aboutsummaryrefslogtreecommitdiff
path: root/fs/cifs/cifs_unicode.c
blob: 614512573c67dc1d55de9d2cb6e4c5e65cd17743 (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
/*
 *   fs/cifs/cifs_unicode.c
 *
 *   Copyright (c) International Business Machines  Corp., 2000,2005
 *   Modified by Steve French (sfrench@us.ibm.com)
 *
 *   This program 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 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;  if not, write to the Free Software
 *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */
#include <linux/fs.h>
#include "cifs_unicode.h"
#include "cifs_uniupr.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifs_debug.h"

/*
 * cifs_ucs2_bytes - how long will a string be after conversion?
 * @ucs - pointer to input string
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - destination codepage
 *
 * Walk a ucs2le string and return the number of bytes that the string will
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 */
int
cifs_ucs2_bytes(const __le16 *from, int maxbytes,
		const struct nls_table *codepage)
{
	int i;
	int charlen, outlen = 0;
	int maxwords = maxbytes / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];

	for (i = 0; from[i] && i < maxwords; i++) {
		charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp,
					     NLS_MAX_CHARSET_SIZE);
		if (charlen > 0)
			outlen += charlen;
		else
			outlen++;
	}

	return outlen;
}

/*
 * cifs_mapchar - convert a little-endian char to proper char in codepage
 * @target - where converted character should be copied
 * @src_char - 2 byte little-endian source character
 * @cp - codepage to which character should be converted
 * @mapchar - should character be mapped according to mapchars mount option?
 *
 * This function handles the conversion of a single character. It is the
 * responsibility of the caller to ensure that the target buffer is large
 * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
 */
static int
cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp,
	     bool mapchar)
{
	int len = 1;

	if (!mapchar)
		goto cp_convert;

	/*
	 * BB: Cannot handle remapping UNI_SLASH until all the calls to
	 *     build_path_from_dentry are modified, as they use slash as
	 *     separator.
	 */
	switch (le16_to_cpu(src_char)) {
	case UNI_COLON:
		*target = ':';
		break;
	case UNI_ASTERIK:
		*target = '*';
		break;
	case UNI_QUESTION:
		*target = '?';
		break;
	case UNI_PIPE:
		*target = '|';
		break;
	case UNI_GRTRTHAN:
		*target = '>';
		break;
	case UNI_LESSTHAN:
		*target = '<';
		break;
	default:
		goto cp_convert;
	}

out:
	return len;

cp_convert:
	len = cp->uni2char(le16_to_cpu(src_char), target,
			   NLS_MAX_CHARSET_SIZE);
	if (len <= 0) {
		*target = '?';
		len = 1;
	}
	goto out;
}

/*
 * cifs_from_ucs2 - convert utf16le string to local charset
 * @to - destination buffer
 * @from - source buffer
 * @tolen - destination buffer size (in bytes)
 * @fromlen - source buffer size (in bytes)
 * @codepage - codepage to which characters should be converted
 * @mapchar - should characters be remapped according to the mapchars option?
 *
 * Convert a little-endian ucs2le string (as sent by the server) to a string
 * in the provided codepage. The tolen and fromlen parameters are to ensure
 * that the code doesn't walk off of the end of the buffer (which is always
 * a danger if the alignment of the source buffer is off). The destination
 * string is always properly null terminated and fits in the destination
 * buffer. Returns the length of the destination string in bytes (including
 * null terminator).
 *
 * Note that some windows versions actually send multiword UTF-16 characters
 * instead of straight UCS-2. The linux nls routines however aren't able to
 * deal with those characters properly. In the event that we get some of
 * those characters, they won't be translated properly.
 */
int
cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
		 const struct nls_table *codepage, bool mapchar)
{
	int i, charlen, safelen;
	int outlen = 0;
	int nullsize = nls_nullsize(codepage);
	int fromwords = fromlen / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];

	/*
	 * because the chars can be of varying widths, we need to take care
	 * not to overflow the destination buffer when we get close to the
	 * end of it. Until we get to this offset, we don't need to check
	 * for overflow however.
	 */
	safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);

	for (i = 0; i < fromwords && from[i]; i++) {
		/*
		 * check to see if converting this character might make the
		 * conversion bleed into the null terminator
		 */
		if (outlen >= safelen) {
			charlen = cifs_mapchar(tmp, from[i], codepage, mapchar);
			if ((outlen + charlen) > (tolen - nullsize))
				break;
		}

		/* put converted char into 'to' buffer */
		charlen = cifs_mapchar(&to[outlen], from[i], codepage, mapchar);
		outlen += charlen;
	}

	/* properly null-terminate string */
	for (i = 0; i < nullsize; i++)
		to[outlen++] = 0;

	return outlen;
}

/*
 * NAME:	cifs_strfromUCS()
 *
 * FUNCTION:	Convert little-endian unicode string to character string
 *
 */
int
cifs_strfromUCS_le(char *to, const __le16 *from,
		   int len, const struct nls_table *codepage)
{
	int i;
	int outlen = 0;

	for (i = 0; (i < len) && from[i]; i++) {
		int charlen;
		/* 2.4.0 kernel or greater */
		charlen =
		    codepage->uni2char(le16_to_cpu(from[i]), &to[outlen],
				       NLS_MAX_CHARSET_SIZE);
		if (charlen > 0) {
			outlen += charlen;
		} else {
			to[outlen++] = '?';
		}
	}
	to[outlen] = 0;
	return outlen;
}

/*
 * NAME:	cifs_strtoUCS()
 *
 * FUNCTION:	Convert character string to unicode string
 *
 */
int
cifs_strtoUCS(__le16 *to, const char *from, int len,
	      const struct nls_table *codepage)
{
	int charlen;
	int i;
	wchar_t *wchar_to = (wchar_t *)to; /* needed to quiet sparse */

	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {

		/* works for 2.4.0 kernel or later */
		charlen = codepage->char2uni(from, len, &wchar_to[i]);
		if (charlen < 1) {
			cERROR(1,
			       ("strtoUCS: char2uni of %d returned %d",
				(int)*from, charlen));
			/* A question mark */
			to[i] = cpu_to_le16(0x003f);
			charlen = 1;
		} else
			to[i] = cpu_to_le16(wchar_to[i]);

	}

	to[i] = 0;
	return i;
}