1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
|
/* Copyright 2008,2009 Alain Knaff.
* This file is part of mtools.
*
* Mtools is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Mtools is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Mtools. If not, see <http://www.gnu.org/licenses/>.
*
* Various character set conversions used by mtools
*/
#include "sysincludes.h"
#include "msdos.h"
#include "mtools.h"
#include <stdio.h>
#include <errno.h>
#include <stdlib.h>
#include "file_name.h"
#ifdef HAVE_ICONV_H
#include <iconv.h>
struct doscp_t {
iconv_t from;
iconv_t to;
};
static char *wcharCp=NULL;
static char* wcharTries[] = {
"WCHAR_T",
"UTF-32BE", "UTF-32LE",
"UTF-16BE", "UTF-16LE",
"UTF-32", "UTF-16",
"UCS-4BE", "UCS-4LE",
"UCS-2BE", "UCS-2LE",
"UCS-4", "UCS-2"
};
static wchar_t *testString = L"ab";
static int try(char *testCp) {
size_t res;
char *inbuf = (char *)testString;
size_t inbufLen = 2*sizeof(wchar_t);
char outbuf[3];
char *outbufP = outbuf;
size_t outbufLen = 2*sizeof(char);
iconv_t test = iconv_open("ASCII", testCp);
if(test == (iconv_t) -1)
goto fail0;
res = iconv(test,
&inbuf, &inbufLen,
&outbufP, &outbufLen);
if(res != 0 || outbufLen != 0 || inbufLen != 0)
goto fail;
if(memcmp(outbuf, "ab", 2))
goto fail;
/* fprintf(stderr, "%s ok\n", testCp); */
return 1;
fail:
iconv_close(test);
fail0:
/*fprintf(stderr, "%s fail\n", testCp);*/
return 0;
}
static const char *getWcharCp() {
int i;
if(wcharCp != NULL)
return wcharCp;
for(i=0; i< sizeof(wcharTries) / sizeof(wcharTries[0]); i++) {
if(try(wcharTries[i]))
return (wcharCp=wcharTries[i]);
}
fprintf(stderr, "No codepage found for wchar_t\n");
return NULL;
}
doscp_t *cp_open(int codepage)
{
char dosCp[17];
doscp_t *ret;
iconv_t *from;
iconv_t *to;
if(codepage == 0)
codepage = mtools_default_codepage;
if(codepage < 0 || codepage > 9999) {
fprintf(stderr, "Bad codepage %d\n", codepage);
return NULL;
}
if(getWcharCp() == NULL)
return NULL;
sprintf(dosCp, "CP%d", codepage);
from = iconv_open(wcharCp, dosCp);
if(from == (iconv_t)-1) {
fprintf(stderr, "Error converting to codepage %d %s\n",
codepage, strerror(errno));
return NULL;
}
sprintf(dosCp, "CP%d//TRANSLIT", codepage);
to = iconv_open(dosCp, wcharCp);
if(to == (iconv_t)-1) {
/* Transliteration not supported? */
sprintf(dosCp, "CP%d", codepage);
to = iconv_open(dosCp, wcharCp);
}
if(to == (iconv_t)-1) {
iconv_close(from);
fprintf(stderr, "Error converting to codepage %d %s\n",
codepage, strerror(errno));
return NULL;
}
ret = New(doscp_t);
if(ret == NULL)
return ret;
ret->from = from;
ret->to = to;
return ret;
}
void cp_close(doscp_t *cp)
{
iconv_close(cp->to);
iconv_close(cp->from);
free(cp);
}
int dos_to_wchar(doscp_t *cp, char *dos, wchar_t *wchar, size_t len)
{
int r;
size_t in_len=len;
size_t out_len=len*sizeof(wchar_t);
wchar_t *dptr=wchar;
r=iconv(cp->from, &dos, &in_len, (char **)&dptr, &out_len);
if(r < 0)
return r;
*dptr = L'\0';
return dptr-wchar;
}
/**
* Converts len wide character to destination. Caller's responsibility to
* ensure that dest is large enough.
* mangled will be set if there has been an untranslatable character.
*/
static int safe_iconv(iconv_t conv, const wchar_t *wchar, char *dest,
size_t len, int *mangled)
{
int r;
int i;
size_t in_len=len*sizeof(wchar_t);
size_t out_len=len*4;
char *dptr = dest;
while(in_len > 0) {
r=iconv(conv, (char**)&wchar, &in_len, &dptr, &out_len);
if(r >= 0 || errno != EILSEQ) {
/* everything transformed, or error that is _not_ a bad
* character */
break;
}
*mangled |= 1;
if(dptr)
*dptr++ = '_';
in_len--;
wchar++;
out_len--;
}
len = dptr-dest; /* how many dest characters have there been
generated */
/* eliminate question marks which might have been formed by
untransliterable characters */
for(i=0; i<len; i++) {
if(dest[i] == '?') {
dest[i] = '_';
*mangled |= 1;
}
}
return len;
}
void wchar_to_dos(doscp_t *cp,
wchar_t *wchar, char *dos, size_t len, int *mangled)
{
safe_iconv(cp->to, wchar, dos, len, mangled);
}
#else
#include "codepage.h"
struct doscp_t {
unsigned char *from_dos;
unsigned char to_dos[0x80];
};
doscp_t *cp_open(int codepage)
{
doscp_t *ret;
int i;
Codepage_t *cp;
if(codepage == 0)
codepage = 850;
ret = New(doscp_t);
if(ret == NULL)
return ret;
for(cp=codepages; cp->nr ; cp++)
if(cp->nr == codepage) {
ret->from_dos = cp->tounix;
break;
}
if(ret->from_dos == NULL) {
fprintf(stderr, "Bad codepage %d\n", codepage);
free(ret);
return NULL;
}
for(i=0; i<0x80; i++) {
char native = ret->from_dos[i];
if(! (native & 0x80))
continue;
ret->to_dos[native & 0x7f] = 0x80 | i;
}
return ret;
}
void cp_close(doscp_t *cp)
{
free(cp);
}
int dos_to_wchar(doscp_t *cp, char *dos, wchar_t *wchar, size_t len)
{
int i;
for(i=0; i<len && dos[i]; i++) {
char c = dos[i];
if(c >= ' ' && c <= '~')
wchar[i] = c;
else {
wchar[i] = cp->from_dos[c & 0x7f];
}
}
wchar[i] = '\0';
return i;
}
void wchar_to_dos(doscp_t *cp,
wchar_t *wchar, char *dos, size_t len, int *mangled)
{
int i;
for(i=0; i<len && wchar[i]; i++) {
char c = wchar[i];
if(c >= ' ' && c <= '~')
dos[i] = c;
else {
dos[i] = cp->to_dos[c & 0x7f];
if(dos[i] == '\0') {
dos[i]='_';
*mangled=1;
}
}
}
}
#endif
#ifndef HAVE_WCHAR_H
typedef int mbstate_t;
static inline size_t wcrtomb(char *s, wchar_t wc, mbstate_t *ps)
{
*s = wc;
return 1;
}
static inline size_t mbrtowc(wchar_t *pwc, const char *s,
size_t n, mbstate_t *ps)
{
*pwc = *s;
return 1;
}
#endif
#ifdef HAVE_ICONV_H
#include <langinfo.h>
static iconv_t to_native = NULL;
static void initialize_to_native(void)
{
char *li, *cp;
int len;
if(to_native != NULL)
return;
li = nl_langinfo(CODESET);
len = strlen(li) + 11;
if(getWcharCp() == NULL)
exit(1);
cp = safe_malloc(len);
strcpy(cp, li);
strcat(cp, "//TRANSLIT");
to_native = iconv_open(cp, wcharCp);
if(to_native == (iconv_t) -1)
to_native = iconv_open(li, wcharCp);
if(to_native == (iconv_t) -1)
fprintf(stderr, "Could not allocate iconv for %s\n", cp);
free(cp);
if(to_native == (iconv_t) -1)
exit(1);
}
#endif
/**
* Convert wchar string to native, converting at most len wchar characters
* Returns number of generated native characters
*/
int wchar_to_native(const wchar_t *wchar, char *native, size_t len)
{
#ifdef HAVE_ICONV_H
int mangled;
int r;
initialize_to_native();
len = wcsnlen(wchar,len);
r=safe_iconv(to_native, wchar, native, len, &mangled);
native[r]='\0';
return r;
#else
int i;
char *dptr = native;
mbstate_t ps;
memset(&ps, 0, sizeof(ps));
for(i=0; i<len && wchar[i] != 0; i++) {
int r = wcrtomb(dptr, wchar[i], &ps);
if(r < 0 && errno == EILSEQ) {
r=1;
*dptr='_';
}
if(r < 0)
return r;
dptr+=r;
}
*dptr='\0';
return dptr-native;
#endif
}
/**
* Convert native string to wchar string, generating at most len wchar
* characters. If end is supplied, stop conversion when source pointer
* exceeds end. Returns number of generated wchars
*/
int native_to_wchar(const char *native, wchar_t *wchar, size_t len,
const char *end, int *mangled)
{
mbstate_t ps;
int i;
memset(&ps, 0, sizeof(ps));
for(i=0; i<len && (native < end || !end); i++) {
int r = mbrtowc(wchar+i, native, len, &ps);
if(r < 0) {
/* Unconvertible character. Just pretend it's Latin1
encoded (if valid Latin1 character) or substitue
with an underscore if not
*/
char c = *native;
if(c >= '\xa0' && c < '\xff')
wchar[i] = c & 0xff;
else
wchar[i] = '_';
memset(&ps, 0, sizeof(ps));
r=1;
}
if(r == 0)
break;
native += r;
}
if(mangled && ((end && native < end) || (!end && *native && i == len)))
*mangled |= 3;
wchar[i]='\0';
return i;
}
|