File:  [ELWIX - Embedded LightWeight unIX -] / embedaddon / libiconv / lib / cp949.h
Revision 1.1.1.2 (vendor branch): download - view: text, annotated - select for diffs - revision graph
Wed Mar 17 13:38:46 2021 UTC (3 years, 3 months ago) by misho
Branches: libiconv, MAIN
CVS tags: v1_16p0, HEAD
libiconv 1.16

    1: /*
    2:  * Copyright (C) 1999-2001, 2005, 2007, 2016 Free Software Foundation, Inc.
    3:  * This file is part of the GNU LIBICONV Library.
    4:  *
    5:  * The GNU LIBICONV Library is free software; you can redistribute it
    6:  * and/or modify it under the terms of the GNU Library General Public
    7:  * License as published by the Free Software Foundation; either version 2
    8:  * of the License, or (at your option) any later version.
    9:  *
   10:  * The GNU LIBICONV Library is distributed in the hope that it will be
   11:  * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
   12:  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   13:  * Library General Public License for more details.
   14:  *
   15:  * You should have received a copy of the GNU Library General Public
   16:  * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
   17:  * If not, see <https://www.gnu.org/licenses/>.
   18:  */
   19: 
   20: /*
   21:  * CP949 is EUC-KR, extended with UHC (Unified Hangul Code).
   22:  *
   23:  * Some variants of CP949 (in JDK, Windows-2000, ICU) also add:
   24:  *
   25:  * 2. Private area mappings:
   26:  *
   27:  *        code           Unicode
   28:  *    0xC9{A1..FE}   U+E000..U+E05D
   29:  *    0xFE{A1..FE}   U+E05E..U+E0BB
   30:  *
   31:  * We add them too because, although there are backward compatibility problems
   32:  * when a character from a private area is moved to an official Unicode code
   33:  * point, they are useful for some people in practice.
   34:  */
   35: 
   36: #include "uhc_1.h"
   37: #include "uhc_2.h"
   38: 
   39: static int
   40: cp949_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, size_t n)
   41: {
   42:   unsigned char c = *s;
   43:   /* Code set 0 (ASCII) */
   44:   if (c < 0x80)
   45:     return ascii_mbtowc(conv,pwc,s,n);
   46:   /* UHC part 1 */
   47:   if (c >= 0x81 && c <= 0xa0)
   48:     return uhc_1_mbtowc(conv,pwc,s,n);
   49:   if (c >= 0xa1 && c < 0xff) {
   50:     if (n < 2)
   51:       return RET_TOOFEW(0);
   52:     {
   53:       unsigned char c2 = s[1];
   54:       if (c2 < 0xa1)
   55:         /* UHC part 2 */
   56:         return uhc_2_mbtowc(conv,pwc,s,n);
   57:       else if (c2 < 0xff && !(c == 0xa2 && c2 == 0xe8)) {
   58:         /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
   59:         unsigned char buf[2];
   60:         int ret;
   61:         buf[0] = c-0x80; buf[1] = c2-0x80;
   62:         ret = ksc5601_mbtowc(conv,pwc,buf,2);
   63:         if (ret != RET_ILSEQ)
   64:           return ret;
   65:         /* User-defined characters */
   66:         if (c == 0xc9) {
   67:           *pwc = 0xe000 + (c2 - 0xa1);
   68:           return 2;
   69:         }
   70:         if (c == 0xfe) {
   71:           *pwc = 0xe05e + (c2 - 0xa1);
   72:           return 2;
   73:         }
   74:       }
   75:     }
   76:   }
   77:   return RET_ILSEQ;
   78: }
   79: 
   80: static int
   81: cp949_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n)
   82: {
   83:   unsigned char buf[2];
   84:   int ret;
   85: 
   86:   /* Code set 0 (ASCII) */
   87:   ret = ascii_wctomb(conv,r,wc,n);
   88:   if (ret != RET_ILUNI)
   89:     return ret;
   90: 
   91:   /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
   92:   if (wc != 0x327e) {
   93:     ret = ksc5601_wctomb(conv,buf,wc,2);
   94:     if (ret != RET_ILUNI) {
   95:       if (ret != 2) abort();
   96:       if (n < 2)
   97:         return RET_TOOSMALL;
   98:       r[0] = buf[0]+0x80;
   99:       r[1] = buf[1]+0x80;
  100:       return 2;
  101:     }
  102:   }
  103: 
  104:   /* UHC */
  105:   if (wc >= 0xac00 && wc < 0xd7a4) {
  106:     if (wc < 0xc8a5)
  107:       return uhc_1_wctomb(conv,r,wc,n);
  108:     else
  109:       return uhc_2_wctomb(conv,r,wc,n);
  110:   }
  111: 
  112:   /* User-defined characters */
  113:   if (wc >= 0xe000 && wc < 0xe0bc) {
  114:     if (n < 2)
  115:       return RET_TOOSMALL;
  116:     if (wc < 0xe05e) {
  117:       r[0] = 0xc9;
  118:       r[1] = wc - 0xe000 + 0xa1;
  119:     } else {
  120:       r[0] = 0xfe;
  121:       r[1] = wc - 0xe05e + 0xa1;
  122:     }
  123:     return 2;
  124:   }
  125: 
  126:   return RET_ILUNI;
  127: }

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>