2 * cifs_unicode: Unicode kernel case support
5 * Convert a unicode character to upper or lower case using
8 * Copyright (c) International Business Machines Corp., 2000,2009
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
12 * the Free Software Foundation; either version 2 of the License, or
13 * (at your option) any later version.
15 * 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.
20 * You should have received a copy of the GNU General Public License
21 * along with this program; if not, write to the Free Software
22 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
26 * These APIs are based on the C library functions. The semantics
27 * should match the C functions but with expanded size operands.
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.
33 #ifndef _CIFS_UNICODE_H
34 #define _CIFS_UNICODE_H
36 #include <asm/byteorder.h>
37 #include <linux/types.h>
38 #include <linux/nls.h>
40 #define UNIUPR_NOLOWER /* Example to not expand lower case tables */
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
47 #define UNI_ASTERISK (__u16) ('*' + 0xF000)
48 #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)
55 /* Just define what we want from uniupr.h. We don't want to define the tables
56 * in each source file.
58 #ifndef UNICASERANGE_DEFINED
64 #endif /* UNICASERANGE_DEFINED */
66 #ifndef UNIUPR_NOUPPER
67 extern signed char CifsUniUpperTable[512];
68 extern const struct UniCaseRange CifsUniUpperRange[];
69 #endif /* UNIUPR_NOUPPER */
71 #ifndef UNIUPR_NOLOWER
72 extern signed char CifsUniLowerTable[512];
73 extern const struct UniCaseRange CifsUniLowerRange[];
74 #endif /* UNIUPR_NOLOWER */
77 int cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
78 const struct nls_table *codepage, bool mapchar);
79 int cifs_ucs2_bytes(const __le16 *from, int maxbytes,
80 const struct nls_table *codepage);
81 int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *);
82 char *cifs_strndup_from_ucs(const char *src, const int maxlen,
83 const bool is_unicode,
84 const struct nls_table *codepage);
85 extern int cifsConvertToUCS(__le16 *target, const char *source, int maxlen,
86 const struct nls_table *cp, int mapChars);
91 * UniStrcat: Concatenate the second string to the first
94 * Address of the first string
96 static inline wchar_t *
97 UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
99 wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
101 while (*ucs1++) ; /* To end of first string */
102 ucs1--; /* Return to the null */
103 while ((*ucs1++ = *ucs2++)) ; /* copy string 2 over */
108 * UniStrchr: Find a character in a string
111 * Address of first occurrence of character in string
112 * or NULL if the character is not in the string
114 static inline wchar_t *
115 UniStrchr(const wchar_t *ucs, wchar_t uc)
117 while ((*ucs != uc) && *ucs)
121 return (wchar_t *) ucs;
126 * UniStrcmp: Compare two strings
129 * < 0: First string is less than second
130 * = 0: Strings are equal
131 * > 0: First string is greater than second
134 UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
136 while ((*ucs1 == *ucs2) && *ucs1) {
140 return (int) *ucs1 - (int) *ucs2;
144 * UniStrcpy: Copy a string
146 static inline wchar_t *
147 UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
149 wchar_t *anchor = ucs1; /* save the start of result string */
151 while ((*ucs1++ = *ucs2++)) ;
156 * UniStrlen: Return the length of a string (in 16 bit Unicode chars not bytes)
159 UniStrlen(const wchar_t *ucs1)
169 * UniStrnlen: Return the length (in 16 bit Unicode chars not bytes) of a
170 * string (length limited)
173 UniStrnlen(const wchar_t *ucs1, int maxlen)
186 * UniStrncat: Concatenate length limited string
188 static inline wchar_t *
189 UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
191 wchar_t *anchor = ucs1; /* save pointer to string 1 */
194 ucs1--; /* point to null terminator of s1 */
195 while (n-- && (*ucs1 = *ucs2)) { /* copy s2 after s1 */
199 *ucs1 = 0; /* Null terminate the result */
204 * UniStrncmp: Compare length limited string
207 UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
210 return 0; /* Null strings are equal */
211 while ((*ucs1 == *ucs2) && *ucs1 && --n) {
215 return (int) *ucs1 - (int) *ucs2;
219 * UniStrncmp_le: Compare length limited string - native to little-endian
222 UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
225 return 0; /* Null strings are equal */
226 while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
230 return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
234 * UniStrncpy: Copy length limited string with pad
236 static inline wchar_t *
237 UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
239 wchar_t *anchor = ucs1;
241 while (n-- && *ucs2) /* Copy the strings */
245 while (n--) /* Pad with nulls */
251 * UniStrncpy_le: Copy length limited string with pad to little-endian
253 static inline wchar_t *
254 UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
256 wchar_t *anchor = ucs1;
258 while (n-- && *ucs2) /* Copy the strings */
259 *ucs1++ = __le16_to_cpu(*ucs2++);
262 while (n--) /* Pad with nulls */
268 * UniStrstr: Find a string in a string
271 * Address of first match found
272 * NULL if no matching string is found
274 static inline wchar_t *
275 UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
277 const wchar_t *anchor1 = ucs1;
278 const wchar_t *anchor2 = ucs2;
281 if (*ucs1 == *ucs2) {
282 /* Partial match found */
286 if (!*ucs2) /* Match found */
287 return (wchar_t *) anchor1;
288 ucs1 = ++anchor1; /* No match */
293 if (!*ucs2) /* Both end together */
294 return (wchar_t *) anchor1; /* Match found */
295 return NULL; /* No match */
298 #ifndef UNIUPR_NOUPPER
300 * UniToupper: Convert a unicode character to upper case
302 static inline wchar_t
303 UniToupper(register wchar_t uc)
305 register const struct UniCaseRange *rp;
307 if (uc < sizeof(CifsUniUpperTable)) {
308 /* Latin characters */
309 return uc + CifsUniUpperTable[uc]; /* Use base tables */
311 rp = CifsUniUpperRange; /* Use range tables */
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 */
320 return uc; /* Past last range */
324 * UniStrupr: Upper case a unicode string
326 static inline wchar_t *
327 UniStrupr(register wchar_t *upin)
329 register wchar_t *up;
332 while (*up) { /* For all characters */
333 *up = UniToupper(*up);
336 return upin; /* Return input pointer */
338 #endif /* UNIUPR_NOUPPER */
340 #ifndef UNIUPR_NOLOWER
342 * UniTolower: Convert a unicode character to lower case
344 static inline wchar_t
345 UniTolower(register wchar_t uc)
347 register const struct UniCaseRange *rp;
349 if (uc < sizeof(CifsUniLowerTable)) {
350 /* Latin characters */
351 return uc + CifsUniLowerTable[uc]; /* Use base tables */
353 rp = CifsUniLowerRange; /* Use range tables */
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 */
362 return uc; /* Past last range */
366 * UniStrlwr: Lower case a unicode string
368 static inline wchar_t *
369 UniStrlwr(register wchar_t *upin)
371 register wchar_t *up;
374 while (*up) { /* For all characters */
375 *up = UniTolower(*up);
378 return upin; /* Return input pointer */
383 #endif /* _CIFS_UNICODE_H */