| 1 |
/* wptUTF8.cpp - UTF8 conversation |
| 2 |
* Copyright (C) 1994, 1998-2001 Free Software Foundation, Inc. |
| 3 |
* Copyright (C) 2002, 2004, 2005, 2006 Timo Schulz |
| 4 |
* |
| 5 |
* This file is part of WinPT. |
| 6 |
* |
| 7 |
* WinPT 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 |
* WinPT 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 WinPT; if not, write to the Free Software Foundation, |
| 19 |
* Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA |
| 20 |
*/ |
| 21 |
|
| 22 |
#ifdef HAVE_CONFIG_H |
| 23 |
#include <config.h> |
| 24 |
#endif |
| 25 |
|
| 26 |
#include <windows.h> |
| 27 |
#include <stdlib.h> |
| 28 |
#include <stdio.h> |
| 29 |
#include <string.h> |
| 30 |
#include <ctype.h> |
| 31 |
|
| 32 |
#include "wptTypes.h" |
| 33 |
#include "wptErrors.h" |
| 34 |
|
| 35 |
|
| 36 |
/* convert latin1 string @string into utf8. */ |
| 37 |
char * |
| 38 |
native_to_utf8( const char *string ) |
| 39 |
{ |
| 40 |
const byte *s; |
| 41 |
char *buffer; |
| 42 |
byte *p; |
| 43 |
size_t length=0; |
| 44 |
|
| 45 |
for (s=(byte*)string; *s; s++) { |
| 46 |
length++; |
| 47 |
if (*s & 0x80) |
| 48 |
length++; |
| 49 |
} |
| 50 |
buffer = (char*)malloc (length + 1); |
| 51 |
for (p = (byte*)buffer, s=(byte*)string; *s; s++) { |
| 52 |
if (*s & 0x80) { |
| 53 |
*p++ = 0xc0 | ((*s >> 6) & 3); |
| 54 |
*p++ = 0x80 | ( *s & 0x3f ); |
| 55 |
} |
| 56 |
else |
| 57 |
*p++ = *s; |
| 58 |
} |
| 59 |
*p = 0; |
| 60 |
return buffer; |
| 61 |
} |
| 62 |
|
| 63 |
|
| 64 |
|
| 65 |
/* Convert utf8 string @str to native CP. */ |
| 66 |
static char* |
| 67 |
utf8_to_native (const char *string) |
| 68 |
{ |
| 69 |
wchar_t *result; |
| 70 |
char *native; |
| 71 |
int n; |
| 72 |
|
| 73 |
/* Convert utf8 to unicode. */ |
| 74 |
n = MultiByteToWideChar (CP_UTF8, 0, string, -1, NULL, 0); |
| 75 |
if (n < 0) |
| 76 |
return NULL; |
| 77 |
|
| 78 |
result = (wchar_t*)malloc ((n+1) * sizeof *result); |
| 79 |
if (!result) |
| 80 |
BUG (0); |
| 81 |
|
| 82 |
n = MultiByteToWideChar (CP_UTF8, 0, string, -1, result, n); |
| 83 |
if (n < 0) { |
| 84 |
free (result); |
| 85 |
return NULL; |
| 86 |
} |
| 87 |
|
| 88 |
/* Convert wide char into native char. */ |
| 89 |
/* |
| 90 |
n = WideCharToMultiByte (GetACP (), 0, result, -1, NULL, 0, NULL, NULL); |
| 91 |
if (n < 0) |
| 92 |
return NULL; |
| 93 |
*/ |
| 94 |
n = wcstombs (NULL, result, wcslen (result)); |
| 95 |
if (n < 0) |
| 96 |
return NULL; |
| 97 |
|
| 98 |
native = (char*)malloc (n+1); |
| 99 |
if (!native) |
| 100 |
BUG (0); |
| 101 |
|
| 102 |
/* |
| 103 |
n = WideCharToMultiByte (CP_ACP, 0, string, -1, result, n, NULL, NULL); |
| 104 |
if (n < 0) { |
| 105 |
free (result); |
| 106 |
return NULL; |
| 107 |
} |
| 108 |
*/ |
| 109 |
n = wcstombs (native, result, -1); |
| 110 |
if (n < 0) { |
| 111 |
free (result); |
| 112 |
return NULL; |
| 113 |
} |
| 114 |
|
| 115 |
return native; |
| 116 |
} |
| 117 |
|
| 118 |
/* CP850 -> CP1251 */ |
| 119 |
static void |
| 120 |
conv_charset (byte *string, size_t size, int what) |
| 121 |
{ |
| 122 |
size_t i; |
| 123 |
|
| 124 |
if( what == 0 ) { |
| 125 |
for( i = 0; i < size; i++, string++ ) { |
| 126 |
switch( *string ) { |
| 127 |
case 0xa0: *string = 0xff; break; /* nobreakspace */ |
| 128 |
case 0xa1: *string = 0xad; break; /* exclamdown */ |
| 129 |
case 0xa2: *string = 0xbd; break; /* cent */ |
| 130 |
case 0xa3: *string = 0x9c; break; /* sterling */ |
| 131 |
case 0xa4: *string = 0xcf; break; /* currency */ |
| 132 |
case 0xa5: *string = 0xbe; break; /* yen */ |
| 133 |
case 0xa6: *string = 0xdd; break; /* brokenbar */ |
| 134 |
case 0xa7: *string = 0xf5; break; /* section */ |
| 135 |
case 0xa8: *string = 0xf9; break; /* diaeresis */ |
| 136 |
case 0xa9: *string = 0xb8; break; /* copyright */ |
| 137 |
case 0xaa: *string = 0xa6; break; /* ordfeminine */ |
| 138 |
case 0xab: *string = 0xae; break; /* guillemotleft */ |
| 139 |
case 0xac: *string = 0xaa; break; /* notsign */ |
| 140 |
case 0xad: *string = 0xf0; break; /* hyphen */ |
| 141 |
case 0xae: *string = 0xa9; break; /* registered */ |
| 142 |
case 0xaf: *string = 0xee; break; /* macron */ |
| 143 |
case 0xb0: *string = 0xf8; break; /* degree */ |
| 144 |
case 0xb1: *string = 0xf1; break; /* plusminus */ |
| 145 |
case 0xb2: *string = 0xfd; break; /* twosuperior */ |
| 146 |
case 0xb3: *string = 0xfc; break; /* threesuperior */ |
| 147 |
case 0xb4: *string = 0xef; break; /* acute */ |
| 148 |
case 0xb5: *string = 0xe6; break; /* mu */ |
| 149 |
case 0xb6: *string = 0xf4; break; /* paragraph */ |
| 150 |
case 0xb7: *string = 0xfa; break; /* periodcentered */ |
| 151 |
case 0xb8: *string = 0xf7; break; /* cedilla */ |
| 152 |
case 0xb9: *string = 0xfb; break; /* onesuperior */ |
| 153 |
case 0xba: *string = 0xa7; break; /* masculine */ |
| 154 |
case 0xbb: *string = 0xaf; break; /* guillemotright */ |
| 155 |
case 0xbc: *string = 0xac; break; /* onequarter */ |
| 156 |
case 0xbd: *string = 0xab; break; /* onehalf */ |
| 157 |
case 0xbe: *string = 0xf3; break; /* threequarters */ |
| 158 |
case 0xbf: *string = 0xa8; break; /* questiondown */ |
| 159 |
case 0xc0: *string = 0xb7; break; /* Agrave */ |
| 160 |
case 0xc1: *string = 0xb5; break; /* Aacute */ |
| 161 |
case 0xc2: *string = 0xb6; break; /* Acircumflex */ |
| 162 |
case 0xc3: *string = 0xc7; break; /* Atilde */ |
| 163 |
case 0xc4: *string = 0x8e; break; /* Adiaeresis */ |
| 164 |
case 0xc5: *string = 0x8f; break; /* Aring */ |
| 165 |
case 0xc6: *string = 0x92; break; /* AE */ |
| 166 |
case 0xc7: *string = 0x80; break; /* Ccedilla */ |
| 167 |
case 0xc8: *string = 0xd4; break; /* Egrave */ |
| 168 |
case 0xc9: *string = 0x90; break; /* Eacute */ |
| 169 |
case 0xca: *string = 0xd2; break; /* Ecircumflex */ |
| 170 |
case 0xcb: *string = 0xd3; break; /* Ediaeresis */ |
| 171 |
case 0xcc: *string = 0xde; break; /* Igrave */ |
| 172 |
case 0xcd: *string = 0xd6; break; /* Iacute */ |
| 173 |
case 0xce: *string = 0xd7; break; /* Icircumflex */ |
| 174 |
case 0xcf: *string = 0xd8; break; /* Idiaeresis */ |
| 175 |
case 0xd0: *string = 0xd1; break; /* Eth */ |
| 176 |
case 0xd1: *string = 0xa5; break; /* Ntilde */ |
| 177 |
case 0xd2: *string = 0xe3; break; /* Ograve */ |
| 178 |
case 0xd3: *string = 0xe0; break; /* Oacute */ |
| 179 |
case 0xd4: *string = 0xe2; break; /* Ocircumflex */ |
| 180 |
case 0xd5: *string = 0xe5; break; /* Otilde */ |
| 181 |
case 0xd6: *string = 0x99; break; /* Odiaeresis */ |
| 182 |
case 0xd7: *string = 0x9e; break; /* multiply */ |
| 183 |
case 0xd8: *string = 0x9d; break; /* Ooblique */ |
| 184 |
case 0xd9: *string = 0xeb; break; /* Ugrave */ |
| 185 |
case 0xda: *string = 0xe9; break; /* Uacute */ |
| 186 |
case 0xdb: *string = 0xea; break; /* Ucircumflex */ |
| 187 |
case 0xdc: *string = 0x9a; break; /* Udiaeresis */ |
| 188 |
case 0xdd: *string = 0xed; break; /* Yacute */ |
| 189 |
case 0xde: *string = 0xe8; break; /* Thorn */ |
| 190 |
case 0xdf: *string = 0xe1; break; /* ssharp */ |
| 191 |
case 0xe0: *string = 0x85; break; /* agrave */ |
| 192 |
case 0xe1: *string = 0xa0; break; /* aacute */ |
| 193 |
case 0xe2: *string = 0x83; break; /* acircumflex */ |
| 194 |
case 0xe3: *string = 0xc6; break; /* atilde */ |
| 195 |
case 0xe4: *string = 0x84; break; /* adiaeresis */ |
| 196 |
case 0xe5: *string = 0x86; break; /* aring */ |
| 197 |
case 0xe6: *string = 0x91; break; /* ae */ |
| 198 |
case 0xe7: *string = 0x87; break; /* ccedilla */ |
| 199 |
case 0xe8: *string = 0x8a; break; /* egrave */ |
| 200 |
case 0xe9: *string = 0x82; break; /* eacute */ |
| 201 |
case 0xea: *string = 0x88; break; /* ecircumflex */ |
| 202 |
case 0xeb: *string = 0x89; break; /* ediaeresis */ |
| 203 |
case 0xec: *string = 0x8d; break; /* igrave */ |
| 204 |
case 0xed: *string = 0xa1; break; /* iacute */ |
| 205 |
case 0xee: *string = 0x8c; break; /* icircumflex */ |
| 206 |
case 0xef: *string = 0x8b; break; /* idiaeresis */ |
| 207 |
case 0xf0: *string = 0xd0; break; /* eth */ |
| 208 |
case 0xf1: *string = 0xa4; break; /* ntilde */ |
| 209 |
case 0xf2: *string = 0x95; break; /* ograve */ |
| 210 |
case 0xf3: *string = 0xa2; break; /* oacute */ |
| 211 |
case 0xf4: *string = 0x93; break; /* ocircumflex */ |
| 212 |
case 0xf5: *string = 0xe4; break; /* otilde */ |
| 213 |
case 0xf6: *string = 0x94; break; /* odiaeresis */ |
| 214 |
case 0xf7: *string = 0xf6; break; /* division */ |
| 215 |
case 0xf8: *string = 0x9b; break; /* oslash */ |
| 216 |
case 0xf9: *string = 0x97; break; /* ugrave */ |
| 217 |
case 0xfa: *string = 0xa3; break; /* uacute */ |
| 218 |
case 0xfb: *string = 0x96; break; /* ucircumflex */ |
| 219 |
case 0xfc: *string = 0x81; break; /* udiaeresis */ |
| 220 |
case 0xfd: *string = 0xec; break; /* yacute */ |
| 221 |
case 0xfe: *string = 0xe7; break; /* thorn */ |
| 222 |
case 0xff: *string = 0x98; break; /* ydiaeresis */ |
| 223 |
default : break; |
| 224 |
} |
| 225 |
} |
| 226 |
} |
| 227 |
else { |
| 228 |
for( i = 0; i < size; i++, string++ ) { |
| 229 |
switch( *string ) { |
| 230 |
case 0xff: *string = 0xa0; break; |
| 231 |
case 0xad: *string = 0xa1; break; |
| 232 |
case 0xbd: *string = 0xa2; break; |
| 233 |
case 0x9c: *string = 0xa3; break; |
| 234 |
case 0xcf: *string = 0xa4; break; |
| 235 |
case 0xbe: *string = 0xa5; break; |
| 236 |
case 0xdd: *string = 0xa6; break; |
| 237 |
case 0xf5: *string = 0xa7; break; |
| 238 |
case 0xf9: *string = 0xa8; break; |
| 239 |
case 0xb8: *string = 0xa9; break; |
| 240 |
case 0xa6: *string = 0xaa; break; |
| 241 |
case 0xae: *string = 0xab; break; |
| 242 |
case 0xaa: *string = 0xac; break; |
| 243 |
case 0xf0: *string = 0xad; break; |
| 244 |
case 0xa9: *string = 0xae; break; |
| 245 |
case 0xee: *string = 0xaf; break; |
| 246 |
case 0xf8: *string = 0xb0; break; |
| 247 |
case 0xf1: *string = 0xb1; break; |
| 248 |
case 0xfd: *string = 0xb2; break; |
| 249 |
case 0xfc: *string = 0xb3; break; |
| 250 |
case 0xef: *string = 0xb4; break; |
| 251 |
case 0xe6: *string = 0xb5; break; |
| 252 |
case 0xf4: *string = 0xb6; break; |
| 253 |
case 0xfa: *string = 0xb7; break; |
| 254 |
case 0xf7: *string = 0xb8; break; |
| 255 |
case 0xfb: *string = 0xb9; break; |
| 256 |
case 0xa7: *string = 0xba; break; |
| 257 |
case 0xaf: *string = 0xbb; break; |
| 258 |
case 0xac: *string = 0xbc; break; |
| 259 |
case 0xab: *string = 0xbd; break; |
| 260 |
case 0xf3: *string = 0xbe; break; |
| 261 |
case 0xa8: *string = 0xbf; break; |
| 262 |
case 0xb7: *string = 0xc0; break; |
| 263 |
case 0xb5: *string = 0xc1; break; |
| 264 |
case 0xb6: *string = 0xc2; break; |
| 265 |
case 0xc7: *string = 0xc3; break; |
| 266 |
case 0x8e: *string = 0xc4; break; |
| 267 |
case 0x8f: *string = 0xc5; break; |
| 268 |
case 0x92: *string = 0xc6; break; |
| 269 |
case 0x80: *string = 0xc7; break; |
| 270 |
case 0xd4: *string = 0xc8; break; |
| 271 |
case 0x90: *string = 0xc9; break; |
| 272 |
case 0xd2: *string = 0xca; break; |
| 273 |
case 0xd3: *string = 0xcb; break; |
| 274 |
case 0xde: *string = 0xcc; break; |
| 275 |
case 0xd6: *string = 0xcd; break; |
| 276 |
case 0xd7: *string = 0xce; break; |
| 277 |
case 0xd8: *string = 0xcf; break; |
| 278 |
case 0xd1: *string = 0xd0; break; |
| 279 |
case 0xa5: *string = 0xd1; break; |
| 280 |
case 0xe3: *string = 0xd2; break; |
| 281 |
case 0xe0: *string = 0xd3; break; |
| 282 |
case 0xe2: *string = 0xd4; break; |
| 283 |
case 0xe5: *string = 0xd5; break; |
| 284 |
case 0x99: *string = 0xd6; break; |
| 285 |
case 0x9e: *string = 0xd7; break; |
| 286 |
case 0x9d: *string = 0xd8; break; |
| 287 |
case 0xeb: *string = 0xd9; break; |
| 288 |
case 0xe9: *string = 0xda; break; |
| 289 |
case 0xea: *string = 0xdb; break; |
| 290 |
case 0x9a: *string = 0xdc; break; |
| 291 |
case 0xed: *string = 0xdd; break; |
| 292 |
case 0xe8: *string = 0xde; break; |
| 293 |
case 0xe1: *string = 0xdf; break; |
| 294 |
case 0x85: *string = 0xe0; break; |
| 295 |
case 0xa0: *string = 0xe1; break; |
| 296 |
case 0x83: *string = 0xe2; break; |
| 297 |
case 0xc6: *string = 0xe3; break; |
| 298 |
case 0x84: *string = 0xe4; break; |
| 299 |
case 0x86: *string = 0xe5; break; |
| 300 |
case 0x91: *string = 0xe6; break; |
| 301 |
case 0x87: *string = 0xe7; break; |
| 302 |
case 0x8a: *string = 0xe8; break; |
| 303 |
case 0x82: *string = 0xe9; break; |
| 304 |
case 0x88: *string = 0xea; break; |
| 305 |
case 0x89: *string = 0xeb; break; |
| 306 |
case 0x8d: *string = 0xec; break; |
| 307 |
case 0xa1: *string = 0xed; break; |
| 308 |
case 0x8c: *string = 0xee; break; |
| 309 |
case 0x8b: *string = 0xef; break; |
| 310 |
case 0xd0: *string = 0xf0; break; |
| 311 |
case 0xa4: *string = 0xf1; break; |
| 312 |
case 0x95: *string = 0xf2; break; |
| 313 |
case 0xa2: *string = 0xf3; break; |
| 314 |
case 0x93: *string = 0xf4; break; |
| 315 |
case 0xe4: *string = 0xf5; break; |
| 316 |
case 0x94: *string = 0xf6; break; |
| 317 |
case 0xf6: *string = 0xf7; break; |
| 318 |
case 0x9b: *string = 0xf8; break; |
| 319 |
case 0x97: *string = 0xf9; break; |
| 320 |
case 0xa3: *string = 0xfa; break; |
| 321 |
case 0x96: *string = 0xfb; break; |
| 322 |
case 0x81: *string = 0xfc; break; |
| 323 |
case 0xec: *string = 0xfd; break; |
| 324 |
case 0xe7: *string = 0xfe; break; |
| 325 |
case 0x98: *string = 0xff; break; |
| 326 |
default : break; |
| 327 |
} |
| 328 |
} |
| 329 |
} |
| 330 |
} |
| 331 |
|
| 332 |
|
| 333 |
/* XXX: the conv_charset() call fails when the user-id was created |
| 334 |
with iso-8859-1 but it is assumed that CP850 (gpg console) is used. */ |
| 335 |
|
| 336 |
char* |
| 337 |
utf8_to_wincp (const char * s, size_t len) |
| 338 |
{ |
| 339 |
char *decs; |
| 340 |
decs = utf8_to_native (s); |
| 341 |
conv_charset ((byte *)decs, strlen (decs), 1); |
| 342 |
return decs; |
| 343 |
} |
| 344 |
|
| 345 |
|
| 346 |
char* |
| 347 |
wincp_to_utf8 (const char * s, size_t len) |
| 348 |
{ |
| 349 |
char * encs; |
| 350 |
conv_charset ((byte *)s, len, 0); |
| 351 |
encs = native_to_utf8 (s); |
| 352 |
return encs; |
| 353 |
} |
| 354 |
|
| 355 |
|
| 356 |
int |
| 357 |
is_8bit_string (const char * str) |
| 358 |
{ |
| 359 |
size_t i; |
| 360 |
|
| 361 |
for (i = 0; i < strlen (str); i++) { |
| 362 |
if (str[i] & 0x80) |
| 363 |
return -1; |
| 364 |
} |
| 365 |
return 0; |
| 366 |
} |
Parent Directory
| 
Revision Log