source/include/charset.h

   1 /*
   2    Unix SMB/CIFS implementation.
   3    charset defines
   4    Copyright (C) Andrew Tridgell 2001
   5    Copyright (C) Jelmer Vernooij 2002
   6
   7    This program is free software; you can redistribute it and/or modify
   8    it under the terms of the GNU General Public License as published by
   9    the Free Software Foundation; either version 3 of the License, or
  10    (at your option) any later version.
  11
  12    This program is distributed in the hope that it will be useful,
  13    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15    GNU General Public License for more details.
  16
  17    You should have received a copy of the GNU General Public License
  18    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  19 */
  20
  21 /* this defines the charset types used in samba */
  22 typedef enum {CH_UTF16LE=0, CH_UTF16=0, CH_UNIX=1, CH_DISPLAY=2, CH_DOS=3, CH_UTF8=4, CH_UTF16BE=5} charset_t;
  23
  24 #define NUM_CHARSETS 6
  25
  26 /*
  27  *   for each charset we have a function that pushes from that charset to a ucs2
  28  *   buffer, and a function that pulls from ucs2 buffer to that  charset.
  29  *     */
  30
  31 struct charset_functions {
  32         const char *name;
  33         size_t (*pull)(void *, const char **inbuf, size_t *inbytesleft,
  34                                    char **outbuf, size_t *outbytesleft);
  35         size_t (*push)(void *, const char **inbuf, size_t *inbytesleft,
  36                                    char **outbuf, size_t *outbytesleft);
  37         struct charset_functions *prev, *next;
  38 };
  39
  40 /*
  41  * This is auxiliary struct used by source/script/gen-8-bit-gap.sh script
  42  * during generation of an encoding table for charset module
  43  *     */
  44
  45 struct charset_gap_table {
  46   uint16 start;
  47   uint16 end;
  48   int32 idx;
  49 };
  50
  51 /*
  52  *   Define stub for charset module which implements 8-bit encoding with gaps.
  53  *   Encoding tables for such module should be produced from glibc's CHARMAPs
  54  *   using script source/script/gen-8bit-gap.sh
  55  *   CHARSETNAME is CAPITALIZED charset name
  56  *
  57  *     */
  58 #define SMB_GENERATE_CHARSET_MODULE_8_BIT_GAP(CHARSETNAME)                                      \
  59 static size_t CHARSETNAME ## _push(void *cd, const char **inbuf, size_t *inbytesleft,                   \
  60                          char **outbuf, size_t *outbytesleft)                                   \
  61 {                                                                                               \
  62         while (*inbytesleft >= 2 && *outbytesleft >= 1) {                                       \
  63                 int i;                                                                          \
  64                 int done = 0;                                                                   \
  65                                                                                                 \
  66                 uint16 ch = SVAL(*inbuf,0);                                                     \
  67                                                                                                 \
  68                 for (i=0; from_idx[i].start != 0xffff; i++) {                                   \
  69                         if ((from_idx[i].start <= ch) && (from_idx[i].end >= ch)) {             \
  70                                 ((unsigned char*)(*outbuf))[0] = from_ucs2[from_idx[i].idx+ch]; \
  71                                 (*inbytesleft) -= 2;                                            \
  72                                 (*outbytesleft) -= 1;                                           \
  73                                 (*inbuf)  += 2;                                                 \
  74                                 (*outbuf) += 1;                                                 \
  75                                 done = 1;                                                       \
  76                                 break;                                                          \
  77                         }                                                                       \
  78                 }                                                                               \
  79                 if (!done) {                                                                    \
  80                         errno = EINVAL;                                                         \
  81                         return -1;                                                              \
  82                 }                                                                               \
  83                                                                                                 \
  84         }                                                                                       \
  85                                                                                                 \
  86         if (*inbytesleft == 1) {                                                                \
  87                 errno = EINVAL;                                                                 \
  88                 return -1;                                                                      \
  89         }                                                                                       \
  90                                                                                                 \
  91         if (*inbytesleft > 1) {                                                                 \
  92                 errno = E2BIG;                                                                  \
  93                 return -1;                                                                      \
  94         }                                                                                       \
  95                                                                                                 \
  96         return 0;                                                                               \
  97 }                                                                                               \
  98                                                                                                 \
  99 static size_t CHARSETNAME ## _pull(void *cd, const char **inbuf, size_t *inbytesleft,                           \
 100                          char **outbuf, size_t *outbytesleft)                                   \
 101 {                                                                                               \
 102         while (*inbytesleft >= 1 && *outbytesleft >= 2) {                                       \
 103                 *(uint16*)(*outbuf) = to_ucs2[((unsigned char*)(*inbuf))[0]];                   \
 104                 (*inbytesleft)  -= 1;                                                           \
 105                 (*outbytesleft) -= 2;                                                           \
 106                 (*inbuf)  += 1;                                                                 \
 107                 (*outbuf) += 2;                                                                 \
 108         }                                                                                       \
 109                                                                                                 \
 110         if (*inbytesleft > 0) {                                                                 \
 111                 errno = E2BIG;                                                                  \
 112                 return -1;                                                                      \
 113         }                                                                                       \
 114                                                                                                 \
 115         return 0;                                                                               \
 116 }                                                                                               \
 117                                                                                                 \
 118 struct charset_functions CHARSETNAME ## _functions =                                            \
 119                 {#CHARSETNAME, CHARSETNAME ## _pull, CHARSETNAME ## _push};                     \
 120                                                                                                 \
 121 NTSTATUS charset_ ## CHARSETNAME ## _init(void);                                                        \
 122 NTSTATUS charset_ ## CHARSETNAME ## _init(void)                                                 \
 123 {                                                                                               \
 124         return smb_register_charset(& CHARSETNAME ## _functions);                               \
 125 }                                                                                               \
 126