| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* | 
|  | 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 French | e89dc92 | 2005-11-11 15:18:19 -0800 | [diff] [blame] | 8 | *   Copyright (c) International Business Machines  Corp., 2000,2005555555555555555555555555555555555555555555555555555555 | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 9 | * | 
|  | 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. | 
|  | 14 | * | 
|  | 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. | 
|  | 19 | * | 
|  | 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 | 
|  | 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 | */ | 
|  | 33 |  | 
|  | 34 | #include <asm/byteorder.h> | 
|  | 35 | #include <linux/types.h> | 
|  | 36 | #include <linux/nls.h> | 
|  | 37 |  | 
|  | 38 | #define  UNIUPR_NOLOWER		/* Example to not expand lower case tables */ | 
|  | 39 |  | 
|  | 40 | /* Just define what we want from uniupr.h.  We don't want to define the tables | 
|  | 41 | * in each source file. | 
|  | 42 | */ | 
|  | 43 | #ifndef	UNICASERANGE_DEFINED | 
|  | 44 | struct UniCaseRange { | 
|  | 45 | wchar_t start; | 
|  | 46 | wchar_t end; | 
|  | 47 | signed char *table; | 
|  | 48 | }; | 
|  | 49 | #endif				/* UNICASERANGE_DEFINED */ | 
|  | 50 |  | 
|  | 51 | #ifndef UNIUPR_NOUPPER | 
|  | 52 | extern signed char CifsUniUpperTable[512]; | 
|  | 53 | extern const struct UniCaseRange CifsUniUpperRange[]; | 
|  | 54 | #endif				/* UNIUPR_NOUPPER */ | 
|  | 55 |  | 
|  | 56 | #ifndef UNIUPR_NOLOWER | 
|  | 57 | extern signed char UniLowerTable[512]; | 
|  | 58 | extern struct UniCaseRange UniLowerRange[]; | 
|  | 59 | #endif				/* UNIUPR_NOLOWER */ | 
|  | 60 |  | 
|  | 61 | #ifdef __KERNEL__ | 
| Steve French | e89dc92 | 2005-11-11 15:18:19 -0800 | [diff] [blame] | 62 | int cifs_strfromUCS_le(char *, const __le16 *, int, const struct nls_table *); | 
|  | 63 | int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 64 | #endif | 
|  | 65 |  | 
|  | 66 | /* | 
|  | 67 | * UniStrcat:  Concatenate the second string to the first | 
|  | 68 | * | 
|  | 69 | * Returns: | 
|  | 70 | *     Address of the first string | 
|  | 71 | */ | 
|  | 72 | static inline wchar_t * | 
|  | 73 | UniStrcat(wchar_t * ucs1, const wchar_t * ucs2) | 
|  | 74 | { | 
|  | 75 | wchar_t *anchor = ucs1;	/* save a pointer to start of ucs1 */ | 
|  | 76 |  | 
|  | 77 | while (*ucs1++) ;	/* To end of first string */ | 
|  | 78 | ucs1--;			/* Return to the null */ | 
|  | 79 | while ((*ucs1++ = *ucs2++)) ;	/* copy string 2 over */ | 
|  | 80 | return anchor; | 
|  | 81 | } | 
|  | 82 |  | 
|  | 83 | /* | 
|  | 84 | * UniStrchr:  Find a character in a string | 
|  | 85 | * | 
|  | 86 | * Returns: | 
|  | 87 | *     Address of first occurrence of character in string | 
|  | 88 | *     or NULL if the character is not in the string | 
|  | 89 | */ | 
|  | 90 | static inline wchar_t * | 
|  | 91 | UniStrchr(const wchar_t * ucs, wchar_t uc) | 
|  | 92 | { | 
|  | 93 | while ((*ucs != uc) && *ucs) | 
|  | 94 | ucs++; | 
|  | 95 |  | 
|  | 96 | if (*ucs == uc) | 
|  | 97 | return (wchar_t *) ucs; | 
|  | 98 | return NULL; | 
|  | 99 | } | 
|  | 100 |  | 
|  | 101 | /* | 
|  | 102 | * UniStrcmp:  Compare two strings | 
|  | 103 | * | 
|  | 104 | * Returns: | 
|  | 105 | *     < 0:  First string is less than second | 
|  | 106 | *     = 0:  Strings are equal | 
|  | 107 | *     > 0:  First string is greater than second | 
|  | 108 | */ | 
|  | 109 | static inline int | 
|  | 110 | UniStrcmp(const wchar_t * ucs1, const wchar_t * ucs2) | 
|  | 111 | { | 
|  | 112 | while ((*ucs1 == *ucs2) && *ucs1) { | 
|  | 113 | ucs1++; | 
|  | 114 | ucs2++; | 
|  | 115 | } | 
|  | 116 | return (int) *ucs1 - (int) *ucs2; | 
|  | 117 | } | 
|  | 118 |  | 
|  | 119 | /* | 
|  | 120 | * UniStrcpy:  Copy a string | 
|  | 121 | */ | 
|  | 122 | static inline wchar_t * | 
|  | 123 | UniStrcpy(wchar_t * ucs1, const wchar_t * ucs2) | 
|  | 124 | { | 
|  | 125 | wchar_t *anchor = ucs1;	/* save the start of result string */ | 
|  | 126 |  | 
|  | 127 | while ((*ucs1++ = *ucs2++)) ; | 
|  | 128 | return anchor; | 
|  | 129 | } | 
|  | 130 |  | 
|  | 131 | /* | 
|  | 132 | * UniStrlen:  Return the length of a string (in 16 bit Unicode chars not bytes) | 
|  | 133 | */ | 
|  | 134 | static inline size_t | 
|  | 135 | UniStrlen(const wchar_t * ucs1) | 
|  | 136 | { | 
|  | 137 | int i = 0; | 
|  | 138 |  | 
|  | 139 | while (*ucs1++) | 
|  | 140 | i++; | 
|  | 141 | return i; | 
|  | 142 | } | 
|  | 143 |  | 
|  | 144 | /* | 
|  | 145 | * UniStrnlen:  Return the length (in 16 bit Unicode chars not bytes) of a string (length limited) | 
|  | 146 | */ | 
|  | 147 | static inline size_t | 
|  | 148 | UniStrnlen(const wchar_t * ucs1, int maxlen) | 
|  | 149 | { | 
|  | 150 | int i = 0; | 
|  | 151 |  | 
|  | 152 | while (*ucs1++) { | 
|  | 153 | i++; | 
|  | 154 | if (i >= maxlen) | 
|  | 155 | break; | 
|  | 156 | } | 
|  | 157 | return i; | 
|  | 158 | } | 
|  | 159 |  | 
|  | 160 | /* | 
|  | 161 | * UniStrncat:  Concatenate length limited string | 
|  | 162 | */ | 
|  | 163 | static inline wchar_t * | 
|  | 164 | UniStrncat(wchar_t * ucs1, const wchar_t * ucs2, size_t n) | 
|  | 165 | { | 
|  | 166 | wchar_t *anchor = ucs1;	/* save pointer to string 1 */ | 
|  | 167 |  | 
|  | 168 | while (*ucs1++) ; | 
|  | 169 | ucs1--;			/* point to null terminator of s1 */ | 
|  | 170 | while (n-- && (*ucs1 = *ucs2)) {	/* copy s2 after s1 */ | 
|  | 171 | ucs1++; | 
|  | 172 | ucs2++; | 
|  | 173 | } | 
|  | 174 | *ucs1 = 0;		/* Null terminate the result */ | 
|  | 175 | return (anchor); | 
|  | 176 | } | 
|  | 177 |  | 
|  | 178 | /* | 
|  | 179 | * UniStrncmp:  Compare length limited string | 
|  | 180 | */ | 
|  | 181 | static inline int | 
|  | 182 | UniStrncmp(const wchar_t * ucs1, const wchar_t * ucs2, size_t n) | 
|  | 183 | { | 
|  | 184 | if (!n) | 
|  | 185 | return 0;	/* Null strings are equal */ | 
|  | 186 | while ((*ucs1 == *ucs2) && *ucs1 && --n) { | 
|  | 187 | ucs1++; | 
|  | 188 | ucs2++; | 
|  | 189 | } | 
|  | 190 | return (int) *ucs1 - (int) *ucs2; | 
|  | 191 | } | 
|  | 192 |  | 
|  | 193 | /* | 
|  | 194 | * UniStrncmp_le:  Compare length limited string - native to little-endian | 
|  | 195 | */ | 
|  | 196 | static inline int | 
|  | 197 | UniStrncmp_le(const wchar_t * ucs1, const wchar_t * ucs2, size_t n) | 
|  | 198 | { | 
|  | 199 | if (!n) | 
|  | 200 | return 0;	/* Null strings are equal */ | 
|  | 201 | while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) { | 
|  | 202 | ucs1++; | 
|  | 203 | ucs2++; | 
|  | 204 | } | 
|  | 205 | return (int) *ucs1 - (int) __le16_to_cpu(*ucs2); | 
|  | 206 | } | 
|  | 207 |  | 
|  | 208 | /* | 
|  | 209 | * UniStrncpy:  Copy length limited string with pad | 
|  | 210 | */ | 
|  | 211 | static inline wchar_t * | 
|  | 212 | UniStrncpy(wchar_t * ucs1, const wchar_t * ucs2, size_t n) | 
|  | 213 | { | 
|  | 214 | wchar_t *anchor = ucs1; | 
|  | 215 |  | 
|  | 216 | while (n-- && *ucs2)	/* Copy the strings */ | 
|  | 217 | *ucs1++ = *ucs2++; | 
|  | 218 |  | 
|  | 219 | n++; | 
|  | 220 | while (n--)		/* Pad with nulls */ | 
|  | 221 | *ucs1++ = 0; | 
|  | 222 | return anchor; | 
|  | 223 | } | 
|  | 224 |  | 
|  | 225 | /* | 
|  | 226 | * UniStrncpy_le:  Copy length limited string with pad to little-endian | 
|  | 227 | */ | 
|  | 228 | static inline wchar_t * | 
|  | 229 | UniStrncpy_le(wchar_t * ucs1, const wchar_t * ucs2, size_t n) | 
|  | 230 | { | 
|  | 231 | wchar_t *anchor = ucs1; | 
|  | 232 |  | 
|  | 233 | while (n-- && *ucs2)	/* Copy the strings */ | 
|  | 234 | *ucs1++ = __le16_to_cpu(*ucs2++); | 
|  | 235 |  | 
|  | 236 | n++; | 
|  | 237 | while (n--)		/* Pad with nulls */ | 
|  | 238 | *ucs1++ = 0; | 
|  | 239 | return anchor; | 
|  | 240 | } | 
|  | 241 |  | 
|  | 242 | /* | 
|  | 243 | * UniStrstr:  Find a string in a string | 
|  | 244 | * | 
|  | 245 | * Returns: | 
|  | 246 | *     Address of first match found | 
|  | 247 | *     NULL if no matching string is found | 
|  | 248 | */ | 
|  | 249 | static inline wchar_t * | 
|  | 250 | UniStrstr(const wchar_t * ucs1, const wchar_t * ucs2) | 
|  | 251 | { | 
|  | 252 | const wchar_t *anchor1 = ucs1; | 
|  | 253 | const wchar_t *anchor2 = ucs2; | 
|  | 254 |  | 
|  | 255 | while (*ucs1) { | 
|  | 256 | if (*ucs1 == *ucs2) {	/* Partial match found */ | 
|  | 257 | ucs1++; | 
|  | 258 | ucs2++; | 
|  | 259 | } else { | 
|  | 260 | if (!*ucs2)	/* Match found */ | 
|  | 261 | return (wchar_t *) anchor1; | 
|  | 262 | ucs1 = ++anchor1;	/* No match */ | 
|  | 263 | ucs2 = anchor2; | 
|  | 264 | } | 
|  | 265 | } | 
|  | 266 |  | 
|  | 267 | if (!*ucs2)		/* Both end together */ | 
|  | 268 | return (wchar_t *) anchor1;	/* Match found */ | 
|  | 269 | return NULL;		/* No match */ | 
|  | 270 | } | 
|  | 271 |  | 
|  | 272 | #ifndef UNIUPR_NOUPPER | 
|  | 273 | /* | 
|  | 274 | * UniToupper:  Convert a unicode character to upper case | 
|  | 275 | */ | 
|  | 276 | static inline wchar_t | 
|  | 277 | UniToupper(register wchar_t uc) | 
|  | 278 | { | 
|  | 279 | register const struct UniCaseRange *rp; | 
|  | 280 |  | 
|  | 281 | if (uc < sizeof (CifsUniUpperTable)) {	/* Latin characters */ | 
|  | 282 | return uc + CifsUniUpperTable[uc];	/* Use base tables */ | 
|  | 283 | } else { | 
|  | 284 | rp = CifsUniUpperRange;	/* Use range tables */ | 
|  | 285 | while (rp->start) { | 
|  | 286 | if (uc < rp->start)	/* Before start of range */ | 
|  | 287 | return uc;	/* Uppercase = input */ | 
|  | 288 | if (uc <= rp->end)	/* In range */ | 
|  | 289 | return uc + rp->table[uc - rp->start]; | 
|  | 290 | rp++;	/* Try next range */ | 
|  | 291 | } | 
|  | 292 | } | 
|  | 293 | return uc;		/* Past last range */ | 
|  | 294 | } | 
|  | 295 |  | 
|  | 296 | /* | 
|  | 297 | * UniStrupr:  Upper case a unicode string | 
|  | 298 | */ | 
|  | 299 | static inline wchar_t * | 
|  | 300 | UniStrupr(register wchar_t * upin) | 
|  | 301 | { | 
|  | 302 | register wchar_t *up; | 
|  | 303 |  | 
|  | 304 | up = upin; | 
|  | 305 | while (*up) {		/* For all characters */ | 
|  | 306 | *up = UniToupper(*up); | 
|  | 307 | up++; | 
|  | 308 | } | 
|  | 309 | return upin;		/* Return input pointer */ | 
|  | 310 | } | 
|  | 311 | #endif				/* UNIUPR_NOUPPER */ | 
|  | 312 |  | 
|  | 313 | #ifndef UNIUPR_NOLOWER | 
|  | 314 | /* | 
|  | 315 | * UniTolower:  Convert a unicode character to lower case | 
|  | 316 | */ | 
|  | 317 | static inline wchar_t | 
|  | 318 | UniTolower(wchar_t uc) | 
|  | 319 | { | 
|  | 320 | register struct UniCaseRange *rp; | 
|  | 321 |  | 
|  | 322 | if (uc < sizeof (UniLowerTable)) {	/* Latin characters */ | 
|  | 323 | return uc + UniLowerTable[uc];	/* Use base tables */ | 
|  | 324 | } else { | 
|  | 325 | rp = UniLowerRange;	/* Use range tables */ | 
|  | 326 | while (rp->start) { | 
|  | 327 | if (uc < rp->start)	/* Before start of range */ | 
|  | 328 | return uc;	/* Uppercase = input */ | 
|  | 329 | if (uc <= rp->end)	/* In range */ | 
|  | 330 | return uc + rp->table[uc - rp->start]; | 
|  | 331 | rp++;	/* Try next range */ | 
|  | 332 | } | 
|  | 333 | } | 
|  | 334 | return uc;		/* Past last range */ | 
|  | 335 | } | 
|  | 336 |  | 
|  | 337 | /* | 
|  | 338 | * UniStrlwr:  Lower case a unicode string | 
|  | 339 | */ | 
|  | 340 | static inline wchar_t * | 
|  | 341 | UniStrlwr(register wchar_t * upin) | 
|  | 342 | { | 
|  | 343 | register wchar_t *up; | 
|  | 344 |  | 
|  | 345 | up = upin; | 
|  | 346 | while (*up) {		/* For all characters */ | 
|  | 347 | *up = UniTolower(*up); | 
|  | 348 | up++; | 
|  | 349 | } | 
|  | 350 | return upin;		/* Return input pointer */ | 
|  | 351 | } | 
|  | 352 |  | 
|  | 353 | #endif |