2 * Copyright (C) 1999-2002, 2006, 2016 Free Software Foundation, Inc.
3 * This file is part of the GNU LIBICONV Library.
5 * The GNU LIBICONV Library is free software; you can redistribute it
6 * and/or modify it under the terms of the GNU Lesser General Public
7 * License as published by the Free Software Foundation; either version 2.1
8 * of the License, or (at your option) any later version.
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 * Lesser General Public License for more details.
15 * You should have received a copy of the GNU Lesser General Public
16 * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
17 * If not, see <https://www.gnu.org/licenses/>.
25 * BIG5-HKSCS:1999 can be downloaded from
26 * http://www.info.gov.hk/digital21/eng/hkscs/download.html
27 * http://www.info.gov.hk/digital21/eng/hkscs/index.html
29 * It extends BIG5 (without the rows 0xC6..0xC7) through the ranges
31 * 0x{88..8D}{40..7E,A1..FE} 641 characters
32 * 0x{8E..A0}{40..7E,A1..FE} 2898 characters
33 * 0x{C6..C8}{40..7E,A1..FE} 359 characters
34 * 0xF9{D6..FE} 41 characters
35 * 0x{FA..FE}{40..7E,A1..FE} 763 characters
37 * Note that some HKSCS characters are not contained in Unicode 3.2
38 * and are therefore best represented as sequences of Unicode characters:
39 * 0x8862 U+00CA U+0304 LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND MACRON
40 * 0x8864 U+00CA U+030C LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND CARON
41 * 0x88A3 U+00EA U+0304 LATIN SMALL LETTER E WITH CIRCUMFLEX AND MACRON
42 * 0x88A5 U+00EA U+030C LATIN SMALL LETTER E WITH CIRCUMFLEX AND CARON
45 #include "hkscs1999.h"
49 big5hkscs1999_mbtowc (conv_t conv
, ucs4_t
*pwc
, const unsigned char *s
, size_t n
)
51 ucs4_t last_wc
= conv
->istate
;
53 /* Output the buffered character. */
56 return 0; /* Don't advance the input pointer. */
59 /* Code set 0 (ASCII) */
61 return ascii_mbtowc(conv
,pwc
,s
,n
);
62 /* Code set 1 (BIG5 extended) */
63 if (c
>= 0xa1 && c
< 0xff) {
67 unsigned char c2
= s
[1];
68 if ((c2
>= 0x40 && c2
< 0x7f) || (c2
>= 0xa1 && c2
< 0xff)) {
69 if (!((c
== 0xc6 && c2
>= 0xa1) || c
== 0xc7)) {
70 int ret
= big5_mbtowc(conv
,pwc
,s
,2);
78 int ret
= hkscs1999_mbtowc(conv
,pwc
,s
,n
);
86 unsigned char c2
= s
[1];
87 if (c2
== 0x62 || c2
== 0x64 || c2
== 0xa3 || c2
== 0xa5) {
88 /* It's a composed character. */
89 ucs4_t wc1
= ((c2
>> 3) << 2) + 0x009a; /* = 0x00ca or 0x00ea */
90 ucs4_t wc2
= ((c2
& 6) << 2) + 0x02fc; /* = 0x0304 or 0x030c */
91 /* We cannot output two Unicode characters at once. So,
92 output the first character and buffer the second one. */
103 #define big5hkscs1999_flushwc normal_flushwc
106 big5hkscs1999_wctomb (conv_t conv
, unsigned char *r
, ucs4_t wc
, size_t n
)
109 unsigned char last
= conv
->ostate
;
112 /* last is = 0x66 or = 0xa7. */
113 if (wc
== 0x0304 || wc
== 0x030c) {
114 /* Output the combined character. */
117 r
[1] = last
+ ((wc
& 24) >> 2) - 4; /* = 0x62 or 0x64 or 0xa3 or 0xa5 */
124 /* Output the buffered character. */
133 /* Code set 0 (ASCII) */
135 /* Plain ASCII character. */
137 r
[0] = (unsigned char) wc
;
143 unsigned char buf
[2];
146 /* Code set 1 (BIG5 extended) */
147 ret
= big5_wctomb(conv
,buf
,wc
,2);
148 if (ret
!= RET_ILUNI
) {
149 if (ret
!= 2) abort();
150 if (!((buf
[0] == 0xc6 && buf
[1] >= 0xa1) || buf
[0] == 0xc7)) {
160 ret
= hkscs1999_wctomb(conv
,buf
,wc
,2);
161 if (ret
!= RET_ILUNI
) {
162 if (ret
!= 2) abort();
163 if ((wc
& ~0x0020) == 0x00ca) {
164 /* A possible first character of a multi-character sequence. We have to
166 if (!(buf
[0] == 0x88 && (buf
[1] == 0x66 || buf
[1] == 0xa7))) abort();
167 conv
->ostate
= buf
[1]; /* = 0x66 or = 0xa7 */
183 big5hkscs1999_reset (conv_t conv
, unsigned char *r
, size_t n
)
185 unsigned char last
= conv
->ostate
;
192 /* conv->ostate = 0; will be done by the caller */