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 | * |
| 8 | * Copyright (c) International Business Machines Corp., 2000,2002 |
| 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__ |
| 62 | int cifs_strfromUCS_le(char *, const wchar_t *, int, const struct nls_table *); |
| 63 | int cifs_strtoUCS(wchar_t *, const char *, int, const struct nls_table *); |
| 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 |