aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorDuane Griffin <duaneg@dghda.com>2007-07-16 02:41:22 -0400
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-07-16 12:05:49 -0400
commit1e96b7ca1e8f17c5117da369daaa7cf2edfdf9b1 (patch)
treee770e898c43bc1e24bec330d97ef26c4f49189f8 /fs
parent29bc5b4f73a65ef667df50d5ed474e371471d915 (diff)
HFS+: refactor ASCII to unicode conversion routine for later reuse
The HFS+ filesystem is case-insensitive and does automatic unicode decomposition by default, but does not provide custom dentry operations. This can lead to multiple dentries being cached for lookups on a filename with varying case and/or character (de)composition. These patches add custom dentry hash and comparison operations for case-sensitive and/or automatically decomposing HFS+ filesystems. Unicode decomposition and case-folding are performed as required to ensure equivalent filenames are hashed to the same values and compare as equal. This patch: Refactor existing HFS+ ASCII to unicode string conversion routine to split out character conversion functionality. This will be reused by the custom dentry hash and comparison routines. This approach avoids unnecessary memory allocation compared to using the string conversion routine directly in the new functions. [akpm@linux-foundation.org: avoid use-of-uninitialised] Signed-off-by: Duane Griffin <duaneg@dghda.com> Signed-off-by: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/hfsplus/unicode.c107
1 files changed, 62 insertions, 45 deletions
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index 689c8bd721fb..5df0052b2775 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -239,58 +239,75 @@ out:
239 return res; 239 return res;
240} 240}
241 241
242int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, const char *astr, int len) 242/*
243 * Convert one or more ASCII characters into a single unicode character.
244 * Returns the number of ASCII characters corresponding to the unicode char.
245 */
246static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
247 wchar_t *uc)
243{ 248{
244 struct nls_table *nls = HFSPLUS_SB(sb).nls; 249 int size = HFSPLUS_SB(sb).nls->char2uni(astr, len, uc);
245 int size, off, decompose; 250 if (size <= 0) {
251 *uc = '?';
252 size = 1;
253 }
254 switch (*uc) {
255 case 0x2400:
256 *uc = 0;
257 break;
258 case ':':
259 *uc = '/';
260 break;
261 }
262 return size;
263}
264
265/* Decomposes a single unicode character. */
266static inline u16 *decompose_unichar(wchar_t uc, int *size)
267{
268 int off;
269
270 off = hfsplus_decompose_table[(uc >> 12) & 0xf];
271 if (off == 0 || off == 0xffff)
272 return NULL;
273
274 off = hfsplus_decompose_table[off + ((uc >> 8) & 0xf)];
275 if (!off)
276 return NULL;
277
278 off = hfsplus_decompose_table[off + ((uc >> 4) & 0xf)];
279 if (!off)
280 return NULL;
281
282 off = hfsplus_decompose_table[off + (uc & 0xf)];
283 *size = off & 3;
284 if (*size == 0)
285 return NULL;
286 return hfsplus_decompose_table + (off / 4);
287}
288
289int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
290 const char *astr, int len)
291{
292 int size, dsize, decompose;
293 u16 *dstr, outlen = 0;
246 wchar_t c; 294 wchar_t c;
247 u16 outlen = 0;
248 295
249 decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE); 296 decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
250
251 while (outlen < HFSPLUS_MAX_STRLEN && len > 0) { 297 while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
252 size = nls->char2uni(astr, len, &c); 298 size = asc2unichar(sb, astr, len, &c);
253 if (size <= 0) { 299
254 c = '?'; 300 if (decompose && (dstr = decompose_unichar(c, &dsize))) {
255 size = 1; 301 if (outlen + dsize > HFSPLUS_MAX_STRLEN)
256 }
257 astr += size;
258 len -= size;
259 switch (c) {
260 case 0x2400:
261 c = 0;
262 break;
263 case ':':
264 c = '/';
265 break;
266 }
267 if (c >= 0xc0 && decompose) {
268 off = hfsplus_decompose_table[(c >> 12) & 0xf];
269 if (!off)
270 goto done;
271 if (off == 0xffff) {
272 goto done;
273 }
274 off = hfsplus_decompose_table[off + ((c >> 8) & 0xf)];
275 if (!off)
276 goto done;
277 off = hfsplus_decompose_table[off + ((c >> 4) & 0xf)];
278 if (!off)
279 goto done;
280 off = hfsplus_decompose_table[off + (c & 0xf)];
281 size = off & 3;
282 if (!size)
283 goto done;
284 off /= 4;
285 if (outlen + size > HFSPLUS_MAX_STRLEN)
286 break; 302 break;
287 do { 303 do {
288 ustr->unicode[outlen++] = cpu_to_be16(hfsplus_decompose_table[off++]); 304 ustr->unicode[outlen++] = cpu_to_be16(*dstr++);
289 } while (--size > 0); 305 } while (--dsize > 0);
290 continue; 306 } else
291 } 307 ustr->unicode[outlen++] = cpu_to_be16(c);
292 done: 308
293 ustr->unicode[outlen++] = cpu_to_be16(c); 309 astr += size;
310 len -= size;
294 } 311 }
295 ustr->length = cpu_to_be16(outlen); 312 ustr->length = cpu_to_be16(outlen);
296 if (len > 0) 313 if (len > 0)