characters are considered invalid: '"', '*', '<', '>' and '?'.
 */
int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
		const ntfschar *name2, const u32 name2_len,
		const int err_val, const IGNORE_CASE_BOOL ic,
		const ntfschar *upcase, const u32 upcase_len)
{
	u32 cnt, min_len;
	u16 c1, c2;

	min_len = name1_len;
	if (name1_len > name2_len)
		min_len = name2_len;
	for (cnt = 0; cnt < min_len; ++cnt) {
		c1 = le16_to_cpu(*name1++);
		c2 = le16_to_cpu(*name2++);
		if (ic) {
			if (c1 < upcase_len)
				c1 = le16_to_cpu(upcase[c1]);
			if (c2 < upcase_len)
				c2 = le16_to_cpu(upcase[c2]);
		}
		if (c1 < 64 && legal_ansi_char_array[c1] & 8)
			return err_val;
		if (c1 < c2)
			return -1;
		if (c1 > c2)
			return 1;
	}
	if (name1_len < name2_len)
		return -1;
	if (name1_len == name2_len)
		return 0;
	/* name1_len > name2_len */
	c1 = le16_to_cpu(*name1);
	if (c1 < 64 && legal_ansi_char_array[c1] & 8)
		return err_val;
	return 1;
}

/**
 * ntfs_ucsncmp - compare two little endian Unicode strings
 * @s1:		first string
 * @s2:		second string
 * @n:		maximum unicode characters to compare
 *
 * Compare the first @n characters of the Unicode strings @s1 and @s2,
 * The strings in little endian format and appropriate le16_to_cpu()
 * conversion is performed on non-little endian machines.
 *
 * The function returns an integer less than, equal to, or greater than zero
 * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
 * to be less than, to match, or be greater than @s2.
 */
int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n)
{
	u16 c1, c2;
	size_t i;

	for (i = 0; i < n; ++i) {
		c1 = le16_to_cpu(s1[i]);
		c2 = le16_to_cpu(s2[i]);
		if (c1 < c2)
			return -1;
		if (c1 > c2)
			return 1;
		if (!c1)
			break;
	}
	return 0;
}

/**
 * ntfs_ucsncasecmp - compare two little endian Unicode strings, ignoring case
 * @s1:			first string
 * @s2:			second string
 * @n:			maximum unicode characters to compare
 * @upcase:		upcase table
 * @upcase_size:	upcase table size in Unicode characters
 *
 * Compare the first @n characters of the Unicode strings @s1 and @s2,
 * ignoring case. The strings in little endian format and appropriate
 * le16_to_cpu() conversion is performed on non-little endian machines.
 *
 * Each character is uppercased using the @upcase table before the comparison.
 *
 * The function returns an integer less than, equal to, or greater than zero
 * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
 * to be less than, to match, or be greater than @s2.
 */
int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
		const ntfschar *upcase, const u32 upcase_size)
{
	size_t i;
	u16 c1, c2;

	for (i = 0; i < n; ++i) {
		if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
			c1 = le16_to_cpu(upcase[c1]);
		if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
			c2 = le16_to_cpu(upcase[c2]);
		if (c1 < c2)
			return -1;
		if (c1 > c2)
			return 1;
		if (!c1)
			break;
	}
	return 0;
}

void ntfs_upcase_name(ntfschar *name, u32 name_len, const ntfschar *upcase,
		const u32 upcase_len)
{
	u32 i;
	u16 u;

	for (i = 0; i < name_len; i++)
		if ((u = le16_to_cpu(name[i])) < upcase_len)
			name[i] = upcase[u];
}

void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
		const ntfschar *upcase, const u32 upcase_len)
{
	ntfs_upcase_name((ntfschar*)&file_name_attr->file_name,
			file_name_attr->file_name_length, upcase, upcase_len);
}

int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
		FILE_NAME_ATTR *file_name_attr2,
		const int err_val, const IGNORE_CASE_BOOL ic,
		const ntfschar *upcase, const u32 upcase_len)
{
	return ntfs_collate_names((ntfschar*)&file_name_attr1->file_name,
			file_name_attr1->file_name_length,
			(ntfschar*)&file_name_attr2->file_name,
			file_name_attr2->file_name_length,
			err_val, ic, upcase, upcase_len);
}

/**
 * ntfs_nlstoucs - convert NLS string to little endian Unicode string
 * @vol:	ntfs volume which we are working with
 * @ins:	input NLS string buffer
 * @ins_len:	length of input string in bytes
 * @outs:	on return contains the allocated output Unicode string buffer
 *
 * Convert the input string @ins, which is in whatever format the loaded NLS
 * map dictates, into a little endian, 2-byte Unicode string.
 *
 * This function allocates the string and the caller is responsible for
 * calling kmem_cache_free(ntfs_name_cache, @outs); when finished with it.
 *
 * On success the function returns the number of Unicode characters written to
 * the output string *@outs (>= 0), not counting the terminating Unicode NULL
 * character. *@outs is set to the allocated output string buffer.
 *
 * On error, a negative number corresponding to the error code is returned. In
 * that case the output string is not allocated. Both *@outs and *@outs_len
 * are then undefined.
 *
 * This might look a bit odd due to fast path optimization...
 */
int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
		const int ins_len, ntfschar **outs)
{
	struct nls_table *nls = vol->nls_map;
	ntfschar *ucs;
	wchar_t wc;
	int i, o, wc_len;

	/* We don't trust outside sources. */
	if (ins) {
		ucs = kmem_cache_alloc(ntfs_name_cache, SLAB_NOFS);
		if (ucs) {
			for (i = o = 0; i < ins_len; i += wc_len) {
				wc_len = nls->char2uni(ins + i, ins_len - i,
						&wc);
				if (wc_len >= 0) {
					if (wc) {
						ucs[o++] = cpu_to_le16(wc);
						continue;
					} /* else (!wc) */
					break;
				} /* else (wc_len < 0) */
				goto conversion_err;
			}
			ucs[o] = 0;
			*outs = ucs;
			return o;
		} /* else (!ucs) */
		ntfs_error(vol->sb, "Failed to allocate name from "
				"ntfs_name_cache!");
		return -ENOMEM;
	} /* else (!ins) */
	ntfs_error(NULL, "Received NULL pointer.");
	return -EINVAL;
conversion_err:
	ntfs_error(vol->sb, "Name using character set %s contains characters "
			"that cannot be converted to Unicode.", nls->charset);
	kmem_cache_free(ntfs_name_cache, ucs);
	return -EILSEQ;
}

/**
 * ntfs_ucstonls - convert little endian Unicode string to NLS string
 * @vol:	ntfs volume which we are working with
 * @ins:	input Unicode string buffer
 * @ins_len:	length of input string in Unicode characters
 * @outs:	on return contains the (allocated) output NLS string buffer
 * @outs_len:	length of output string buffer in bytes
 *
 * Convert the input little endian, 2-byte Unicode string @ins, of length
 * @ins_len into the string format dictated by the loaded NLS.
 *
 * If *@outs is NULL, this function allocates the string and the caller is
 * responsible for calling kfree(*@outs); when finished with it. In this case
 * @outs_len is ignored and can be 0.
 *
 * On success the function returns the number of bytes written to the output
 * string *@outs (>= 0), not counting the terminating NULL byte. If the output
 * string buffer was allocated, *@outs is set to it.
 *
 * On error, a negative number corresponding to the error code is returned. In
 * that case the output string is not allocated. The contents of *@outs are
 * then undefined.
 *
 * This might look a bit odd due to fast path optimization...
 */
int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
		const int ins_len, unsigned char **outs, int outs_len)
{
	struct nls_table *nls = vol->nls_map;
	unsigned char *ns;
	int i, o, ns_len, wc;

	/* We don't trust outside sources. */
	if (ins) {
		ns = *outs;
		ns_len = outs_len;
		if (ns && !ns_len) {
			wc = -ENAMETOOLONG;
			goto conversion_err;
		}
		if (!ns) {
			ns_len = ins_len * NLS_MAX_CHARSET_SIZE;
			ns = (unsigned char*)kmalloc(ns_len + 1, GFP_NOFS);
			if (!ns)
				goto mem_err_out;
		}
		for (i = o = 0; i < ins_len; i++) {
retry:			wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
					ns_len - o);
			if (wc > 0) {
				o += wc;
				continue;
			} else if (!wc)
				break;
			else if (wc == -ENAMETOOLONG && ns != *outs) {
				unsigned char *tc;
				/* Grow in multiples of 64 bytes. */
				tc = (unsigned char*)kmalloc((ns_len + 64) &
						~63, GFP_NOFS);
				if (tc) {
					memcpy(tc, ns, ns_len);
					ns_len = ((ns_len + 64) & ~63) - 1;
					kfree(ns);
					ns = tc;
					goto retry;
				} /* No memory so goto conversion_error; */
			} /* wc < 0, real error. */
			goto conversion_err;
		}
		ns[o] = 0;
		*outs = ns;
		return o;
	} /* else (!ins) */
	ntfs_error(vol->sb, "Received NULL pointer.");
	return -EINVAL;
conversion_err:
	ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
			"converted to character set %s.", nls->charset);
	if (ns != *outs)
		kfree(ns);
	if (wc != -ENAMETOOLONG)
		wc = -EILSEQ;
	return wc;
mem_err_out:
	ntfs_error(vol->sb, "Failed to allocate name!");
	return -ENOMEM;
}