Blame view
fs/cifs/cifs_unicode.c
8.77 KB
1da177e4c
|
1 2 3 |
/* * fs/cifs/cifs_unicode.c * |
d185cda77
|
4 |
* Copyright (c) International Business Machines Corp., 2000,2009 |
1da177e4c
|
5 6 7 8 |
* 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 |
221601c3d
|
9 |
* the Free Software Foundation; either version 2 of the License, or |
1da177e4c
|
10 |
* (at your option) any later version. |
221601c3d
|
11 |
* |
1da177e4c
|
12 13 14 15 16 17 |
* 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 |
221601c3d
|
18 |
* along with this program; if not, write to the Free Software |
1da177e4c
|
19 20 21 |
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> |
5a0e3ad6a
|
22 |
#include <linux/slab.h> |
1da177e4c
|
23 24 25 |
#include "cifs_unicode.h" #include "cifs_uniupr.h" #include "cifspdu.h" |
3979877e5
|
26 |
#include "cifsglob.h" |
1da177e4c
|
27 28 29 |
#include "cifs_debug.h" /* |
69f801fca
|
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
* 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]; |
ba2dbf30d
|
47 |
__u16 ftmp; |
69f801fca
|
48 |
|
ba2dbf30d
|
49 50 51 52 53 54 |
for (i = 0; i < maxwords; i++) { ftmp = get_unaligned_le16(&from[i]); if (ftmp == 0) break; charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE); |
69f801fca
|
55 56 57 58 59 60 61 62 63 64 |
if (charlen > 0) outlen += charlen; else outlen++; } return outlen; } /* |
ba2dbf30d
|
65 |
* cifs_mapchar - convert a host-endian char to proper char in codepage |
7fabf0c94
|
66 |
* @target - where converted character should be copied |
ba2dbf30d
|
67 |
* @src_char - 2 byte host-endian source character |
7fabf0c94
|
68 69 70 71 72 73 74 75 |
* @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 |
ba2dbf30d
|
76 |
cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, |
7fabf0c94
|
77 78 79 80 81 82 83 84 85 86 87 88 |
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. */ |
ba2dbf30d
|
89 |
switch (src_char) { |
7fabf0c94
|
90 91 92 |
case UNI_COLON: *target = ':'; break; |
581ade4d1
|
93 |
case UNI_ASTERISK: |
7fabf0c94
|
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
*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: |
ba2dbf30d
|
116 |
len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE); |
7fabf0c94
|
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 |
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]; |
ba2dbf30d
|
155 |
__u16 ftmp; |
7fabf0c94
|
156 157 158 159 160 161 162 163 |
/* * 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); |
ba2dbf30d
|
164 165 166 167 |
for (i = 0; i < fromwords; i++) { ftmp = get_unaligned_le16(&from[i]); if (ftmp == 0) break; |
7fabf0c94
|
168 169 170 171 172 |
/* * check to see if converting this character might make the * conversion bleed into the null terminator */ if (outlen >= safelen) { |
ba2dbf30d
|
173 |
charlen = cifs_mapchar(tmp, ftmp, codepage, mapchar); |
7fabf0c94
|
174 175 176 177 178 |
if ((outlen + charlen) > (tolen - nullsize)) break; } /* put converted char into 'to' buffer */ |
ba2dbf30d
|
179 |
charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar); |
7fabf0c94
|
180 181 182 183 184 185 186 187 188 189 190 |
outlen += charlen; } /* properly null-terminate string */ for (i = 0; i < nullsize; i++) to[outlen++] = 0; return outlen; } /* |
1da177e4c
|
191 192 193 194 195 196 |
* NAME: cifs_strtoUCS() * * FUNCTION: Convert character string to unicode string * */ int |
ad7a2926b
|
197 |
cifs_strtoUCS(__le16 *to, const char *from, int len, |
1da177e4c
|
198 199 200 201 |
const struct nls_table *codepage) { int charlen; int i; |
ba2dbf30d
|
202 |
wchar_t wchar_to; /* needed to quiet sparse */ |
1da177e4c
|
203 204 |
for (i = 0; len && *from; i++, from += charlen, len -= charlen) { |
ba2dbf30d
|
205 |
charlen = codepage->char2uni(from, len, &wchar_to); |
1da177e4c
|
206 |
if (charlen < 1) { |
ba2dbf30d
|
207 208 |
cERROR(1, "strtoUCS: char2uni of 0x%x returned %d", *from, charlen); |
69114089b
|
209 |
/* A question mark */ |
ba2dbf30d
|
210 |
wchar_to = 0x003f; |
1da177e4c
|
211 |
charlen = 1; |
ba2dbf30d
|
212 213 |
} put_unaligned_le16(wchar_to, &to[i]); |
1da177e4c
|
214 |
} |
ba2dbf30d
|
215 |
put_unaligned_le16(0, &to[i]); |
1da177e4c
|
216 217 |
return i; } |
066ce6899
|
218 |
/* |
d185cda77
|
219 |
* cifs_strndup_from_ucs - copy a string from wire format to the local codepage |
066ce6899
|
220 221 222 223 224 225 226 227 228 229 |
* @src - source string * @maxlen - don't walk past this many bytes in the source string * @is_unicode - is this a unicode string? * @codepage - destination codepage * * Take a string given by the server, convert it to the local codepage and * put it in a new buffer. Returns a pointer to the new string or NULL on * error. */ char * |
d185cda77
|
230 |
cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode, |
066ce6899
|
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 |
const struct nls_table *codepage) { int len; char *dst; if (is_unicode) { len = cifs_ucs2_bytes((__le16 *) src, maxlen, codepage); len += nls_nullsize(codepage); dst = kmalloc(len, GFP_KERNEL); if (!dst) return NULL; cifs_from_ucs2(dst, (__le16 *) src, len, maxlen, codepage, false); } else { len = strnlen(src, maxlen); len++; dst = kmalloc(len, GFP_KERNEL); if (!dst) return NULL; strlcpy(dst, src, len); } return dst; } |
84cdf74e8
|
255 256 257 258 259 260 261 |
/* * Convert 16 bit Unicode pathname to wire format from string in current code * page. Conversion may involve remapping up the six characters that are * only legal in POSIX-like OS (if they are present in the string). Path * names are little endian 16 bit Unicode on the wire */ int |
581ade4d1
|
262 |
cifsConvertToUCS(__le16 *target, const char *source, int srclen, |
84cdf74e8
|
263 264 265 |
const struct nls_table *cp, int mapChars) { int i, j, charlen; |
84cdf74e8
|
266 |
char src_char; |
581ade4d1
|
267 268 |
__le16 dst_char; wchar_t tmp; |
84cdf74e8
|
269 270 271 |
if (!mapChars) return cifs_strtoUCS(target, source, PATH_MAX, cp); |
581ade4d1
|
272 |
for (i = 0, j = 0; i < srclen; j++) { |
84cdf74e8
|
273 |
src_char = source[i]; |
11379b5e3
|
274 |
charlen = 1; |
84cdf74e8
|
275 276 |
switch (src_char) { case 0: |
581ade4d1
|
277 |
put_unaligned(0, &target[j]); |
84cdf74e8
|
278 279 |
goto ctoUCS_out; case ':': |
581ade4d1
|
280 |
dst_char = cpu_to_le16(UNI_COLON); |
84cdf74e8
|
281 282 |
break; case '*': |
581ade4d1
|
283 |
dst_char = cpu_to_le16(UNI_ASTERISK); |
84cdf74e8
|
284 285 |
break; case '?': |
581ade4d1
|
286 |
dst_char = cpu_to_le16(UNI_QUESTION); |
84cdf74e8
|
287 288 |
break; case '<': |
581ade4d1
|
289 |
dst_char = cpu_to_le16(UNI_LESSTHAN); |
84cdf74e8
|
290 291 |
break; case '>': |
581ade4d1
|
292 |
dst_char = cpu_to_le16(UNI_GRTRTHAN); |
84cdf74e8
|
293 294 |
break; case '|': |
581ade4d1
|
295 |
dst_char = cpu_to_le16(UNI_PIPE); |
84cdf74e8
|
296 297 298 299 300 301 302 |
break; /* * FIXME: We can not handle remapping backslash (UNI_SLASH) * until all the calls to build_path_from_dentry are modified, * as they use backslash as separator. */ default: |
581ade4d1
|
303 304 |
charlen = cp->char2uni(source + i, srclen - i, &tmp); dst_char = cpu_to_le16(tmp); |
84cdf74e8
|
305 306 307 308 309 |
/* * if no match, use question mark, which at least in * some cases serves as wild card */ if (charlen < 1) { |
581ade4d1
|
310 |
dst_char = cpu_to_le16(0x003f); |
84cdf74e8
|
311 312 |
charlen = 1; } |
84cdf74e8
|
313 |
} |
11379b5e3
|
314 315 316 317 318 |
/* * character may take more than one byte in the source string, * but will take exactly two bytes in the target string */ i += charlen; |
581ade4d1
|
319 |
put_unaligned(dst_char, &target[j]); |
84cdf74e8
|
320 321 322 323 324 |
} ctoUCS_out: return i; } |