blob: a513a546700b5e1a9be653b77316b9487d04cde0 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * cifs_unicode: Unicode kernel case support
3 *
4 * Function:
5 * Convert a unicode character to upper or lower case using
6 * compressed tables.
7 *
Steve Frenchd185cda2009-04-30 17:45:10 +00008 * Copyright (c) International Business Machines Corp., 2000,2009
Linus Torvalds1da177e2005-04-16 15:20:36 -07009 *
10 * This program is free software; you can redistribute it and/or modify
11 * it under the terms of the GNU General Public License as published by
Steve Frenchd38d8c72007-06-28 19:44:13 +000012 * the Free Software Foundation; either version 2 of the License, or
Linus Torvalds1da177e2005-04-16 15:20:36 -070013 * (at your option) any later version.
Steve Frenchd38d8c72007-06-28 19:44:13 +000014 *
Linus Torvalds1da177e2005-04-16 15:20:36 -070015 * This program is distributed in the hope that it will be useful,
16 * but WITHOUT ANY WARRANTY; without even the implied warranty of
17 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
18 * the GNU General Public License for more details.
19 *
20 * You should have received a copy of the GNU General Public License
Steve Frenchd38d8c72007-06-28 19:44:13 +000021 * along with this program; if not, write to the Free Software
Linus Torvalds1da177e2005-04-16 15:20:36 -070022 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
23 *
24 *
25 * Notes:
26 * These APIs are based on the C library functions. The semantics
27 * should match the C functions but with expanded size operands.
28 *
29 * The upper/lower functions are based on a table created by mkupr.
30 * This is a compressed table of upper and lower case conversion.
31 *
32 */
Igor Druzhininbf4f1212010-08-20 00:27:12 +040033#ifndef _CIFS_UNICODE_H
34#define _CIFS_UNICODE_H
Linus Torvalds1da177e2005-04-16 15:20:36 -070035
36#include <asm/byteorder.h>
37#include <linux/types.h>
38#include <linux/nls.h>
39
40#define UNIUPR_NOLOWER /* Example to not expand lower case tables */
41
Jeff Layton66345f52009-04-30 06:45:08 -040042/*
43 * Windows maps these to the user defined 16 bit Unicode range since they are
44 * reserved symbols (along with \ and /), otherwise illegal to store
45 * in filenames in NTFS
46 */
Jeff Layton581ade42011-04-05 15:02:37 -040047#define UNI_ASTERISK (__u16) ('*' + 0xF000)
Jeff Layton66345f52009-04-30 06:45:08 -040048#define UNI_QUESTION (__u16) ('?' + 0xF000)
49#define UNI_COLON (__u16) (':' + 0xF000)
50#define UNI_GRTRTHAN (__u16) ('>' + 0xF000)
51#define UNI_LESSTHAN (__u16) ('<' + 0xF000)
52#define UNI_PIPE (__u16) ('|' + 0xF000)
53#define UNI_SLASH (__u16) ('\\' + 0xF000)
54
Linus Torvalds1da177e2005-04-16 15:20:36 -070055/* Just define what we want from uniupr.h. We don't want to define the tables
56 * in each source file.
57 */
58#ifndef UNICASERANGE_DEFINED
59struct UniCaseRange {
60 wchar_t start;
61 wchar_t end;
62 signed char *table;
63};
64#endif /* UNICASERANGE_DEFINED */
65
66#ifndef UNIUPR_NOUPPER
67extern signed char CifsUniUpperTable[512];
68extern const struct UniCaseRange CifsUniUpperRange[];
69#endif /* UNIUPR_NOUPPER */
70
71#ifndef UNIUPR_NOLOWER
Igor Druzhininbf4f1212010-08-20 00:27:12 +040072extern signed char CifsUniLowerTable[512];
73extern const struct UniCaseRange CifsUniLowerRange[];
Linus Torvalds1da177e2005-04-16 15:20:36 -070074#endif /* UNIUPR_NOLOWER */
75
76#ifdef __KERNEL__
Steve Frenchacbbb762012-01-18 22:32:33 -060077int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
78 const struct nls_table *codepage, bool mapchar);
79int cifs_utf16_bytes(const __le16 *from, int maxbytes,
80 const struct nls_table *codepage);
81int cifs_strtoUTF16(__le16 *, const char *, int, const struct nls_table *);
82char *cifs_strndup_from_utf16(const char *src, const int maxlen,
83 const bool is_unicode,
84 const struct nls_table *codepage);
85extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
86 const struct nls_table *cp, int mapChars);
Steve Frenchceec1e02011-03-14 19:01:59 +000087
Linus Torvalds1da177e2005-04-16 15:20:36 -070088#endif
89
90/*
91 * UniStrcat: Concatenate the second string to the first
92 *
93 * Returns:
94 * Address of the first string
95 */
96static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +000097UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
Linus Torvalds1da177e2005-04-16 15:20:36 -070098{
99 wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
100
101 while (*ucs1++) ; /* To end of first string */
102 ucs1--; /* Return to the null */
103 while ((*ucs1++ = *ucs2++)) ; /* copy string 2 over */
104 return anchor;
105}
106
107/*
108 * UniStrchr: Find a character in a string
109 *
110 * Returns:
111 * Address of first occurrence of character in string
112 * or NULL if the character is not in the string
113 */
114static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000115UniStrchr(const wchar_t *ucs, wchar_t uc)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700116{
117 while ((*ucs != uc) && *ucs)
118 ucs++;
119
120 if (*ucs == uc)
121 return (wchar_t *) ucs;
122 return NULL;
123}
124
125/*
126 * UniStrcmp: Compare two strings
127 *
128 * Returns:
129 * < 0: First string is less than second
130 * = 0: Strings are equal
131 * > 0: First string is greater than second
132 */
133static inline int
Steve French50c2f752007-07-13 00:33:32 +0000134UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700135{
136 while ((*ucs1 == *ucs2) && *ucs1) {
137 ucs1++;
138 ucs2++;
139 }
140 return (int) *ucs1 - (int) *ucs2;
141}
142
143/*
144 * UniStrcpy: Copy a string
145 */
146static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000147UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700148{
149 wchar_t *anchor = ucs1; /* save the start of result string */
150
151 while ((*ucs1++ = *ucs2++)) ;
152 return anchor;
153}
154
155/*
156 * UniStrlen: Return the length of a string (in 16 bit Unicode chars not bytes)
157 */
158static inline size_t
Steve French50c2f752007-07-13 00:33:32 +0000159UniStrlen(const wchar_t *ucs1)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700160{
161 int i = 0;
162
163 while (*ucs1++)
164 i++;
165 return i;
166}
167
168/*
Steve Frenchd38d8c72007-06-28 19:44:13 +0000169 * UniStrnlen: Return the length (in 16 bit Unicode chars not bytes) of a
170 * string (length limited)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700171 */
172static inline size_t
Steve French50c2f752007-07-13 00:33:32 +0000173UniStrnlen(const wchar_t *ucs1, int maxlen)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700174{
175 int i = 0;
176
177 while (*ucs1++) {
178 i++;
179 if (i >= maxlen)
180 break;
181 }
182 return i;
183}
184
185/*
186 * UniStrncat: Concatenate length limited string
187 */
188static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000189UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700190{
191 wchar_t *anchor = ucs1; /* save pointer to string 1 */
192
193 while (*ucs1++) ;
194 ucs1--; /* point to null terminator of s1 */
195 while (n-- && (*ucs1 = *ucs2)) { /* copy s2 after s1 */
196 ucs1++;
197 ucs2++;
198 }
199 *ucs1 = 0; /* Null terminate the result */
200 return (anchor);
201}
202
203/*
204 * UniStrncmp: Compare length limited string
205 */
206static inline int
Steve French50c2f752007-07-13 00:33:32 +0000207UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700208{
209 if (!n)
210 return 0; /* Null strings are equal */
211 while ((*ucs1 == *ucs2) && *ucs1 && --n) {
212 ucs1++;
213 ucs2++;
214 }
215 return (int) *ucs1 - (int) *ucs2;
216}
217
218/*
219 * UniStrncmp_le: Compare length limited string - native to little-endian
220 */
221static inline int
Steve French50c2f752007-07-13 00:33:32 +0000222UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700223{
224 if (!n)
225 return 0; /* Null strings are equal */
226 while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
227 ucs1++;
228 ucs2++;
229 }
230 return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
231}
232
233/*
234 * UniStrncpy: Copy length limited string with pad
235 */
236static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000237UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700238{
239 wchar_t *anchor = ucs1;
240
241 while (n-- && *ucs2) /* Copy the strings */
242 *ucs1++ = *ucs2++;
243
244 n++;
245 while (n--) /* Pad with nulls */
246 *ucs1++ = 0;
247 return anchor;
248}
249
250/*
251 * UniStrncpy_le: Copy length limited string with pad to little-endian
252 */
253static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000254UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700255{
256 wchar_t *anchor = ucs1;
257
258 while (n-- && *ucs2) /* Copy the strings */
259 *ucs1++ = __le16_to_cpu(*ucs2++);
260
261 n++;
262 while (n--) /* Pad with nulls */
263 *ucs1++ = 0;
264 return anchor;
265}
266
267/*
268 * UniStrstr: Find a string in a string
269 *
270 * Returns:
271 * Address of first match found
272 * NULL if no matching string is found
273 */
274static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000275UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700276{
277 const wchar_t *anchor1 = ucs1;
278 const wchar_t *anchor2 = ucs2;
279
280 while (*ucs1) {
Steve Frenchad7a2922008-02-07 23:25:02 +0000281 if (*ucs1 == *ucs2) {
282 /* Partial match found */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700283 ucs1++;
284 ucs2++;
285 } else {
286 if (!*ucs2) /* Match found */
287 return (wchar_t *) anchor1;
288 ucs1 = ++anchor1; /* No match */
289 ucs2 = anchor2;
290 }
291 }
292
293 if (!*ucs2) /* Both end together */
294 return (wchar_t *) anchor1; /* Match found */
295 return NULL; /* No match */
296}
297
298#ifndef UNIUPR_NOUPPER
299/*
300 * UniToupper: Convert a unicode character to upper case
301 */
302static inline wchar_t
303UniToupper(register wchar_t uc)
304{
305 register const struct UniCaseRange *rp;
306
Steve Frenchad7a2922008-02-07 23:25:02 +0000307 if (uc < sizeof(CifsUniUpperTable)) {
308 /* Latin characters */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700309 return uc + CifsUniUpperTable[uc]; /* Use base tables */
310 } else {
311 rp = CifsUniUpperRange; /* Use range tables */
312 while (rp->start) {
313 if (uc < rp->start) /* Before start of range */
314 return uc; /* Uppercase = input */
315 if (uc <= rp->end) /* In range */
316 return uc + rp->table[uc - rp->start];
317 rp++; /* Try next range */
318 }
319 }
320 return uc; /* Past last range */
321}
322
323/*
324 * UniStrupr: Upper case a unicode string
325 */
326static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000327UniStrupr(register wchar_t *upin)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700328{
329 register wchar_t *up;
330
331 up = upin;
332 while (*up) { /* For all characters */
333 *up = UniToupper(*up);
334 up++;
335 }
336 return upin; /* Return input pointer */
337}
338#endif /* UNIUPR_NOUPPER */
339
340#ifndef UNIUPR_NOLOWER
341/*
342 * UniTolower: Convert a unicode character to lower case
343 */
344static inline wchar_t
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400345UniTolower(register wchar_t uc)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700346{
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400347 register const struct UniCaseRange *rp;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700348
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400349 if (uc < sizeof(CifsUniLowerTable)) {
Steve Frenchad7a2922008-02-07 23:25:02 +0000350 /* Latin characters */
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400351 return uc + CifsUniLowerTable[uc]; /* Use base tables */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700352 } else {
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400353 rp = CifsUniLowerRange; /* Use range tables */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700354 while (rp->start) {
355 if (uc < rp->start) /* Before start of range */
356 return uc; /* Uppercase = input */
357 if (uc <= rp->end) /* In range */
358 return uc + rp->table[uc - rp->start];
359 rp++; /* Try next range */
360 }
361 }
362 return uc; /* Past last range */
363}
364
365/*
366 * UniStrlwr: Lower case a unicode string
367 */
368static inline wchar_t *
Steve French50c2f752007-07-13 00:33:32 +0000369UniStrlwr(register wchar_t *upin)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700370{
371 register wchar_t *up;
372
373 up = upin;
374 while (*up) { /* For all characters */
375 *up = UniTolower(*up);
376 up++;
377 }
378 return upin; /* Return input pointer */
379}
380
381#endif
Igor Druzhininbf4f1212010-08-20 00:27:12 +0400382
383#endif /* _CIFS_UNICODE_H */