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 #ifdef CONFIG_CIFS_SMB2
  88 extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
  89                                      int *utf16_len, const struct nls_table *cp,
  90                                      int remap);
  91 #endif /* CONFIG_CIFS_SMB2 */
  92 #endif
  93
  94 /*
  95  * UniStrcat:  Concatenate the second string to the first
  96  *
  97  * Returns:
  98  *     Address of the first string
  99  */
 100 static inline wchar_t *
 101 UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
 102 {
 103         wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
 104
 105         while (*ucs1++) ;       /* To end of first string */
 106         ucs1--;                 /* Return to the null */
 107         while ((*ucs1++ = *ucs2++)) ;   /* copy string 2 over */
 108         return anchor;
 109 }
 110
 111 /*
 112  * UniStrchr:  Find a character in a string
 113  *
 114  * Returns:
 115  *     Address of first occurrence of character in string
 116  *     or NULL if the character is not in the string
 117  */
 118 static inline wchar_t *
 119 UniStrchr(const wchar_t *ucs, wchar_t uc)
 120 {
 121         while ((*ucs != uc) && *ucs)
 122                 ucs++;
 123
 124         if (*ucs == uc)
 125                 return (wchar_t *) ucs;
 126         return NULL;
 127 }
 128
 129 /*
 130  * UniStrcmp:  Compare two strings
 131  *
 132  * Returns:
 133  *     < 0:  First string is less than second
 134  *     = 0:  Strings are equal
 135  *     > 0:  First string is greater than second
 136  */
 137 static inline int
 138 UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
 139 {
 140         while ((*ucs1 == *ucs2) && *ucs1) {
 141                 ucs1++;
 142                 ucs2++;
 143         }
 144         return (int) *ucs1 - (int) *ucs2;
 145 }
 146
 147 /*
 148  * UniStrcpy:  Copy a string
 149  */
 150 static inline wchar_t *
 151 UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
 152 {
 153         wchar_t *anchor = ucs1; /* save the start of result string */
 154
 155         while ((*ucs1++ = *ucs2++)) ;
 156         return anchor;
 157 }
 158
 159 /*
 160  * UniStrlen:  Return the length of a string (in 16 bit Unicode chars not bytes)
 161  */
 162 static inline size_t
 163 UniStrlen(const wchar_t *ucs1)
 164 {
 165         int i = 0;
 166
 167         while (*ucs1++)
 168                 i++;
 169         return i;
 170 }
 171
 172 /*
 173  * UniStrnlen:  Return the length (in 16 bit Unicode chars not bytes) of a
 174  *              string (length limited)
 175  */
 176 static inline size_t
 177 UniStrnlen(const wchar_t *ucs1, int maxlen)
 178 {
 179         int i = 0;
 180
 181         while (*ucs1++) {
 182                 i++;
 183                 if (i >= maxlen)
 184                         break;
 185         }
 186         return i;
 187 }
 188
 189 /*
 190  * UniStrncat:  Concatenate length limited string
 191  */
 192 static inline wchar_t *
 193 UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 194 {
 195         wchar_t *anchor = ucs1; /* save pointer to string 1 */
 196
 197         while (*ucs1++) ;
 198         ucs1--;                 /* point to null terminator of s1 */
 199         while (n-- && (*ucs1 = *ucs2)) {        /* copy s2 after s1 */
 200                 ucs1++;
 201                 ucs2++;
 202         }
 203         *ucs1 = 0;              /* Null terminate the result */
 204         return (anchor);
 205 }
 206
 207 /*
 208  * UniStrncmp:  Compare length limited string
 209  */
 210 static inline int
 211 UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 212 {
 213         if (!n)
 214                 return 0;       /* Null strings are equal */
 215         while ((*ucs1 == *ucs2) && *ucs1 && --n) {
 216                 ucs1++;
 217                 ucs2++;
 218         }
 219         return (int) *ucs1 - (int) *ucs2;
 220 }
 221
 222 /*
 223  * UniStrncmp_le:  Compare length limited string - native to little-endian
 224  */
 225 static inline int
 226 UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 227 {
 228         if (!n)
 229                 return 0;       /* Null strings are equal */
 230         while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
 231                 ucs1++;
 232                 ucs2++;
 233         }
 234         return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
 235 }
 236
 237 /*
 238  * UniStrncpy:  Copy length limited string with pad
 239  */
 240 static inline wchar_t *
 241 UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 242 {
 243         wchar_t *anchor = ucs1;
 244
 245         while (n-- && *ucs2)    /* Copy the strings */
 246                 *ucs1++ = *ucs2++;
 247
 248         n++;
 249         while (n--)             /* Pad with nulls */
 250                 *ucs1++ = 0;
 251         return anchor;
 252 }
 253
 254 /*
 255  * UniStrncpy_le:  Copy length limited string with pad to little-endian
 256  */
 257 static inline wchar_t *
 258 UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
 259 {
 260         wchar_t *anchor = ucs1;
 261
 262         while (n-- && *ucs2)    /* Copy the strings */
 263                 *ucs1++ = __le16_to_cpu(*ucs2++);
 264
 265         n++;
 266         while (n--)             /* Pad with nulls */
 267                 *ucs1++ = 0;
 268         return anchor;
 269 }
 270
 271 /*
 272  * UniStrstr:  Find a string in a string
 273  *
 274  * Returns:
 275  *     Address of first match found
 276  *     NULL if no matching string is found
 277  */
 278 static inline wchar_t *
 279 UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
 280 {
 281         const wchar_t *anchor1 = ucs1;
 282         const wchar_t *anchor2 = ucs2;
 283
 284         while (*ucs1) {
 285                 if (*ucs1 == *ucs2) {
 286                         /* Partial match found */
 287                         ucs1++;
 288                         ucs2++;
 289                 } else {
 290                         if (!*ucs2)     /* Match found */
 291                                 return (wchar_t *) anchor1;
 292                         ucs1 = ++anchor1;       /* No match */
 293                         ucs2 = anchor2;
 294                 }
 295         }
 296
 297         if (!*ucs2)             /* Both end together */
 298                 return (wchar_t *) anchor1;     /* Match found */
 299         return NULL;            /* No match */
 300 }
 301
 302 #ifndef UNIUPR_NOUPPER
 303 /*
 304  * UniToupper:  Convert a unicode character to upper case
 305  */
 306 static inline wchar_t
 307 UniToupper(register wchar_t uc)
 308 {
 309         register const struct UniCaseRange *rp;
 310
 311         if (uc < sizeof(CifsUniUpperTable)) {
 312                 /* Latin characters */
 313                 return uc + CifsUniUpperTable[uc];      /* Use base tables */
 314         } else {
 315                 rp = CifsUniUpperRange; /* Use range tables */
 316                 while (rp->start) {
 317                         if (uc < rp->start)     /* Before start of range */
 318                                 return uc;      /* Uppercase = input */
 319                         if (uc <= rp->end)      /* In range */
 320                                 return uc + rp->table[uc - rp->start];
 321                         rp++;   /* Try next range */
 322                 }
 323         }
 324         return uc;              /* Past last range */
 325 }
 326
 327 /*
 328  * UniStrupr:  Upper case a unicode string
 329  */
 330 static inline wchar_t *
 331 UniStrupr(register wchar_t *upin)
 332 {
 333         register wchar_t *up;
 334
 335         up = upin;
 336         while (*up) {           /* For all characters */
 337                 *up = UniToupper(*up);
 338                 up++;
 339         }
 340         return upin;            /* Return input pointer */
 341 }
 342 #endif                          /* UNIUPR_NOUPPER */
 343
 344 #ifndef UNIUPR_NOLOWER
 345 /*
 346  * UniTolower:  Convert a unicode character to lower case
 347  */
 348 static inline wchar_t
 349 UniTolower(register wchar_t uc)
 350 {
 351         register const struct UniCaseRange *rp;
 352
 353         if (uc < sizeof(CifsUniLowerTable)) {
 354                 /* Latin characters */
 355                 return uc + CifsUniLowerTable[uc];      /* Use base tables */
 356         } else {
 357                 rp = CifsUniLowerRange; /* Use range tables */
 358                 while (rp->start) {
 359                         if (uc < rp->start)     /* Before start of range */
 360                                 return uc;      /* Uppercase = input */
 361                         if (uc <= rp->end)      /* In range */
 362                                 return uc + rp->table[uc - rp->start];
 363                         rp++;   /* Try next range */
 364                 }
 365         }
 366         return uc;              /* Past last range */
 367 }
 368
 369 /*
 370  * UniStrlwr:  Lower case a unicode string
 371  */
 372 static inline wchar_t *
 373 UniStrlwr(register wchar_t *upin)
 374 {
 375         register wchar_t *up;
 376
 377         up = upin;
 378         while (*up) {           /* For all characters */
 379                 *up = UniTolower(*up);
 380                 up++;
 381         }
 382         return upin;            /* Return input pointer */
 383 }
 384
 385 #endif
 386
 387 #endif /* _CIFS_UNICODE_H */