1 /*
2 * Copyright (C) 1999-2001, 2005, 2007 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, write to the Free Software Foundation, Inc., 51 Franklin Street,
18 * Fifth Floor, Boston, MA 02110-1301, USA.
19 */
20
21 /*
22 * CP949 is EUC-KR, extended with UHC (Unified Hangul Code).
23 *
24 * Some variants of CP949 (in JDK, Windows-2000, ICU) also add:
25 *
26 * 2. Private area mappings:
27 *
28 * code Unicode
29 * 0xC9{A1..FE} U+E000..U+E05D
30 * 0xFE{A1..FE} U+E05E..U+E0BB
31 *
32 * We add them too because, although there are backward compatibility problems
33 * when a character from a private area is moved to an official Unicode code
34 * point, they are useful for some people in practice.
35 */
36
37 #include "uhc_1.h"
38 #include "uhc_2.h"
39
40 static int
cp949_mbtowc(conv_t conv,ucs4_t * pwc,const unsigned char * s,int n)41 cp949_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
42 {
43 unsigned char c = *s;
44 /* Code set 0 (ASCII) */
45 if (c < 0x80)
46 return ascii_mbtowc(conv,pwc,s,n);
47 /* UHC part 1 */
48 if (c >= 0x81 && c <= 0xa0)
49 return uhc_1_mbtowc(conv,pwc,s,n);
50 if (c >= 0xa1 && c < 0xff) {
51 if (n < 2)
52 return RET_TOOFEW(0);
53 {
54 unsigned char c2 = s[1];
55 if (c2 < 0xa1)
56 /* UHC part 2 */
57 return uhc_2_mbtowc(conv,pwc,s,n);
58 else if (c2 < 0xff && !(c == 0xa2 && c2 == 0xe8)) {
59 /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
60 unsigned char buf[2];
61 int ret;
62 buf[0] = c-0x80; buf[1] = c2-0x80;
63 ret = ksc5601_mbtowc(conv,pwc,buf,2);
64 if (ret != RET_ILSEQ)
65 return ret;
66 /* User-defined characters */
67 if (c == 0xc9) {
68 *pwc = 0xe000 + (c2 - 0xa1);
69 return 2;
70 }
71 if (c == 0xfe) {
72 *pwc = 0xe05e + (c2 - 0xa1);
73 return 2;
74 }
75 }
76 }
77 }
78 return RET_ILSEQ;
79 }
80
81 static int
cp949_wctomb(conv_t conv,unsigned char * r,ucs4_t wc,int n)82 cp949_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, int n)
83 {
84 unsigned char buf[2];
85 int ret;
86
87 /* Code set 0 (ASCII) */
88 ret = ascii_wctomb(conv,r,wc,n);
89 if (ret != RET_ILUNI)
90 return ret;
91
92 /* Code set 1 (KS C 5601-1992, now KS X 1001:1998) */
93 if (wc != 0x327e) {
94 ret = ksc5601_wctomb(conv,buf,wc,2);
95 if (ret != RET_ILUNI) {
96 if (ret != 2) abort();
97 if (n < 2)
98 return RET_TOOSMALL;
99 r[0] = buf[0]+0x80;
100 r[1] = buf[1]+0x80;
101 return 2;
102 }
103 }
104
105 /* UHC */
106 if (wc >= 0xac00 && wc < 0xd7a4) {
107 if (wc < 0xc8a5)
108 return uhc_1_wctomb(conv,r,wc,n);
109 else
110 return uhc_2_wctomb(conv,r,wc,n);
111 }
112
113 /* User-defined characters */
114 if (wc >= 0xe000 && wc < 0xe0bc) {
115 if (n < 2)
116 return RET_TOOSMALL;
117 if (wc < 0xe05e) {
118 r[0] = 0xc9;
119 r[1] = wc - 0xe000 + 0xa1;
120 } else {
121 r[0] = 0xfe;
122 r[1] = wc - 0xe05e + 0xa1;
123 }
124 return 2;
125 }
126
127 return RET_ILUNI;
128 }
129