1 /* $NetBSD: citrus_gbk2k.c,v 1.8 2013/05/28 16:57:56 joerg Exp $ */
4 * Copyright (c)2003 Citrus Project,
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 #include <sys/cdefs.h>
30 #if defined(LIBC_SCCS) && !defined(lint)
31 __RCSID("$NetBSD: citrus_gbk2k.c,v 1.8 2013/05/28 16:57:56 joerg Exp $");
32 #endif /* LIBC_SCCS and not lint */
41 #include <sys/types.h>
44 #include "citrus_namespace.h"
45 #include "citrus_types.h"
46 #include "citrus_bcs.h"
47 #include "citrus_module.h"
48 #include "citrus_ctype.h"
49 #include "citrus_stdenc.h"
50 #include "citrus_gbk2k.h"
53 /* ----------------------------------------------------------------------
54 * private stuffs used by templates
57 typedef struct _GBK2KState
{
67 _GBK2KEncodingInfo ei
;
69 /* for future multi-locale facility */
72 _GBK2KState s_mbrtowc
;
74 _GBK2KState s_mbsrtowcs
;
75 _GBK2KState s_mbsnrtowcs
;
76 _GBK2KState s_wcrtomb
;
77 _GBK2KState s_wcsrtombs
;
78 _GBK2KState s_wcsnrtombs
;
83 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
84 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
86 #define _FUNCNAME(m) _citrus_GBK2K_##m
87 #define _ENCODING_INFO _GBK2KEncodingInfo
88 #define _CTYPE_INFO _GBK2KCTypeInfo
89 #define _ENCODING_STATE _GBK2KState
90 #define _ENCODING_MB_CUR_MAX(_ei_) (_ei_)->mb_cur_max
91 #define _ENCODING_IS_STATE_DEPENDENT 0
92 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
96 _citrus_GBK2K_init_state(_GBK2KEncodingInfo
* __restrict ei
,
97 _GBK2KState
* __restrict s
)
99 memset(s
, 0, sizeof(*s
));
104 _citrus_GBK2K_pack_state(_GBK2KEncodingInfo
* __restrict ei
,
105 void * __restrict pspriv
,
106 const _GBK2KState
* __restrict s
)
108 memcpy(pspriv
, (const void *)s
, sizeof(*s
));
113 _citrus_GBK2K_unpack_state(_GBK2KEncodingInfo
* __restrict ei
,
114 _GBK2KState
* __restrict s
,
115 const void * __restrict pspriv
)
117 memcpy((void *)s
, pspriv
, sizeof(*s
));
121 _mb_singlebyte(int c
)
131 return (0x81 <= c
&& c
<= 0xfe);
138 return ((0x40 <= c
&& c
<= 0x7e) || (0x80 <= c
&& c
<= 0xfe));
145 return (0x30 <= c
&& c
<= 0x39);
153 c
= (u_int32_t
)v
; /* XXX */
154 if (!(c
& 0xffffff00))
156 if (!(c
& 0xffff0000))
161 #define _PSENC (psenc->ch[psenc->chlen - 1])
162 #define _PUSH_PSENC(c) (psenc->ch[psenc->chlen++] = (c))
165 _citrus_GBK2K_mbrtowc_priv(_GBK2KEncodingInfo
* __restrict ei
,
166 wchar_t * __restrict pwc
,
167 const char ** __restrict s
, size_t n
,
168 _GBK2KState
* __restrict psenc
,
169 size_t * __restrict nresult
)
175 _DIAGASSERT(ei
!= NULL
);
176 /* pwc may be NULL */
177 _DIAGASSERT(s
!= NULL
);
178 _DIAGASSERT(psenc
!= NULL
);
183 /* _citrus_GBK2K_init_state(ei, psenc); */
189 chlenbak
= psenc
->chlen
;
191 switch (psenc
->chlen
) {
193 if (!_mb_leadbyte (_PSENC
))
197 if (!_mb_surrogate(_PSENC
) || _mb_trailbyte(_PSENC
))
201 if (!_mb_leadbyte (_PSENC
))
216 switch (psenc
->chlen
) {
218 if (_mb_singlebyte(_PSENC
))
220 if (_mb_leadbyte (_PSENC
))
224 if (_mb_trailbyte (_PSENC
))
226 if (ei
->mb_cur_max
== 4 &&
227 _mb_surrogate (_PSENC
))
231 if (_mb_leadbyte (_PSENC
))
235 if (_mb_surrogate (_PSENC
))
246 wc
= (wc
<< 8) | (*s1
++ & 0xff);
251 *nresult
= (wc
== 0) ? 0 : psenc
->chlen
- chlenbak
;
252 /* _citrus_GBK2K_init_state(ei, psenc); */
259 *nresult
= (size_t)-2;
267 *nresult
= (size_t)-1;
272 _citrus_GBK2K_wcrtomb_priv(_GBK2KEncodingInfo
* __restrict ei
,
273 char * __restrict s
, size_t n
, wchar_t wc
,
274 _GBK2KState
* __restrict psenc
,
275 size_t * __restrict nresult
)
279 _DIAGASSERT(ei
!= NULL
);
280 _DIAGASSERT(s
!= NULL
);
281 _DIAGASSERT(psenc
!= NULL
);
283 if (psenc
->chlen
!= 0) {
296 if (!_mb_singlebyte(_PUSH_PSENC(wc
))) {
302 if (!_mb_leadbyte (_PUSH_PSENC(wc
>> 8)) ||
303 !_mb_trailbyte (_PUSH_PSENC(wc
))) {
309 if (ei
->mb_cur_max
!= 4 ||
310 !_mb_leadbyte (_PUSH_PSENC(wc
>> 24)) ||
311 !_mb_surrogate (_PUSH_PSENC(wc
>> 16)) ||
312 !_mb_leadbyte (_PUSH_PSENC(wc
>> 8)) ||
313 !_mb_surrogate (_PUSH_PSENC(wc
))) {
320 _DIAGASSERT(len
== psenc
->chlen
);
322 memcpy(s
, psenc
->ch
, psenc
->chlen
);
323 *nresult
= psenc
->chlen
;
324 /* _citrus_GBK2K_init_state(ei, psenc); */
330 *nresult
= (size_t)-1;
336 _citrus_GBK2K_stdenc_wctocs(_GBK2KEncodingInfo
* __restrict ei
,
337 _csid_t
* __restrict csid
,
338 _index_t
* __restrict idx
, wchar_t wc
)
342 _DIAGASSERT(csid
!= NULL
&& idx
!= NULL
);
344 if ((u_int32_t
)wc
<0x80) {
348 } else if ((u_int32_t
)wc
>=0x10000) {
353 ch
= (u_int8_t
)(wc
>> 8);
355 if (ch
>=0xA1 && cl
>=0xA1) {
358 *idx
= (_index_t
)wc
& 0x7F7FU
;
360 /* extended area (0x8140-) */
371 _citrus_GBK2K_stdenc_cstowc(_GBK2KEncodingInfo
* __restrict ei
,
372 wchar_t * __restrict wc
,
373 _csid_t csid
, _index_t idx
)
376 _DIAGASSERT(wc
!= NULL
);
385 *wc
= (wchar_t)idx
| 0x8080U
;
393 if (ei
->mb_cur_max
!= 4)
406 _citrus_GBK2K_stdenc_get_state_desc_generic(_GBK2KEncodingInfo
* __restrict ei
,
407 _GBK2KState
* __restrict psenc
,
408 int * __restrict rstate
)
411 if (psenc
->chlen
== 0)
412 *rstate
= _STDENC_SDGEN_INITIAL
;
414 *rstate
= _STDENC_SDGEN_INCOMPLETE_CHAR
;
421 _citrus_GBK2K_encoding_module_init(_GBK2KEncodingInfo
* __restrict ei
,
422 const void * __restrict var
, size_t lenvar
)
426 _DIAGASSERT(ei
!= NULL
);
429 #define MATCH(x, act) \
431 if (lenvar >= (sizeof(#x)-1) && \
432 _bcs_strncasecmp(p, #x, sizeof(#x)-1) == 0) { \
434 lenvar -= sizeof(#x)-1; \
437 } while (/*CONSTCOND*/0)
438 memset((void *)ei
, 0, sizeof(*ei
));
441 switch (_bcs_tolower(*p
)) {
443 MATCH("2byte", ei
->mb_cur_max
= 2);
455 _citrus_GBK2K_encoding_module_uninit(_GBK2KEncodingInfo
*ei
)
460 /* ----------------------------------------------------------------------
461 * public interface for ctype
464 _CITRUS_CTYPE_DECLS(GBK2K
);
465 _CITRUS_CTYPE_DEF_OPS(GBK2K
);
467 #include "citrus_ctype_template.h"
469 /* ----------------------------------------------------------------------
470 * public interface for stdenc
473 _CITRUS_STDENC_DECLS(GBK2K
);
474 _CITRUS_STDENC_DEF_OPS(GBK2K
);
476 #include "citrus_stdenc_template.h"