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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
|
/* $Id: avc_mbyte.c,v 1.3 2005/06/03 03:49:59 daniel Exp $
*
* Name: avc_mbyte.c
* Project: Arc/Info vector coverage (AVC) E00->BIN conversion library
* Language: ANSI C
* Purpose: Functions to handle multibyte character conversions.
* Author: Daniel Morissette, dmorissette@dmsolutions.ca
*
**********************************************************************
* Copyright (c) 1999-2005, Daniel Morissette
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included
* in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
**********************************************************************
*
* $Log: avc_mbyte.c,v $
* Revision 1.3 2005/06/03 03:49:59 daniel
* Update email address, website url, and copyright dates
*
* Revision 1.2 2000/09/22 19:45:21 daniel
* Switch to MIT-style license
*
* Revision 1.1 2000/05/29 15:31:03 daniel
* Initial revision - Japanese support
*
**********************************************************************/
#include "avc.h"
#ifdef _WIN32
# include <mbctype.h>
#endif
static int _AVCDetectJapaneseEncoding(const unsigned char *pszLine);
static const char *_AVCJapanese2ArcDBCS(AVCDBCSInfo *psDBCSInfo,
const unsigned char *pszLine,
int nMaxOutputLen);
static const char *_AVCArcDBCS2JapaneseShiftJIS(AVCDBCSInfo *psDBCSInfo,
const unsigned char *pszLine,
int nMaxOutputLen);
/*=====================================================================
* Functions to handle multibyte char conversions
*====================================================================*/
#define IS_ASCII(c) ((c) < 0x80)
/**********************************************************************
* AVCAllocDBCSInfo()
*
* Alloc and init a new AVCDBCSInfo structure.
**********************************************************************/
AVCDBCSInfo *AVCAllocDBCSInfo()
{
AVCDBCSInfo *psInfo;
psInfo = (AVCDBCSInfo*)CPLCalloc(1, sizeof(AVCDBCSInfo));
psInfo->nDBCSCodePage = AVCGetDBCSCodePage();
psInfo->nDBCSEncoding = AVC_CODE_UNKNOWN;
psInfo->pszDBCSBuf = NULL;
psInfo->nDBCSBufSize = 0;
return psInfo;
}
/**********************************************************************
* AVCFreeDBCSInfo()
*
* Release all memory associated with a AVCDBCSInfo structure.
**********************************************************************/
void AVCFreeDBCSInfo(AVCDBCSInfo *psInfo)
{
if (psInfo)
{
CPLFree(psInfo->pszDBCSBuf);
CPLFree(psInfo);
}
}
/**********************************************************************
* AVCGetDBCSCodePage()
*
* Fetch current multibyte codepage on the system.
* Returns a valid codepage number, or 0 if the codepage is single byte or
* unsupported.
**********************************************************************/
int AVCGetDBCSCodePage()
{
#ifdef _WIN32
int nCP;
nCP = _getmbcp();
/* Check if that's a supported codepage */
if (nCP == AVC_DBCS_JAPANESE)
return nCP;
#endif
return 0;
}
/**********************************************************************
* AVCE00DetectEncoding()
*
* Try to detect the encoding used in the current file by examining lines
* of input.
*
* Returns TRUE once the encoding is established, or FALSE if more lines
* of input are required to establish the encoding.
**********************************************************************/
GBool AVCE00DetectEncoding(AVCDBCSInfo *psDBCSInfo, const char *pszLine)
{
if (psDBCSInfo == NULL || psDBCSInfo->nDBCSCodePage == 0 ||
psDBCSInfo->nDBCSEncoding != AVC_CODE_UNKNOWN)
{
/* Either single byte codepage, or encoding has already been detected
*/
return TRUE;
}
switch (psDBCSInfo->nDBCSCodePage)
{
case AVC_DBCS_JAPANESE:
psDBCSInfo->nDBCSEncoding =
_AVCDetectJapaneseEncoding((const unsigned char *)pszLine);
break;
default:
psDBCSInfo->nDBCSEncoding = AVC_CODE_UNKNOWN;
return TRUE; /* Codepage not supported... no need to scan more lines*/
}
if (psDBCSInfo->nDBCSEncoding != AVC_CODE_UNKNOWN)
return TRUE; /* We detected the encoding! */
return FALSE;
}
/**********************************************************************
* AVCE00Convert2ArcDBCS()
*
* If encoding is still unknown, try to detect the encoding used in the
* current file, and then convert the string to an encoding validfor output
* to a coverage.
*
* Returns a reference to a const buffer that should not be freed by the
* caller. It can be either the original string buffer or a ref. to an
* internal buffer.
**********************************************************************/
const char *AVCE00Convert2ArcDBCS(AVCDBCSInfo *psDBCSInfo,
const char *pszLine,
int nMaxOutputLen)
{
const char *pszOutBuf = NULL;
unsigned char *pszTmp;
GBool bAllAscii;
if (psDBCSInfo == NULL ||
psDBCSInfo->nDBCSCodePage == 0 || pszLine == NULL)
{
/* Single byte codepage... nothing to do
*/
return pszLine;
}
/* If string is all ASCII then there is nothing to do...
*/
pszTmp = (unsigned char *)pszLine;
for(bAllAscii = TRUE ; bAllAscii && pszTmp && *pszTmp; pszTmp++)
{
if ( !IS_ASCII(*pszTmp) )
bAllAscii = FALSE;
}
if (bAllAscii)
return pszLine;
/* Make sure output buffer is large enough.
* We add 2 chars to buffer size to simplify processing... no need to
* check if second byte of a pair would overflow buffer.
*/
if (psDBCSInfo->pszDBCSBuf == NULL ||
psDBCSInfo->nDBCSBufSize < nMaxOutputLen+2)
{
psDBCSInfo->nDBCSBufSize = nMaxOutputLen+2;
psDBCSInfo->pszDBCSBuf =
(unsigned char *)CPLRealloc(psDBCSInfo->pszDBCSBuf,
psDBCSInfo->nDBCSBufSize*
sizeof(unsigned char));
}
/* Do the conversion according to current code page
*/
switch (psDBCSInfo->nDBCSCodePage)
{
case AVC_DBCS_JAPANESE:
pszOutBuf = (char*)_AVCJapanese2ArcDBCS(psDBCSInfo,
(const unsigned char *)pszLine,
nMaxOutputLen);
break;
default:
/* We should never get here anyways, but just in case return pszLine
*/
pszOutBuf = pszLine;
}
return pszOutBuf;
}
/**********************************************************************
* AVCE00ConvertFromArcDBCS()
*
* Convert DBCS encoding in binary coverage files to E00 encoding.
*
* Returns a reference to a const buffer that should not be freed by the
* caller. It can be either the original string buffer or a ref. to an
* internal buffer.
**********************************************************************/
const char *AVCE00ConvertFromArcDBCS(AVCDBCSInfo *psDBCSInfo,
const char *pszLine,
int nMaxOutputLen)
{
const char *pszOutBuf = NULL;
unsigned char *pszTmp;
GBool bAllAscii;
if (psDBCSInfo == NULL ||
psDBCSInfo->nDBCSCodePage == 0 || pszLine == NULL)
{
/* Single byte codepage... nothing to do
*/
return pszLine;
}
/* If string is all ASCII then there is nothing to do...
*/
pszTmp = (unsigned char *)pszLine;
for(bAllAscii = TRUE ; bAllAscii && pszTmp && *pszTmp; pszTmp++)
{
if ( !IS_ASCII(*pszTmp) )
bAllAscii = FALSE;
}
if (bAllAscii)
return pszLine;
/* Make sure output buffer is large enough.
* We add 2 chars to buffer size to simplify processing... no need to
* check if second byte of a pair would overflow buffer.
*/
if (psDBCSInfo->pszDBCSBuf == NULL ||
psDBCSInfo->nDBCSBufSize < nMaxOutputLen+2)
{
psDBCSInfo->nDBCSBufSize = nMaxOutputLen+2;
psDBCSInfo->pszDBCSBuf =
(unsigned char *)CPLRealloc(psDBCSInfo->pszDBCSBuf,
psDBCSInfo->nDBCSBufSize*
sizeof(unsigned char));
}
/* Do the conversion according to current code page
*/
switch (psDBCSInfo->nDBCSCodePage)
{
case AVC_DBCS_JAPANESE:
pszOutBuf = (char*)_AVCArcDBCS2JapaneseShiftJIS(psDBCSInfo,
(const unsigned char *)pszLine,
nMaxOutputLen);
break;
default:
/* We should never get here anyways, but just in case return pszLine
*/
pszOutBuf = pszLine;
}
return pszOutBuf;
}
/*=====================================================================
*=====================================================================
* Functions Specific to Japanese encoding (CodePage 932).
*
* For now we assume that we can receive only Katakana, Shift-JIS, or EUC
* encoding as input. Coverages use EUC encoding in most cases, except
* for Katakana characters that are prefixed with a 0x8e byte.
*
* Most of the Japanese conversion functions are based on information and
* algorithms found at:
* http://www.mars.dti.ne.jp/~torao/program/appendix/japanese-en.html
*=====================================================================
*====================================================================*/
/**********************************************************************
* _AVCDetectJapaneseEncoding()
*
* Scan a line of text to try to establish the type of japanese encoding
*
* Returns the encoding number (AVC_CODE_JAP_*), or AVC_CODE_UNKNOWN if no
* specific encoding was detected.
**********************************************************************/
#define IS_JAP_SHIFTJIS_1(c) ((c) >= 0x81 && (c) <= 0x9f)
#define IS_JAP_SHIFTJIS_2(c) (((c) >= 0x40 && (c) <= 0x7e) || \
((c) >= 0x80 && (c) <= 0xA0) )
#define IS_JAP_EUC_1(c) ((c) >= 0xF0 && (c) <= 0xFE)
#define IS_JAP_EUC_2(c) ((c) >= 0xFD && (c) <= 0xFE)
#define IS_JAP_KANA(c) ((c) >= 0xA1 && (c) <= 0xDF)
static int _AVCDetectJapaneseEncoding(const unsigned char *pszLine)
{
int nEncoding = AVC_CODE_UNKNOWN;
for( ; nEncoding == AVC_CODE_UNKNOWN && pszLine && *pszLine; pszLine++)
{
if (IS_ASCII(*pszLine))
continue;
else if (IS_JAP_SHIFTJIS_1(*pszLine))
{
nEncoding = AVC_CODE_JAP_SHIFTJIS;
break;
}
else if (IS_JAP_KANA(*pszLine) && *(pszLine+1) &&
(IS_ASCII(*(pszLine+1)) ||
(*(pszLine+1)>=0x80 && *(pszLine+1)<=0xA0) ) )
{
nEncoding = AVC_CODE_JAP_SHIFTJIS; /* SHIFT-JIS + Kana */
break;
}
else if (IS_JAP_EUC_1(*pszLine))
{
nEncoding = AVC_CODE_JAP_EUC;
break;
}
if (*(++pszLine) == '\0')
break;
if (IS_JAP_SHIFTJIS_2(*pszLine))
{
nEncoding = AVC_CODE_JAP_SHIFTJIS;
break;
}
else if (IS_JAP_EUC_2(*pszLine))
{
nEncoding = AVC_CODE_JAP_EUC;
break;
}
}
return nEncoding;
}
/**********************************************************************
* _AVCJapanese2ArcDBCS()
*
* Try to detect type of Japanese encoding if not done yet, and convert
* string from Japanese to proper coverage DBCS encoding.
**********************************************************************/
static const char *_AVCJapanese2ArcDBCS(AVCDBCSInfo *psDBCSInfo,
const unsigned char *pszLine,
int nMaxOutputLen)
{
unsigned char *pszOut;
int iDst;
pszOut = psDBCSInfo->pszDBCSBuf;
if (psDBCSInfo->nDBCSEncoding == AVC_CODE_UNKNOWN)
{
/* Type of encoding (Shift-JIS or EUC) not known yet... try to
* detect it now.
*/
psDBCSInfo->nDBCSEncoding = _AVCDetectJapaneseEncoding(pszLine);
/*
if (psDBCSInfo->nDBCSEncoding == AVC_CODE_JAP_SHIFTJIS)
{
printf("Found Japanese Shift-JIS encoding\n");
}
else if (psDBCSInfo->nDBCSEncoding == AVC_CODE_JAP_EUC)
{
printf("Found Japanese EUC encoding\n");
}
*/
}
for(iDst=0; *pszLine && iDst < nMaxOutputLen; pszLine++)
{
if (IS_ASCII(*pszLine))
{
/* No transformation required for ASCII */
pszOut[iDst++] = *pszLine;
}
else if ( psDBCSInfo->nDBCSEncoding==AVC_CODE_JAP_EUC && *(pszLine+1) )
{
/* This must be a pair of EUC chars and both should be in
* the range 0xA1-0xFE
*/
pszOut[iDst++] = *(pszLine++);
pszOut[iDst++] = *pszLine;
}
else if ( IS_JAP_KANA(*pszLine) )
{
/* Katakana char. prefix it with 0x8e */
pszOut[iDst++] = 0x8e;
pszOut[iDst++] = *pszLine;
}
else if ( *(pszLine+1) )
{
/* This must be a pair of Shift-JIS chars... convert them to EUC
*
* If we haven't been able to establish the encoding for sure
* yet, then it is possible that a pair of EUC chars could be
* treated as shift-JIS here... but there is not much we can do
* about that unless we scan the whole E00 input before we
* start the conversion.
*/
unsigned char leader, trailer;
leader = *(pszLine++);
trailer = *pszLine;
if(leader <= 0x9F) leader -= 0x71;
else leader -= 0xB1;
leader = (leader << 1) + 1;
if(trailer > 0x7F) trailer --;
if(trailer >= 0x9E)
{
trailer -= 0x7D;
leader ++;
}
else
{
trailer -= 0x1F;
}
pszOut[iDst++] = leader | 0x80;
pszOut[iDst++] = trailer | 0x80;
}
else
{
/* We should never get here unless a double-byte pair was
* truncated... but just in case...
*/
pszOut[iDst++] = *pszLine;
}
}
pszOut[iDst] = '\0';
return psDBCSInfo->pszDBCSBuf;
}
/**********************************************************************
* _AVCArcDBCS2JapaneseShiftJIS()
*
* Convert string from coverage DBCS (EUC) to Japanese Shift-JIS.
*
* We know that binary coverages use a custom EUC encoding for japanese
* which is EUC + all Katakana chars are prefixed with 0x8e. So this
* function just does a simple conversion.
**********************************************************************/
static const char *_AVCArcDBCS2JapaneseShiftJIS(AVCDBCSInfo *psDBCSInfo,
const unsigned char *pszLine,
int nMaxOutputLen)
{
unsigned char *pszOut;
int iDst;
pszOut = psDBCSInfo->pszDBCSBuf;
for(iDst=0; *pszLine && iDst < nMaxOutputLen; pszLine++)
{
if (IS_ASCII(*pszLine))
{
/* No transformation required for ASCII */
pszOut[iDst++] = *pszLine;
}
else if (*pszLine == 0x8e && *(pszLine+1))
{
pszLine++; /* Flush the 0x8e */
pszOut[iDst++] = *pszLine;
}
else if (*(pszLine+1))
{
/* This is a pair of EUC chars... convert them to Shift-JIS
*/
unsigned char leader, trailer;
leader = *(pszLine++) & 0x7F;
trailer = *pszLine & 0x7F;
if((leader & 0x01) != 0) trailer += 0x1F;
else trailer += 0x7D;
if(trailer >= 0x7F) trailer ++;
leader = ((leader - 0x21) >> 1) + 0x81;
if(leader > 0x9F) leader += 0x40;
pszOut[iDst++] = leader;
pszOut[iDst++] = trailer;
}
else
{
/* We should never get here unless a double-byte pair was
* truncated... but just in case...
*/
pszOut[iDst++] = *pszLine;
}
}
pszOut[iDst] = '\0';
return psDBCSInfo->pszDBCSBuf;
}
|