| 1 |
/* wptUTF8.cpp - UTF8 conversation |
| 2 |
* Copyright (C) 1994, 1998-2001 Free Software Foundation, Inc. |
| 3 |
* Copyright (C) 2002, 2004 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 |
#include <windows.h> |
| 23 |
#include <stdlib.h> |
| 24 |
#include <stdio.h> |
| 25 |
#include <string.h> |
| 26 |
#include <ctype.h> |
| 27 |
|
| 28 |
#include "wptTypes.h" |
| 29 |
#include "wptErrors.h" |
| 30 |
|
| 31 |
static u16 koi8_unicode[128] = { |
| 32 |
0x2500,0x2502,0x250c,0x2510,0x2514,0x2518,0x251c,0x2524, |
| 33 |
0x252c,0x2534,0x253c,0x2580,0x2584,0x2588,0x258c,0x2590, |
| 34 |
0x2591,0x2592,0x2593,0x2320,0x25a0,0x2219,0x221a,0x2248, |
| 35 |
0x2264,0x2265,0x00a0,0x2321,0x00b0,0x00b2,0x00b7,0x00f7, |
| 36 |
0x2550,0x2551,0x2552,0x0451,0x2553,0x2554,0x2555,0x2556, |
| 37 |
0x2557,0x2558,0x2559,0x255a,0x255b,0x255c,0x255d,0x255e, |
| 38 |
0x255f,0x2560,0x2561,0x0401,0x2562,0x2563,0x2564,0x2565, |
| 39 |
0x2566,0x2567,0x2568,0x2569,0x256a,0x256b,0x256c,0x00a9, |
| 40 |
0x044e,0x0430,0x0431,0x0446,0x0434,0x0435,0x0444,0x0433, |
| 41 |
0x0445,0x0438,0x0439,0x043a,0x043b,0x043c,0x043d,0x043e, |
| 42 |
0x043f,0x044f,0x0440,0x0441,0x0442,0x0443,0x0436,0x0432, |
| 43 |
0x044c,0x044b,0x0437,0x0448,0x044d,0x0449,0x0447,0x044a, |
| 44 |
0x042e,0x0410,0x0411,0x0426,0x0414,0x0415,0x0424,0x0413, |
| 45 |
0x0425,0x0418,0x0419,0x041a,0x041b,0x041c,0x041d,0x041e, |
| 46 |
0x041f,0x042f,0x0420,0x0421,0x0422,0x0423,0x0416,0x0412, |
| 47 |
0x042c,0x042b,0x0417,0x0428,0x042d,0x0429,0x0427,0x042a |
| 48 |
}; |
| 49 |
|
| 50 |
static u16 latin2_unicode[128] = { |
| 51 |
0x0080,0x0081,0x0082,0x0083,0x0084,0x0085,0x0086,0x0087, |
| 52 |
0x0088,0x0089,0x008A,0x008B,0x008C,0x008D,0x008E,0x008F, |
| 53 |
0x0090,0x0091,0x0092,0x0093,0x0094,0x0095,0x0096,0x0097, |
| 54 |
0x0098,0x0099,0x009A,0x009B,0x009C,0x009D,0x009E,0x009F, |
| 55 |
0x00A0,0x0104,0x02D8,0x0141,0x00A4,0x013D,0x015A,0x00A7, |
| 56 |
0x00A8,0x0160,0x015E,0x0164,0x0179,0x00AD,0x017D,0x017B, |
| 57 |
0x00B0,0x0105,0x02DB,0x0142,0x00B4,0x013E,0x015B,0x02C7, |
| 58 |
0x00B8,0x0161,0x015F,0x0165,0x017A,0x02DD,0x017E,0x017C, |
| 59 |
0x0154,0x00C1,0x00C2,0x0102,0x00C4,0x0139,0x0106,0x00C7, |
| 60 |
0x010C,0x00C9,0x0118,0x00CB,0x011A,0x00CD,0x00CE,0x010E, |
| 61 |
0x0110,0x0143,0x0147,0x00D3,0x00D4,0x0150,0x00D6,0x00D7, |
| 62 |
0x0158,0x016E,0x00DA,0x0170,0x00DC,0x00DD,0x0162,0x00DF, |
| 63 |
0x0155,0x00E1,0x00E2,0x0103,0x00E4,0x013A,0x0107,0x00E7, |
| 64 |
0x010D,0x00E9,0x0119,0x00EB,0x011B,0x00ED,0x00EE,0x010F, |
| 65 |
0x0111,0x0144,0x0148,0x00F3,0x00F4,0x0151,0x00F6,0x00F7, |
| 66 |
0x0159,0x016F,0x00FA,0x0171,0x00FC,0x00FD,0x0163,0x02D9 |
| 67 |
}; |
| 68 |
|
| 69 |
|
| 70 |
static const char *active_charset_name = "iso-8859-1"; |
| 71 |
static u16 *active_charset = NULL; |
| 72 |
static int no_translation = 0; |
| 73 |
|
| 74 |
static int |
| 75 |
ascii_strcasecmp( const char *a, const char *b ) |
| 76 |
{ |
| 77 |
if( a == b ) |
| 78 |
return 0; |
| 79 |
|
| 80 |
for (; *a && *b; a++, b++) { |
| 81 |
if (*a != *b && toupper(*a) != toupper(*b)) |
| 82 |
break; |
| 83 |
} |
| 84 |
|
| 85 |
return *a == *b? 0 : (toupper (*a) - toupper (*b)); |
| 86 |
} /* ascii_strcasecmp */ |
| 87 |
|
| 88 |
int |
| 89 |
set_native_charset( const char *newset ) |
| 90 |
{ |
| 91 |
if( !ascii_strcasecmp( newset, "iso-8859-1" ) ) { |
| 92 |
active_charset_name = "iso-8859-1"; |
| 93 |
no_translation = 0; |
| 94 |
active_charset = NULL; |
| 95 |
} |
| 96 |
else if( !ascii_strcasecmp( newset, "iso-8859-2" ) ) { |
| 97 |
active_charset_name = "iso-8859-2"; |
| 98 |
no_translation = 0; |
| 99 |
active_charset = latin2_unicode; |
| 100 |
} |
| 101 |
else if( !ascii_strcasecmp( newset, "koi8-r" ) ) { |
| 102 |
active_charset_name = "koi8-r"; |
| 103 |
no_translation = 0; |
| 104 |
active_charset = koi8_unicode; |
| 105 |
} |
| 106 |
else if( !ascii_strcasecmp (newset, "utf8" ) |
| 107 |
|| !ascii_strcasecmp(newset, "utf-8") ) { |
| 108 |
active_charset_name = "utf-8"; |
| 109 |
no_translation = 1; |
| 110 |
active_charset = NULL; |
| 111 |
} |
| 112 |
else |
| 113 |
return WPTERR_GENERAL; |
| 114 |
|
| 115 |
return 0; |
| 116 |
} /* set_native_charset */ |
| 117 |
|
| 118 |
const char* |
| 119 |
get_native_charset( void ) |
| 120 |
{ |
| 121 |
return active_charset_name; |
| 122 |
} /* get_native_charset */ |
| 123 |
|
| 124 |
/**************** |
| 125 |
* Convert string, which is in native encoding to UTF8 and return the |
| 126 |
* new allocated UTF8 string. |
| 127 |
*/ |
| 128 |
char * |
| 129 |
native_to_utf8( const char *string ) |
| 130 |
{ |
| 131 |
const byte *s; |
| 132 |
char *buffer; |
| 133 |
byte *p; |
| 134 |
size_t length=0; |
| 135 |
|
| 136 |
if (no_translation) |
| 137 |
buffer = strdup( string ); |
| 138 |
else if( active_charset ) { |
| 139 |
for(s=(byte*)string; *s; s++ ) { |
| 140 |
length++; |
| 141 |
if( *s & 0x80 ) |
| 142 |
length += 2; /* we may need 3 bytes */ |
| 143 |
} |
| 144 |
buffer = (char *)malloc( length + 1 ); |
| 145 |
for(p=(byte *)buffer, s=(byte *)string; *s; s++ ) { |
| 146 |
if( *s & 0x80 ) { |
| 147 |
u16 val = active_charset[ *s & 0x7f ]; |
| 148 |
if( val < 0x0800 ) { |
| 149 |
*p++ = 0xc0 | ( (val >> 6) & 0x1f ); |
| 150 |
*p++ = 0x80 | ( val & 0x3f ); |
| 151 |
} |
| 152 |
else { |
| 153 |
*p++ = 0xe0 | ( (val >> 12) & 0x0f ); |
| 154 |
*p++ = 0x80 | ( (val >> 6) & 0x3f ); |
| 155 |
*p++ = 0x80 | ( val & 0x3f ); |
| 156 |
} |
| 157 |
} |
| 158 |
else |
| 159 |
*p++ = *s; |
| 160 |
} |
| 161 |
*p = 0; |
| 162 |
} |
| 163 |
else { |
| 164 |
for(s=(byte*)string; *s; s++ ) { |
| 165 |
length++; |
| 166 |
if( *s & 0x80 ) |
| 167 |
length++; |
| 168 |
} |
| 169 |
buffer = (char*)malloc( length + 1 ); |
| 170 |
for(p=(byte*)buffer, s=(byte*)string; *s; s++ ) { |
| 171 |
if( *s & 0x80 ) { |
| 172 |
*p++ = 0xc0 | ((*s >> 6) & 3); |
| 173 |
*p++ = 0x80 | ( *s & 0x3f ); |
| 174 |
} |
| 175 |
else |
| 176 |
*p++ = *s; |
| 177 |
} |
| 178 |
*p = 0; |
| 179 |
} |
| 180 |
|
| 181 |
return buffer; |
| 182 |
} /* native_to_utf8 */ |
| 183 |
|
| 184 |
/**************** |
| 185 |
* Convert string, which is in UTF8 to native encoding. illegal |
| 186 |
* encodings by some "\xnn" and quote all control characters. A |
| 187 |
* character with value DELIM will always be quoted, it must be a |
| 188 |
* vanilla ASCII character. |
| 189 |
*/ |
| 190 |
char * |
| 191 |
utf8_to_native( const char *string, size_t length, int delim ) |
| 192 |
{ |
| 193 |
int nleft; |
| 194 |
int i; |
| 195 |
byte encbuf[8]; |
| 196 |
int encidx; |
| 197 |
const byte *s; |
| 198 |
size_t n; |
| 199 |
byte *buffer = NULL, *p = NULL; |
| 200 |
unsigned long val = 0; |
| 201 |
size_t slen; |
| 202 |
int resync = 0; |
| 203 |
|
| 204 |
/* 1. pass (p==NULL): count the extended utf-8 characters */ |
| 205 |
/* 2. pass (p!=NULL): create string */ |
| 206 |
for( ;; ) { |
| 207 |
for( slen=length, nleft=encidx=0, n=0, s=(byte*)string; slen; s++, slen-- ) { |
| 208 |
if( resync ) { |
| 209 |
if( !(*s < 128 || (*s >= 0xc0 && *s <= 0xfd)) ) { |
| 210 |
/* still invalid */ |
| 211 |
if( p ) { |
| 212 |
sprintf((char*)p, "\\x%02x", *s ); |
| 213 |
p += 4; |
| 214 |
} |
| 215 |
n += 4; |
| 216 |
continue; |
| 217 |
} |
| 218 |
resync = 0; |
| 219 |
} |
| 220 |
if( !nleft ) { |
| 221 |
if( !(*s & 0x80) ) { /* plain ascii */ |
| 222 |
if( *s < 0x20 || *s == 0x7f || *s == delim) { |
| 223 |
n++; |
| 224 |
if( p ) |
| 225 |
*p++ = '\\'; |
| 226 |
switch( *s ) { |
| 227 |
case '\n': n++; if( p ) *p++ = 'n'; break; |
| 228 |
case '\r': n++; if( p ) *p++ = 'r'; break; |
| 229 |
case '\f': n++; if( p ) *p++ = 'f'; break; |
| 230 |
case '\v': n++; if( p ) *p++ = 'v'; break; |
| 231 |
case '\b': n++; if( p ) *p++ = 'b'; break; |
| 232 |
case 0 : n++; if( p ) *p++ = '0'; break; |
| 233 |
default: |
| 234 |
n += 3; |
| 235 |
if ( p ) { |
| 236 |
sprintf( (char*)p, "x%02x", *s ); |
| 237 |
p += 3; |
| 238 |
} |
| 239 |
break; |
| 240 |
} |
| 241 |
} |
| 242 |
else { |
| 243 |
if( p ) *p++ = *s; |
| 244 |
n++; |
| 245 |
} |
| 246 |
} |
| 247 |
else if( (*s & 0xe0) == 0xc0 ) { /* 110x xxxx */ |
| 248 |
val = *s & 0x1f; |
| 249 |
nleft = 1; |
| 250 |
encidx = 0; |
| 251 |
encbuf[encidx++] = *s; |
| 252 |
} |
| 253 |
else if( (*s & 0xf0) == 0xe0 ) { /* 1110 xxxx */ |
| 254 |
val = *s & 0x0f; |
| 255 |
nleft = 2; |
| 256 |
encidx = 0; |
| 257 |
encbuf[encidx++] = *s; |
| 258 |
} |
| 259 |
else if( (*s & 0xf8) == 0xf0 ) { /* 1111 0xxx */ |
| 260 |
val = *s & 0x07; |
| 261 |
nleft = 3; |
| 262 |
encidx = 0; |
| 263 |
encbuf[encidx++] = *s; |
| 264 |
} |
| 265 |
else if( (*s & 0xfc) == 0xf8 ) { /* 1111 10xx */ |
| 266 |
val = *s & 0x03; |
| 267 |
nleft = 4; |
| 268 |
encidx = 0; |
| 269 |
encbuf[encidx++] = *s; |
| 270 |
} |
| 271 |
else if( (*s & 0xfe) == 0xfc ) { /* 1111 110x */ |
| 272 |
val = *s & 0x01; |
| 273 |
nleft = 5; |
| 274 |
encidx = 0; |
| 275 |
encbuf[encidx++] = *s; |
| 276 |
} |
| 277 |
else { /* invalid encoding: print as \xnn */ |
| 278 |
if( p ) { |
| 279 |
sprintf((char*)p, "\\x%02x", *s ); |
| 280 |
p += 4; |
| 281 |
} |
| 282 |
n += 4; |
| 283 |
resync = 1; |
| 284 |
} |
| 285 |
} |
| 286 |
else if( *s < 0x80 || *s >= 0xc0 ) { /* invalid */ |
| 287 |
if( p ) { |
| 288 |
for(i=0; i < encidx; i++ ) { |
| 289 |
sprintf((char*)p, "\\x%02x", encbuf[i] ); |
| 290 |
p += 4; |
| 291 |
} |
| 292 |
sprintf((char*)p, "\\x%02x", *s ); |
| 293 |
p += 4; |
| 294 |
} |
| 295 |
n += 4 + 4*encidx; |
| 296 |
nleft = 0; |
| 297 |
encidx = 0; |
| 298 |
resync = 1; |
| 299 |
} |
| 300 |
else { |
| 301 |
encbuf[encidx++] = *s; |
| 302 |
val <<= 6; |
| 303 |
val |= *s & 0x3f; |
| 304 |
if( !--nleft ) { /* ready */ |
| 305 |
if (no_translation) { |
| 306 |
if( p ) { |
| 307 |
for(i=0; i < encidx; i++ ) |
| 308 |
*p++ = encbuf[i]; |
| 309 |
} |
| 310 |
n += encidx; |
| 311 |
encidx = 0; |
| 312 |
} |
| 313 |
else if( active_charset ) { /* table lookup */ |
| 314 |
for(i=0; i < 128; i++ ) { |
| 315 |
if( active_charset[i] == val ) |
| 316 |
break; |
| 317 |
} |
| 318 |
if( i < 128 ) { /* we can print this one */ |
| 319 |
if( p ) *p++ = i+128; |
| 320 |
n++; |
| 321 |
} |
| 322 |
else { /* we do not have a translation: print utf8 */ |
| 323 |
if( p ) { |
| 324 |
for(i=0; i < encidx; i++ ) { |
| 325 |
sprintf((char*)p, "\\x%02x", encbuf[i] ); |
| 326 |
p += 4; |
| 327 |
} |
| 328 |
} |
| 329 |
n += encidx*4; |
| 330 |
encidx = 0; |
| 331 |
} |
| 332 |
} |
| 333 |
else { /* native set */ |
| 334 |
if( val >= 0x80 && val < 256 ) { |
| 335 |
n++; /* we can simply print this character */ |
| 336 |
if( p ) *p++ = val; |
| 337 |
} |
| 338 |
else { /* we do not have a translation: print utf8 */ |
| 339 |
if( p ) { |
| 340 |
for(i=0; i < encidx; i++ ) { |
| 341 |
sprintf((char*)p, "\\x%02x", encbuf[i] ); |
| 342 |
p += 4; |
| 343 |
} |
| 344 |
} |
| 345 |
n += encidx*4; |
| 346 |
encidx = 0; |
| 347 |
} |
| 348 |
} |
| 349 |
} |
| 350 |
|
| 351 |
} |
| 352 |
} |
| 353 |
if( !buffer ) { /* allocate the buffer after the first pass */ |
| 354 |
buffer = p = (byte *)malloc( n + 1 ); |
| 355 |
} |
| 356 |
else { |
| 357 |
*p = 0; /* make a string */ |
| 358 |
return (char*)buffer; |
| 359 |
} |
| 360 |
} |
| 361 |
} |
| 362 |
|
| 363 |
|
| 364 |
static void |
| 365 |
conv_charset (byte *string, size_t size, int what) |
| 366 |
{ |
| 367 |
int i; |
| 368 |
|
| 369 |
if( what == 0 ) { |
| 370 |
for( i = 0; i < size; i++, string++ ) { |
| 371 |
switch( *string ) { |
| 372 |
case 0xa0: *string = 0xff; break; /* nobreakspace */ |
| 373 |
case 0xa1: *string = 0xad; break; /* exclamdown */ |
| 374 |
case 0xa2: *string = 0xbd; break; /* cent */ |
| 375 |
case 0xa3: *string = 0x9c; break; /* sterling */ |
| 376 |
case 0xa4: *string = 0xcf; break; /* currency */ |
| 377 |
case 0xa5: *string = 0xbe; break; /* yen */ |
| 378 |
case 0xa6: *string = 0xdd; break; /* brokenbar */ |
| 379 |
case 0xa7: *string = 0xf5; break; /* section */ |
| 380 |
case 0xa8: *string = 0xf9; break; /* diaeresis */ |
| 381 |
case 0xa9: *string = 0xb8; break; /* copyright */ |
| 382 |
case 0xaa: *string = 0xa6; break; /* ordfeminine */ |
| 383 |
case 0xab: *string = 0xae; break; /* guillemotleft */ |
| 384 |
case 0xac: *string = 0xaa; break; /* notsign */ |
| 385 |
case 0xad: *string = 0xf0; break; /* hyphen */ |
| 386 |
case 0xae: *string = 0xa9; break; /* registered */ |
| 387 |
case 0xaf: *string = 0xee; break; /* macron */ |
| 388 |
case 0xb0: *string = 0xf8; break; /* degree */ |
| 389 |
case 0xb1: *string = 0xf1; break; /* plusminus */ |
| 390 |
case 0xb2: *string = 0xfd; break; /* twosuperior */ |
| 391 |
case 0xb3: *string = 0xfc; break; /* threesuperior */ |
| 392 |
case 0xb4: *string = 0xef; break; /* acute */ |
| 393 |
case 0xb5: *string = 0xe6; break; /* mu */ |
| 394 |
case 0xb6: *string = 0xf4; break; /* paragraph */ |
| 395 |
case 0xb7: *string = 0xfa; break; /* periodcentered */ |
| 396 |
case 0xb8: *string = 0xf7; break; /* cedilla */ |
| 397 |
case 0xb9: *string = 0xfb; break; /* onesuperior */ |
| 398 |
case 0xba: *string = 0xa7; break; /* masculine */ |
| 399 |
case 0xbb: *string = 0xaf; break; /* guillemotright */ |
| 400 |
case 0xbc: *string = 0xac; break; /* onequarter */ |
| 401 |
case 0xbd: *string = 0xab; break; /* onehalf */ |
| 402 |
case 0xbe: *string = 0xf3; break; /* threequarters */ |
| 403 |
case 0xbf: *string = 0xa8; break; /* questiondown */ |
| 404 |
case 0xc0: *string = 0xb7; break; /* Agrave */ |
| 405 |
case 0xc1: *string = 0xb5; break; /* Aacute */ |
| 406 |
case 0xc2: *string = 0xb6; break; /* Acircumflex */ |
| 407 |
case 0xc3: *string = 0xc7; break; /* Atilde */ |
| 408 |
case 0xc4: *string = 0x8e; break; /* Adiaeresis */ |
| 409 |
case 0xc5: *string = 0x8f; break; /* Aring */ |
| 410 |
case 0xc6: *string = 0x92; break; /* AE */ |
| 411 |
case 0xc7: *string = 0x80; break; /* Ccedilla */ |
| 412 |
case 0xc8: *string = 0xd4; break; /* Egrave */ |
| 413 |
case 0xc9: *string = 0x90; break; /* Eacute */ |
| 414 |
case 0xca: *string = 0xd2; break; /* Ecircumflex */ |
| 415 |
case 0xcb: *string = 0xd3; break; /* Ediaeresis */ |
| 416 |
case 0xcc: *string = 0xde; break; /* Igrave */ |
| 417 |
case 0xcd: *string = 0xd6; break; /* Iacute */ |
| 418 |
case 0xce: *string = 0xd7; break; /* Icircumflex */ |
| 419 |
case 0xcf: *string = 0xd8; break; /* Idiaeresis */ |
| 420 |
case 0xd0: *string = 0xd1; break; /* Eth */ |
| 421 |
case 0xd1: *string = 0xa5; break; /* Ntilde */ |
| 422 |
case 0xd2: *string = 0xe3; break; /* Ograve */ |
| 423 |
case 0xd3: *string = 0xe0; break; /* Oacute */ |
| 424 |
case 0xd4: *string = 0xe2; break; /* Ocircumflex */ |
| 425 |
case 0xd5: *string = 0xe5; break; /* Otilde */ |
| 426 |
case 0xd6: *string = 0x99; break; /* Odiaeresis */ |
| 427 |
case 0xd7: *string = 0x9e; break; /* multiply */ |
| 428 |
case 0xd8: *string = 0x9d; break; /* Ooblique */ |
| 429 |
case 0xd9: *string = 0xeb; break; /* Ugrave */ |
| 430 |
case 0xda: *string = 0xe9; break; /* Uacute */ |
| 431 |
case 0xdb: *string = 0xea; break; /* Ucircumflex */ |
| 432 |
case 0xdc: *string = 0x9a; break; /* Udiaeresis */ |
| 433 |
case 0xdd: *string = 0xed; break; /* Yacute */ |
| 434 |
case 0xde: *string = 0xe8; break; /* Thorn */ |
| 435 |
case 0xdf: *string = 0xe1; break; /* ssharp */ |
| 436 |
case 0xe0: *string = 0x85; break; /* agrave */ |
| 437 |
case 0xe1: *string = 0xa0; break; /* aacute */ |
| 438 |
case 0xe2: *string = 0x83; break; /* acircumflex */ |
| 439 |
case 0xe3: *string = 0xc6; break; /* atilde */ |
| 440 |
case 0xe4: *string = 0x84; break; /* adiaeresis */ |
| 441 |
case 0xe5: *string = 0x86; break; /* aring */ |
| 442 |
case 0xe6: *string = 0x91; break; /* ae */ |
| 443 |
case 0xe7: *string = 0x87; break; /* ccedilla */ |
| 444 |
case 0xe8: *string = 0x8a; break; /* egrave */ |
| 445 |
case 0xe9: *string = 0x82; break; /* eacute */ |
| 446 |
case 0xea: *string = 0x88; break; /* ecircumflex */ |
| 447 |
case 0xeb: *string = 0x89; break; /* ediaeresis */ |
| 448 |
case 0xec: *string = 0x8d; break; /* igrave */ |
| 449 |
case 0xed: *string = 0xa1; break; /* iacute */ |
| 450 |
case 0xee: *string = 0x8c; break; /* icircumflex */ |
| 451 |
case 0xef: *string = 0x8b; break; /* idiaeresis */ |
| 452 |
case 0xf0: *string = 0xd0; break; /* eth */ |
| 453 |
case 0xf1: *string = 0xa4; break; /* ntilde */ |
| 454 |
case 0xf2: *string = 0x95; break; /* ograve */ |
| 455 |
case 0xf3: *string = 0xa2; break; /* oacute */ |
| 456 |
case 0xf4: *string = 0x93; break; /* ocircumflex */ |
| 457 |
case 0xf5: *string = 0xe4; break; /* otilde */ |
| 458 |
case 0xf6: *string = 0x94; break; /* odiaeresis */ |
| 459 |
case 0xf7: *string = 0xf6; break; /* division */ |
| 460 |
case 0xf8: *string = 0x9b; break; /* oslash */ |
| 461 |
case 0xf9: *string = 0x97; break; /* ugrave */ |
| 462 |
case 0xfa: *string = 0xa3; break; /* uacute */ |
| 463 |
case 0xfb: *string = 0x96; break; /* ucircumflex */ |
| 464 |
case 0xfc: *string = 0x81; break; /* udiaeresis */ |
| 465 |
case 0xfd: *string = 0xec; break; /* yacute */ |
| 466 |
case 0xfe: *string = 0xe7; break; /* thorn */ |
| 467 |
case 0xff: *string = 0x98; break; /* ydiaeresis */ |
| 468 |
default : break; |
| 469 |
} |
| 470 |
} |
| 471 |
} |
| 472 |
else { |
| 473 |
for( i = 0; i < size; i++, string++ ) { |
| 474 |
switch( *string ) { |
| 475 |
case 0xff: *string = 0xa0; break; |
| 476 |
case 0xad: *string = 0xa1; break; |
| 477 |
case 0xbd: *string = 0xa2; break; |
| 478 |
case 0x9c: *string = 0xa3; break; |
| 479 |
case 0xcf: *string = 0xa4; break; |
| 480 |
case 0xbe: *string = 0xa5; break; |
| 481 |
case 0xdd: *string = 0xa6; break; |
| 482 |
case 0xf5: *string = 0xa7; break; |
| 483 |
case 0xf9: *string = 0xa8; break; |
| 484 |
case 0xb8: *string = 0xa9; break; |
| 485 |
case 0xa6: *string = 0xaa; break; |
| 486 |
case 0xae: *string = 0xab; break; |
| 487 |
case 0xaa: *string = 0xac; break; |
| 488 |
case 0xf0: *string = 0xad; break; |
| 489 |
case 0xa9: *string = 0xae; break; |
| 490 |
case 0xee: *string = 0xaf; break; |
| 491 |
case 0xf8: *string = 0xb0; break; |
| 492 |
case 0xf1: *string = 0xb1; break; |
| 493 |
case 0xfd: *string = 0xb2; break; |
| 494 |
case 0xfc: *string = 0xb3; break; |
| 495 |
case 0xef: *string = 0xb4; break; |
| 496 |
case 0xe6: *string = 0xb5; break; |
| 497 |
case 0xf4: *string = 0xb6; break; |
| 498 |
case 0xfa: *string = 0xb7; break; |
| 499 |
case 0xf7: *string = 0xb8; break; |
| 500 |
case 0xfb: *string = 0xb9; break; |
| 501 |
case 0xa7: *string = 0xba; break; |
| 502 |
case 0xaf: *string = 0xbb; break; |
| 503 |
case 0xac: *string = 0xbc; break; |
| 504 |
case 0xab: *string = 0xbd; break; |
| 505 |
case 0xf3: *string = 0xbe; break; |
| 506 |
case 0xa8: *string = 0xbf; break; |
| 507 |
case 0xb7: *string = 0xc0; break; |
| 508 |
case 0xb5: *string = 0xc1; break; |
| 509 |
case 0xb6: *string = 0xc2; break; |
| 510 |
case 0xc7: *string = 0xc3; break; |
| 511 |
case 0x8e: *string = 0xc4; break; |
| 512 |
case 0x8f: *string = 0xc5; break; |
| 513 |
case 0x92: *string = 0xc6; break; |
| 514 |
case 0x80: *string = 0xc7; break; |
| 515 |
case 0xd4: *string = 0xc8; break; |
| 516 |
case 0x90: *string = 0xc9; break; |
| 517 |
case 0xd2: *string = 0xca; break; |
| 518 |
case 0xd3: *string = 0xcb; break; |
| 519 |
case 0xde: *string = 0xcc; break; |
| 520 |
case 0xd6: *string = 0xcd; break; |
| 521 |
case 0xd7: *string = 0xce; break; |
| 522 |
case 0xd8: *string = 0xcf; break; |
| 523 |
case 0xd1: *string = 0xd0; break; |
| 524 |
case 0xa5: *string = 0xd1; break; |
| 525 |
case 0xe3: *string = 0xd2; break; |
| 526 |
case 0xe0: *string = 0xd3; break; |
| 527 |
case 0xe2: *string = 0xd4; break; |
| 528 |
case 0xe5: *string = 0xd5; break; |
| 529 |
case 0x99: *string = 0xd6; break; |
| 530 |
case 0x9e: *string = 0xd7; break; |
| 531 |
case 0x9d: *string = 0xd8; break; |
| 532 |
case 0xeb: *string = 0xd9; break; |
| 533 |
case 0xe9: *string = 0xda; break; |
| 534 |
case 0xea: *string = 0xdb; break; |
| 535 |
case 0x9a: *string = 0xdc; break; |
| 536 |
case 0xed: *string = 0xdd; break; |
| 537 |
case 0xe8: *string = 0xde; break; |
| 538 |
case 0xe1: *string = 0xdf; break; |
| 539 |
case 0x85: *string = 0xe0; break; |
| 540 |
case 0xa0: *string = 0xe1; break; |
| 541 |
case 0x83: *string = 0xe2; break; |
| 542 |
case 0xc6: *string = 0xe3; break; |
| 543 |
case 0x84: *string = 0xe4; break; |
| 544 |
case 0x86: *string = 0xe5; break; |
| 545 |
case 0x91: *string = 0xe6; break; |
| 546 |
case 0x87: *string = 0xe7; break; |
| 547 |
case 0x8a: *string = 0xe8; break; |
| 548 |
case 0x82: *string = 0xe9; break; |
| 549 |
case 0x88: *string = 0xea; break; |
| 550 |
case 0x89: *string = 0xeb; break; |
| 551 |
case 0x8d: *string = 0xec; break; |
| 552 |
case 0xa1: *string = 0xed; break; |
| 553 |
case 0x8c: *string = 0xee; break; |
| 554 |
case 0x8b: *string = 0xef; break; |
| 555 |
case 0xd0: *string = 0xf0; break; |
| 556 |
case 0xa4: *string = 0xf1; break; |
| 557 |
case 0x95: *string = 0xf2; break; |
| 558 |
case 0xa2: *string = 0xf3; break; |
| 559 |
case 0x93: *string = 0xf4; break; |
| 560 |
case 0xe4: *string = 0xf5; break; |
| 561 |
case 0x94: *string = 0xf6; break; |
| 562 |
case 0xf6: *string = 0xf7; break; |
| 563 |
case 0x9b: *string = 0xf8; break; |
| 564 |
case 0x97: *string = 0xf9; break; |
| 565 |
case 0xa3: *string = 0xfa; break; |
| 566 |
case 0x96: *string = 0xfb; break; |
| 567 |
case 0x81: *string = 0xfc; break; |
| 568 |
case 0xec: *string = 0xfd; break; |
| 569 |
case 0xe7: *string = 0xfe; break; |
| 570 |
case 0x98: *string = 0xff; break; |
| 571 |
default : break; |
| 572 |
} |
| 573 |
} |
| 574 |
} |
| 575 |
} /* conv_charset */ |
| 576 |
|
| 577 |
|
| 578 |
char * |
| 579 |
utf8_to_wincp (const char * s, size_t len) |
| 580 |
{ |
| 581 |
char * decs; |
| 582 |
decs = utf8_to_native (s, len, 0); |
| 583 |
conv_charset ((byte *)decs, strlen (decs), 1); |
| 584 |
return decs; |
| 585 |
} |
| 586 |
|
| 587 |
|
| 588 |
char * |
| 589 |
wincp_to_utf8 (const char * s, size_t len) |
| 590 |
{ |
| 591 |
char * encs; |
| 592 |
conv_charset ((byte *)s, len, 0); |
| 593 |
encs = native_to_utf8 (s); |
| 594 |
return encs; |
| 595 |
} |
| 596 |
|
| 597 |
|
| 598 |
int |
| 599 |
is_8bit_string (const char * str) |
| 600 |
{ |
| 601 |
size_t i; |
| 602 |
|
| 603 |
for (i = 0; i < strlen (str); i++) { |
| 604 |
if (str[i] & 0x80) |
| 605 |
return -1; |
| 606 |
} |
| 607 |
return 0; |
| 608 |
} /* is_8bit_string */ |
Parent Directory
| 
Revision Log