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 #ifndef _CIFS_UNICODE_H
  34 #define _CIFS_UNICODE_H
  35
  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
  42 /*
  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  */
  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)
  54
  55 /* 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
  59 struct UniCaseRange {
  60         wchar_t start;
  61         wchar_t end;
  62         signed char *table;
  63 };
  64 #endif                          /* UNICASERANGE_DEFINED */
  65
  66 #ifndef UNIUPR_NOUPPER
  67 extern signed char CifsUniUpperTable[512];
  68 extern const struct UniCaseRange CifsUniUpperRange[];
  69 #endif                          /* UNIUPR_NOUPPER */
  70
  71 #ifndef UNIUPR_NOLOWER
  72 extern signed char CifsUniLowerTable[512];
  73 extern const struct UniCaseRange CifsUniLowerRange[];
  74 #endif                          /* UNIUPR_NOLOWER */
  75
  76 #ifdef __KERNEL__
  77 int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
  78                     const struct nls_table *codepage, bool mapchar);
  79 int cifs_utf16_bytes(const __le16 *from, int maxbytes,
  80                      const struct nls_table *codepage);
  81 int cifs_strtoUTF16(__le16 *, const char *, int, const struct nls_table *);
  82 char *cifs_strndup_from_utf16(const char *src, const int maxlen,
  83                               const bool is_unicode,
  84                               const struct nls_table *codepage);
  85 extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
  86                               const struct nls_table *cp, int mapChars);
  87
  88 #endif
  89
  90 /*
  91  * UniStrcat:  Concatenate the second string to the first
  92  *
  93  * Returns:
  94  *     Address of the first string
  95  */
  96 static inline wchar_t *
  97 UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
  98 {
  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  */
 114 static inline wchar_t *
 115 UniStrchr(const wchar_t *ucs, wchar_t uc)
 116 {
 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  */
 133 static inline int
 134 UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
 135 {
 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  */
 146 static inline wchar_t *
 147 UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
 148 {
 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  */
 158 static inline size_t
 159 UniStrlen(const wchar_t *ucs1)
 160 {
 161         int i = 0;
 162
 163         while (*ucs1++)
 164                 i++;
 165         return i;
 166 }
 167
 168 /*
 169  * UniStrnlen:  Return the length (in 16 bit Unicode chars not bytes) of a
 170  *              string (length limited)
 171  */
 172 static inline size_t
 173 UniStrnlen(const wchar_t *ucs1, int maxlen)
 174 {
 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  */
 188 static inline wchar_t *
 189 UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 190 {
 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  */
 206 static inline int
 207 UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 208 {
 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  */
 221 static inline int
 222 UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 223 {
 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  */
 236 static inline wchar_t *
 237 UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 238 {
 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  */
 253 static inline wchar_t *
 254 UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 255 {
 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  */
 274 static inline wchar_t *
 275 UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
 276 {
 277         const wchar_t *anchor1 = ucs1;
 278         const wchar_t *anchor2 = ucs2;
 279
 280         while (*ucs1) {
 281                 if (*ucs1 == *ucs2) {
 282                         /* Partial match found */
 283                         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  */
 302 static inline wchar_t
 303 UniToupper(register wchar_t uc)
 304 {
 305         register const struct UniCaseRange *rp;
 306
 307         if (uc < sizeof(CifsUniUpperTable)) {
 308                 /* Latin characters */
 309                 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  */
 326 static inline wchar_t *
 327 UniStrupr(register wchar_t *upin)
 328 {
 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  */
 344 static inline wchar_t
 345 UniTolower(register wchar_t uc)
 346 {
 347         register const struct UniCaseRange *rp;
 348
 349         if (uc < sizeof(CifsUniLowerTable)) {
 350                 /* Latin characters */
 351                 return uc + CifsUniLowerTable[uc];      /* Use base tables */
 352         } else {
 353                 rp = CifsUniLowerRange; /* Use range tables */
 354                 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  */
 368 static inline wchar_t *
 369 UniStrlwr(register wchar_t *upin)
 370 {
 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
 382
 383 #endif /* _CIFS_UNICODE_H */