fs/cifs/cifs_unicode.h

   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., 2000,2009
   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 /*
  41  * Windows maps these to the user defined 16 bit Unicode range since they are
  42  * reserved symbols (along with \ and /), otherwise illegal to store
  43  * in filenames in NTFS
  44  */
  45 #define UNI_ASTERIK     (__u16) ('*' + 0xF000)
  46 #define UNI_QUESTION    (__u16) ('?' + 0xF000)
  47 #define UNI_COLON       (__u16) (':' + 0xF000)
  48 #define UNI_GRTRTHAN    (__u16) ('>' + 0xF000)
  49 #define UNI_LESSTHAN    (__u16) ('<' + 0xF000)
  50 #define UNI_PIPE        (__u16) ('|' + 0xF000)
  51 #define UNI_SLASH       (__u16) ('\\' + 0xF000)
  52
  53 /* Just define what we want from uniupr.h.  We don't want to define the tables
  54  * in each source file.
  55  */
  56 #ifndef UNICASERANGE_DEFINED
  57 struct UniCaseRange {
  58         wchar_t start;
  59         wchar_t end;
  60         signed char *table;
  61 };
  62 #endif                          /* UNICASERANGE_DEFINED */
  63
  64 #ifndef UNIUPR_NOUPPER
  65 extern signed char CifsUniUpperTable[512];
  66 extern const struct UniCaseRange CifsUniUpperRange[];
  67 #endif                          /* UNIUPR_NOUPPER */
  68
  69 #ifndef UNIUPR_NOLOWER
  70 extern signed char UniLowerTable[512];
  71 extern struct UniCaseRange UniLowerRange[];
  72 #endif                          /* UNIUPR_NOLOWER */
  73
  74 #ifdef __KERNEL__
  75 int cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
  76                    const struct nls_table *codepage, bool mapchar);
  77 int cifs_ucs2_bytes(const __le16 *from, int maxbytes,
  78                     const struct nls_table *codepage);
  79 int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *);
  80 char *cifs_strndup_from_ucs(const char *src, const int maxlen,
  81                             const bool is_unicode,
  82                             const struct nls_table *codepage);
  83 #endif
  84
  85 /*
  86  * UniStrcat:  Concatenate the second string to the first
  87  *
  88  * Returns:
  89  *     Address of the first string
  90  */
  91 static inline wchar_t *
  92 UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
  93 {
  94         wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
  95
  96         while (*ucs1++) ;       /* To end of first string */
  97         ucs1--;                 /* Return to the null */
  98         while ((*ucs1++ = *ucs2++)) ;   /* copy string 2 over */
  99         return anchor;
 100 }
 101
 102 /*
 103  * UniStrchr:  Find a character in a string
 104  *
 105  * Returns:
 106  *     Address of first occurrence of character in string
 107  *     or NULL if the character is not in the string
 108  */
 109 static inline wchar_t *
 110 UniStrchr(const wchar_t *ucs, wchar_t uc)
 111 {
 112         while ((*ucs != uc) && *ucs)
 113                 ucs++;
 114
 115         if (*ucs == uc)
 116                 return (wchar_t *) ucs;
 117         return NULL;
 118 }
 119
 120 /*
 121  * UniStrcmp:  Compare two strings
 122  *
 123  * Returns:
 124  *     < 0:  First string is less than second
 125  *     = 0:  Strings are equal
 126  *     > 0:  First string is greater than second
 127  */
 128 static inline int
 129 UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
 130 {
 131         while ((*ucs1 == *ucs2) && *ucs1) {
 132                 ucs1++;
 133                 ucs2++;
 134         }
 135         return (int) *ucs1 - (int) *ucs2;
 136 }
 137
 138 /*
 139  * UniStrcpy:  Copy a string
 140  */
 141 static inline wchar_t *
 142 UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
 143 {
 144         wchar_t *anchor = ucs1; /* save the start of result string */
 145
 146         while ((*ucs1++ = *ucs2++)) ;
 147         return anchor;
 148 }
 149
 150 /*
 151  * UniStrlen:  Return the length of a string (in 16 bit Unicode chars not bytes)
 152  */
 153 static inline size_t
 154 UniStrlen(const wchar_t *ucs1)
 155 {
 156         int i = 0;
 157
 158         while (*ucs1++)
 159                 i++;
 160         return i;
 161 }
 162
 163 /*
 164  * UniStrnlen:  Return the length (in 16 bit Unicode chars not bytes) of a
 165  *              string (length limited)
 166  */
 167 static inline size_t
 168 UniStrnlen(const wchar_t *ucs1, int maxlen)
 169 {
 170         int i = 0;
 171
 172         while (*ucs1++) {
 173                 i++;
 174                 if (i >= maxlen)
 175                         break;
 176         }
 177         return i;
 178 }
 179
 180 /*
 181  * UniStrncat:  Concatenate length limited string
 182  */
 183 static inline wchar_t *
 184 UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 185 {
 186         wchar_t *anchor = ucs1; /* save pointer to string 1 */
 187
 188         while (*ucs1++) ;
 189         ucs1--;                 /* point to null terminator of s1 */
 190         while (n-- && (*ucs1 = *ucs2)) {        /* copy s2 after s1 */
 191                 ucs1++;
 192                 ucs2++;
 193         }
 194         *ucs1 = 0;              /* Null terminate the result */
 195         return (anchor);
 196 }
 197
 198 /*
 199  * UniStrncmp:  Compare length limited string
 200  */
 201 static inline int
 202 UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 203 {
 204         if (!n)
 205                 return 0;       /* Null strings are equal */
 206         while ((*ucs1 == *ucs2) && *ucs1 && --n) {
 207                 ucs1++;
 208                 ucs2++;
 209         }
 210         return (int) *ucs1 - (int) *ucs2;
 211 }
 212
 213 /*
 214  * UniStrncmp_le:  Compare length limited string - native to little-endian
 215  */
 216 static inline int
 217 UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 218 {
 219         if (!n)
 220                 return 0;       /* Null strings are equal */
 221         while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
 222                 ucs1++;
 223                 ucs2++;
 224         }
 225         return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
 226 }
 227
 228 /*
 229  * UniStrncpy:  Copy length limited string with pad
 230  */
 231 static inline wchar_t *
 232 UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 233 {
 234         wchar_t *anchor = ucs1;
 235
 236         while (n-- && *ucs2)    /* Copy the strings */
 237                 *ucs1++ = *ucs2++;
 238
 239         n++;
 240         while (n--)             /* Pad with nulls */
 241                 *ucs1++ = 0;
 242         return anchor;
 243 }
 244
 245 /*
 246  * UniStrncpy_le:  Copy length limited string with pad to little-endian
 247  */
 248 static inline wchar_t *
 249 UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 250 {
 251         wchar_t *anchor = ucs1;
 252
 253         while (n-- && *ucs2)    /* Copy the strings */
 254                 *ucs1++ = __le16_to_cpu(*ucs2++);
 255
 256         n++;
 257         while (n--)             /* Pad with nulls */
 258                 *ucs1++ = 0;
 259         return anchor;
 260 }
 261
 262 /*
 263  * UniStrstr:  Find a string in a string
 264  *
 265  * Returns:
 266  *     Address of first match found
 267  *     NULL if no matching string is found
 268  */
 269 static inline wchar_t *
 270 UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
 271 {
 272         const wchar_t *anchor1 = ucs1;
 273         const wchar_t *anchor2 = ucs2;
 274
 275         while (*ucs1) {
 276                 if (*ucs1 == *ucs2) {
 277                         /* Partial match found */
 278                         ucs1++;
 279                         ucs2++;
 280                 } else {
 281                         if (!*ucs2)     /* Match found */
 282                                 return (wchar_t *) anchor1;
 283                         ucs1 = ++anchor1;       /* No match */
 284                         ucs2 = anchor2;
 285                 }
 286         }
 287
 288         if (!*ucs2)             /* Both end together */
 289                 return (wchar_t *) anchor1;     /* Match found */
 290         return NULL;            /* No match */
 291 }
 292
 293 #ifndef UNIUPR_NOUPPER
 294 /*
 295  * UniToupper:  Convert a unicode character to upper case
 296  */
 297 static inline wchar_t
 298 UniToupper(register wchar_t uc)
 299 {
 300         register const struct UniCaseRange *rp;
 301
 302         if (uc < sizeof(CifsUniUpperTable)) {
 303                 /* Latin characters */
 304                 return uc + CifsUniUpperTable[uc];      /* Use base tables */
 305         } else {
 306                 rp = CifsUniUpperRange; /* Use range tables */
 307                 while (rp->start) {
 308                         if (uc < rp->start)     /* Before start of range */
 309                                 return uc;      /* Uppercase = input */
 310                         if (uc <= rp->end)      /* In range */
 311                                 return uc + rp->table[uc - rp->start];
 312                         rp++;   /* Try next range */
 313                 }
 314         }
 315         return uc;              /* Past last range */
 316 }
 317
 318 /*
 319  * UniStrupr:  Upper case a unicode string
 320  */
 321 static inline wchar_t *
 322 UniStrupr(register wchar_t *upin)
 323 {
 324         register wchar_t *up;
 325
 326         up = upin;
 327         while (*up) {           /* For all characters */
 328                 *up = UniToupper(*up);
 329                 up++;
 330         }
 331         return upin;            /* Return input pointer */
 332 }
 333 #endif                          /* UNIUPR_NOUPPER */
 334
 335 #ifndef UNIUPR_NOLOWER
 336 /*
 337  * UniTolower:  Convert a unicode character to lower case
 338  */
 339 static inline wchar_t
 340 UniTolower(wchar_t uc)
 341 {
 342         register struct UniCaseRange *rp;
 343
 344         if (uc < sizeof(UniLowerTable)) {
 345                 /* Latin characters */
 346                 return uc + UniLowerTable[uc];  /* Use base tables */
 347         } else {
 348                 rp = UniLowerRange;     /* Use range tables */
 349                 while (rp->start) {
 350                         if (uc < rp->start)     /* Before start of range */
 351                                 return uc;      /* Uppercase = input */
 352                         if (uc <= rp->end)      /* In range */
 353                                 return uc + rp->table[uc - rp->start];
 354                         rp++;   /* Try next range */
 355                 }
 356         }
 357         return uc;              /* Past last range */
 358 }
 359
 360 /*
 361  * UniStrlwr:  Lower case a unicode string
 362  */
 363 static inline wchar_t *
 364 UniStrlwr(register wchar_t *upin)
 365 {
 366         register wchar_t *up;
 367
 368         up = upin;
 369         while (*up) {           /* For all characters */
 370                 *up = UniTolower(*up);
 371                 up++;
 372         }
 373         return upin;            /* Return input pointer */
 374 }
 375
 376 #endif