1 /* Access functions for KS C 5601-1992 based encoding conversion.
2 Copyright (C) 1998-2016 Free Software Foundation, Inc.
3 This file is part of the GNU C Library.
5 The GNU C Library is free software; you can redistribute it and/or
6 modify it under the terms of the GNU Lesser General Public
7 License as published by the Free Software Foundation; either
8 version 2.1 of the License, or (at your option) any later version.
10 The GNU C Library is distributed in the hope that it will be useful,
11 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 C Library; if not, see
17 <http://www.gnu.org/licenses/>. */
22 #define KSC5601_HANGUL 2350
23 #define KSC5601_HANJA 4888
24 #define KSC5601_SYMBOL 989
29 /* Structure to map from UCS to KSC. This structure should be packed
37 /* Conversion table. */
38 extern const uint16_t __ksc5601_hangul_to_ucs
[KSC5601_HANGUL
];
39 extern const uint16_t __ksc5601_sym_to_ucs
[];
40 extern const struct map __ksc5601_sym_from_ucs
[KSC5601_SYMBOL
];
41 extern const uint16_t __ksc5601_hanja_to_ucs
[KSC5601_HANJA
];
42 extern const struct map __ksc5601_hanja_from_ucs
[KSC5601_HANJA
];
45 static inline uint32_t
46 __attribute ((always_inline
))
47 ksc5601_to_ucs4 (const unsigned char **s
, size_t avail
, unsigned char offset
)
49 unsigned char ch
= **s
;
53 /* row 94(0x7e) and row 41(0x49) are user-defined area in KS C 5601 */
55 if (ch
< offset
|| (ch
- offset
) <= 0x20 || (ch
- offset
) >= 0x7e
56 || (ch
- offset
) == 0x49)
57 return __UNKNOWN_10646_CHAR
;
63 if (ch2
< offset
|| (ch2
- offset
) <= 0x20 || (ch2
- offset
) >= 0x7f)
64 return __UNKNOWN_10646_CHAR
;
66 idx
= (ch
- offset
- 0x21) * 94 + (ch2
- offset
- 0x21);
68 /* 1410 = 15 * 94 , 3760 = 40 * 94
69 Hangul in KS C 5601 : row 16 - row 40 */
73 if (idx
>= 1410 && idx
< 1410 + KSC5601_HANGUL
)
74 return (__ksc5601_hangul_to_ucs
[idx
- 1410]
75 ?: (*s
-= 2, __UNKNOWN_10646_CHAR
));
77 /* Hanja : row 42 - row 93 : 3854 = 94 * (42-1) */
78 return (__ksc5601_hanja_to_ucs
[idx
- 3854]
79 ?: (*s
-= 2, __UNKNOWN_10646_CHAR
));
81 return __ksc5601_sym_to_ucs
[idx
] ?: (*s
-= 2, __UNKNOWN_10646_CHAR
);
84 return __UNKNOWN_10646_CHAR
;
88 __attribute ((always_inline
))
89 ucs4_to_ksc5601_hangul (uint32_t wch
, unsigned char *s
, size_t avail
)
92 int u
= KSC5601_HANGUL
- 1;
98 try = (uint32_t) __ksc5601_hangul_to_ucs
[m
];
108 s
[0] = (m
/ 94) + 0x30;
109 s
[1] = (m
% 94) + 0x21;
115 return __UNKNOWN_10646_CHAR
;
120 __attribute ((always_inline
))
121 ucs4_to_ksc5601_hanja (uint32_t wch
, unsigned char *s
, size_t avail
)
124 int u
= KSC5601_HANJA
- 1;
130 try = (uint32_t) __ksc5601_hanja_from_ucs
[m
].ucs
;
140 s
[0] = __ksc5601_hanja_from_ucs
[m
].val
[0];
141 s
[1] = __ksc5601_hanja_from_ucs
[m
].val
[1];
147 return __UNKNOWN_10646_CHAR
;
151 __attribute ((always_inline
))
152 ucs4_to_ksc5601_sym (uint32_t wch
, unsigned char *s
, size_t avail
)
155 int u
= KSC5601_SYMBOL
- 1;
161 try = __ksc5601_sym_from_ucs
[m
].ucs
;
171 s
[0] = __ksc5601_sym_from_ucs
[m
].val
[0];
172 s
[1] = __ksc5601_sym_from_ucs
[m
].val
[1];
178 return __UNKNOWN_10646_CHAR
;
183 __attribute ((always_inline
))
184 ucs4_to_ksc5601 (uint32_t wch
, unsigned char *s
, size_t avail
)
186 if (wch
>= 0xac00 && wch
<= 0xd7a3)
187 return ucs4_to_ksc5601_hangul (wch
, s
, avail
);
188 else if ((wch
>= 0x4e00 && wch
<= 0x9fff)
189 || (wch
>= 0xf900 && wch
<= 0xfa0b))
190 return ucs4_to_ksc5601_hanja (wch
, s
, avail
);
192 return ucs4_to_ksc5601_sym (wch
, s
, avail
);
195 #endif /* ksc5601.h */