source/lib/charset.c

   1 /*
   2    Unix SMB/Netbios implementation.
   3    Version 1.9.
   4    Character set handling
   5    Copyright (C) Andrew Tridgell 1992-1997
   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 2 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, write to the Free Software
  19    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  20 */
  21
  22 #define CHARSET_C
  23 #include "includes.h"
  24
  25 extern int DEBUGLEVEL;
  26
  27 /*
  28  * Codepage definitions.
  29  */
  30
  31 /* lower->upper mapping for IBM Code Page 850 - MS-DOS Latin 1 */
  32 unsigned char cp_850[][4] = {
  33 /* dec col/row oct hex  description */
  34 /* 133  08/05  205  85  a grave */
  35 /* 183  11/07  267  B7  A grave */      {0x85,0xB7,1,1},
  36 /* 160  10/00  240  A0  a acute */
  37 /* 181  11/05  265  B5  A acute */      {0xA0,0xB5,1,1},
  38 /* 131  08/03  203  83  a circumflex */
  39 /* 182  11/06  266  B6  A circumflex */ {0x83,0xB6,1,1},
  40 /* 198  12/06  306  C6  a tilde */
  41 /* 199  12/07  307  C7  A tilde */      {0xC6,0xC7,1,1},
  42 /* 132  08/04  204  84  a diaeresis */
  43 /* 142  08/14  216  8E  A diaeresis */  {0x84,0x8E,1,1},
  44 /* 134  08/06  206  86  a ring */
  45 /* 143  08/15  217  8F  A ring */       {0x86,0x8F,1,1},
  46 /* 145  09/01  221  91  ae diphthong */
  47 /* 146  09/02  222  92  AE diphthong */ {0x91,0x92,1,1},
  48 /* 135  08/07  207  87  c cedilla */
  49 /* 128  08/00  200  80  C cedilla */    {0x87,0x80,1,1},
  50 /* 138  08/10  212  8A  e grave */
  51 /* 212  13/04  324  D4  E grave */      {0x8A,0xD4,1,1},
  52 /* 130  08/02  202  82  e acute */
  53 /* 144  09/00  220  90  E acute */      {0x82,0x90,1,1},
  54 /* 136  08/08  210  88  e circumflex */
  55 /* 210  13/02  322  D2  E circumflex */ {0x88,0xD2,1,1},
  56 /* 137  08/09  211  89  e diaeresis */
  57 /* 211  13/03  323  D3  E diaeresis */  {0x89,0xD3,1,1},
  58 /* 141  08/13  215  8D  i grave */
  59 /* 222  13/14  336  DE  I grave */      {0x8D,0xDE,1,1},
  60 /* 161  10/01  241  A1  i acute */
  61 /* 214  13/06  326  D6  I acute */      {0xA1,0xD6,1,1},
  62 /* 140  08/12  214  8C  i circumflex */
  63 /* 215  13/07  327  D7  I circumflex */ {0x8C,0xD7,1,1},
  64 /* 139  08/11  213  8B  i diaeresis */
  65 /* 216  13/08  330  D8  I diaeresis */  {0x8B,0xD8,1,1},
  66 /* 208  13/00  320  D0  Icelandic eth */
  67 /* 209  13/01  321  D1  Icelandic Eth */ {0xD0,0xD1,1,1},
  68 /* 164  10/04  244  A4  n tilde */
  69 /* 165  10/05  245  A5  N tilde */      {0xA4,0xA5,1,1},
  70 /* 149  09/05  225  95  o grave */
  71 /* 227  14/03  343  E3  O grave */      {0x95,0xE3,1,1},
  72 /* 162  10/02  242  A2  o acute */
  73 /* 224  14/00  340  E0  O acute */      {0xA2,0xE0,1,1},
  74 /* 147  09/03  223  93  o circumflex */
  75 /* 226  14/02  342  E2  O circumflex */ {0x93,0xE2,1,1},
  76 /* 228  14/04  344  E4  o tilde */
  77 /* 229  14/05  345  E5  O tilde */      {0xE4,0xE5,1,1},
  78 /* 148  09/04  224  94  o diaeresis */
  79 /* 153  09/09  231  99  O diaeresis */  {0x94,0x99,1,1},
  80 /* 155  09/11  233  9B  o slash */
  81 /* 157  09/13  235  9D  O slash */      {0x9B,0x9D,1,1},
  82 /* 151  09/07  227  97  u grave */
  83 /* 235  14/11  353  EB  U grave */      {0x97,0xEB,1,1},
  84 /* 163  10/03  243  A3  u acute */
  85 /* 233  14/09  351  E9  U acute */      {0xA3,0xE9,1,1},
  86 /* 150  09/06  226  96  u circumflex */
  87 /* 234  14/10  352  EA  U circumflex */ {0x96,0xEA,1,1},
  88 /* 129  08/01  201  81  u diaeresis */
  89 /* 154  09/10  232  9A  U diaeresis */  {0x81,0x9A,1,1},
  90 /* 236  14/12  354  EC  y acute */
  91 /* 237  14/13  355  ED  Y acute */      {0xEC,0xED,1,1},
  92 /* 231  14/07  347  E7  Icelandic thorn */
  93 /* 232  14/08  350  E8  Icelandic Thorn */ {0xE7,0xE8,1,1},
  94
  95   {0x9C,0,0,0},     /* Pound        */
  96   {0,0,0,0}
  97 };
  98
  99 /* lower->upper mapping for IBM Code Page 437 - MS-DOS Latin US */
 100 unsigned char cp_437[][4] = {
 101 /* 135  08/07  207  87  c cedilla */
 102 /* 128  08/00  200  80  C cedilla */    {0x87,0x80,1,1},
 103 /* 129  08/01  201  81  u diaeresis */
 104 /* 154  09/10  232  9A  U diaeresis */  {0x81,0x9A,1,1},
 105 /* 130  08/02  202  82  e acute */
 106 /* 144  09/00  220  90  E acute */      {0x82,0x90,1,1},
 107 /* 131  08/03  203  83  a circumflex */ {0x83,0x41,1,0},
 108 /* 132  08/04  204  84  a diaeresis */
 109 /* 142  08/14  216  8E  A diaeresis */  {0x84,0x8E,1,1},
 110 /* 133  08/05  205  85  a grave */      {0x85,0x41,1,0},
 111 /* 134  08/06  206  86  a ring */       {0x86,0x8F,1,1},
 112 /* 136  08/08  210  88  e circumflex */ {0x88,0x45,1,0},
 113 /* 137  08/09  211  89  e diaeresis */  {0x89,0x45,1,0},
 114 /* 138  08/10  212  8A  e grave */      {0x8A,0x45,1,0},
 115 /* 139  08/11  213  8B  i diaeresis */  {0x8B,0x49,1,0},
 116 /* 140  08/12  214  8C  i circumflex */ {0x8C,0x49,1,0},
 117 /* 141  08/13  215  8D  i grave */      {0x8D,0x49,1,0},
 118 /* 145  09/01  221  91  ae diphthong */
 119 /* 146  09/02  222  92  AE diphthong */ {0x91,0x92,1,1},
 120 /* 147  09/03  223  93  o circumflex */ {0x93,0x4F,1,0},
 121 /* 148  09/04  224  94  o diaeresis */
 122 /* 153  09/09  231  99  O diaeresis */  {0x94,0x99,1,1},
 123 /* 149  09/05  225  95  o grave */      {0x95,0x4F,1,0},
 124 /* 150  09/06  226  96  u circumflex */ {0x96,0x55,1,0},
 125 /* 151  09/07  227  97  u grave */      {0x97,0x55,1,0},
 126 /* 152  ??/??  201  98  u diaeresis */
 127   {0x9B,0,0,0},     /* Cent         */
 128   {0x9C,0,0,0},     /* Pound        */
 129   {0x9D,0,0,0},     /* Yen          */
 130 /* 160  10/00  240  A0  a acute */      {0xA0,0x41,1,0},
 131 /* 161  10/01  241  A1  i acute */      {0xA1,0x49,1,0},
 132 /* 162  10/02  242  A2  o acute */      {0xA2,0x4F,1,0},
 133 /* 163  10/03  243  A3  u acute */      {0xA3,0x55,1,0},
 134 /* 164  10/04  244  A4  n tilde */
 135 /* 165  10/05  245  A5  N tilde */      {0xA4,0xA5,1,1},
 136 /* Punctuation... */
 137   {0xA8,0,0,0},
 138   {0xAD,0,0,0},
 139   {0xAE,0,0,0},
 140   {0xAF,0,0,0},
 141 /* Greek character set */
 142   {0xE0,0,0,0},
 143   {0xE1,0,0,0},
 144   {0xE2,0,0,0},
 145   {0xE3,0,0,0},
 146   {0xE4,0,0,0},
 147   {0xE5,0,0,0},
 148   {0xE6,0,0,0},
 149   {0xE7,0,0,0},
 150   {0xE8,0,0,0},
 151   {0xE9,0,0,0},
 152   {0xEA,0,0,0},
 153   {0xEB,0,0,0},
 154   {0xEC,0,0,0},
 155   {0xED,0,0,0},
 156   {0xEE,0,0,0},
 157   {0xEF,0,0,0},
 158   {0,0,0,0}
 159 };
 160
 161 char xx_dos_char_map[256];
 162 char xx_upper_char_map[256];
 163 char xx_lower_char_map[256];
 164
 165 char *dos_char_map = xx_dos_char_map;
 166 char *upper_char_map = xx_upper_char_map;
 167 char *lower_char_map = xx_lower_char_map;
 168
 169 /*
 170  * This code has been extended to deal with ascynchronous mappings
 171  * like MS-DOS Latin US (Code page 437) where things like :
 172  * a acute are capitalized to 'A', but the reverse mapping
 173  * must not hold true. This allows the filename case insensitive
 174  * matching in do_match() to work, as the DOS/Win95/NT client
 175  * uses 'A' as a mask to match against characters like a acute.
 176  * This is the meaning behind the parameters that allow a
 177  * mapping from lower to upper, but not upper to lower.
 178  */
 179
 180 static void add_dos_char(int lower, BOOL map_lower_to_upper,
 181                          int upper, BOOL map_upper_to_lower)
 182 {
 183   lower &= 0xff;
 184   upper &= 0xff;
 185   DEBUG(6,("Adding chars 0x%x 0x%x (l->u = %s) (u->l = %s)\n",lower,upper,
 186          map_lower_to_upper ? "True" : "False",
 187          map_upper_to_lower ? "True" : "False"));
 188   if (lower) dos_char_map[lower] = 1;
 189   if (upper) dos_char_map[upper] = 1;
 190   if (lower && upper) {
 191     if(map_upper_to_lower)
 192       lower_char_map[upper] = (char)lower;
 193     if(map_lower_to_upper)
 194       upper_char_map[lower] = (char)upper;
 195   }
 196 }
 197
 198 /****************************************************************************
 199 initialise the charset arrays
 200 ****************************************************************************/
 201 void charset_initialise(int client_codepage)
 202 {
 203   int i;
 204   unsigned char (*cp)[4];
 205
 206 #ifdef LC_ALL
 207   /* include <locale.h> in includes.h if available for OS                  */
 208   /* we take only standard 7-bit ASCII definitions from ctype              */
 209   setlocale(LC_ALL,"C");
 210 #endif
 211
 212   for (i= 0;i<=255;i++) {
 213     dos_char_map[i] = 0;
 214   }
 215
 216   for (i=0;i<=127;i++) {
 217     if (isalnum((char)i) || strchr("._^$~!#%&-{}()@'`",(char)i))
 218       add_dos_char(i,0,False,False);
 219   }
 220
 221   for (i=0; i<=255; i++) {
 222     char c = (char)i;
 223     upper_char_map[i] = lower_char_map[i] = c;
 224     if (isupper(c)) lower_char_map[i] = tolower(c);
 225     if (islower(c)) upper_char_map[i] = toupper(c);
 226   }
 227
 228  if(client_codepage != -1)
 229    DEBUG(6,("charset_initialise: client code page = %d\n", client_codepage));
 230
 231   /*
 232    * Known client codepages - these can be added to.
 233    */
 234   switch(client_codepage)
 235   {
 236     case 850:
 237       cp = cp_850;
 238       break;
 239     case 437:
 240       cp = cp_437;
 241       break;
 242     case -1: /* pre-initialize call so that toupper/tolower work
 243                 before smb.conf is read. */
 244       cp = NULL;
 245       break;
 246     default:
 247       /* Default charset - currently 850 */
 248       DEBUG(6,("charset_initialise: Using default client codepage %d\n", 850));
 249       cp = cp_850;
 250       break;
 251
 252   }
 253
 254   if(cp)
 255   {
 256     for(i = 0; (cp[i][0] != '\0') && (cp[i][1] != '\0'); i++)
 257       add_dos_char(cp[i][0], (BOOL)cp[i][2], cp[i][1], (BOOL)cp[i][3]);
 258   }
 259 }
 260
 261 /*******************************************************************
 262 add characters depending on a string passed by the user
 263 ********************************************************************/
 264 void add_char_string(char *s)
 265 {
 266   char *extra_chars = (char *)strdup(s);
 267   char *t;
 268   if (!extra_chars) return;
 269
 270   for (t=strtok(extra_chars," \t\r\n"); t; t=strtok(NULL," \t\r\n")) {
 271     char c1=0,c2=0;
 272     int i1=0,i2=0;
 273     if (isdigit(*t) || (*t)=='-') {
 274       sscanf(t,"%i:%i",&i1,&i2);
 275       add_dos_char(i1,True,i2,True);
 276     } else {
 277       sscanf(t,"%c:%c",&c1,&c2);
 278       add_dos_char(c1,True,c2, True);
 279     }
 280   }
 281
 282   free(extra_chars);
 283 }