citrus_big5.c revision 252583 
1/* $FreeBSD: head/lib/libiconv_modules/BIG5/citrus_big5.c 252583 2013-07-03 18:27:45Z peter $ */
2/*	$NetBSD: citrus_big5.c,v 1.12 2008/06/14 16:01:07 tnozaki Exp $	*/
3
4/*-
5 * Copyright (c)2002, 2006 Citrus Project,
6 * All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 */
29
30/*-
31 * Copyright (c) 1993
32 *	The Regents of the University of California.  All rights reserved.
33 *
34 * This code is derived from software contributed to Berkeley by
35 * Paul Borman at Krystal Technologies.
36 *
37 * Redistribution and use in source and binary forms, with or without
38 * modification, are permitted provided that the following conditions
39 * are met:
40 * 1. Redistributions of source code must retain the above copyright
41 *    notice, this list of conditions and the following disclaimer.
42 * 2. Redistributions in binary form must reproduce the above copyright
43 *    notice, this list of conditions and the following disclaimer in the
44 *    documentation and/or other materials provided with the distribution.
45 * 3. Neither the name of the University nor the names of its contributors
46 *    may be used to endorse or promote products derived from this software
47 *    without specific prior written permission.
48 *
49 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
50 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
51 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
52 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
53 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
54 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
55 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
56 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
57 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
58 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
59 * SUCH DAMAGE.
60 */
61
62#include <sys/cdefs.h>
63#include <sys/queue.h>
64#include <sys/types.h>
65
66#include <assert.h>
67#include <errno.h>
68#include <limits.h>
69#include <stddef.h>
70#include <stdint.h>
71#include <stdio.h>
72#include <stdlib.h>
73#include <string.h>
74#include <wchar.h>
75
76#include "citrus_namespace.h"
77#include "citrus_prop.h"
78#include "citrus_types.h"
79#include "citrus_bcs.h"
80#include "citrus_module.h"
81#include "citrus_stdenc.h"
82#include "citrus_big5.h"
83
84/* ----------------------------------------------------------------------
85 * private stuffs used by templates
86 */
87
88typedef struct {
89	int	 chlen;
90	char	 ch[2];
91} _BIG5State;
92
93typedef struct _BIG5Exclude {
94	TAILQ_ENTRY(_BIG5Exclude)	 entry;
95	wint_t				 end;
96	wint_t				 start;
97} _BIG5Exclude;
98
99typedef TAILQ_HEAD(_BIG5ExcludeList, _BIG5Exclude) _BIG5ExcludeList;
100
101typedef struct {
102	_BIG5ExcludeList	 excludes;
103	int			 cell[0x100];
104} _BIG5EncodingInfo;
105
106#define _CEI_TO_EI(_cei_)		(&(_cei_)->ei)
107#define _CEI_TO_STATE(_cei_, _func_)	(_cei_)->states.s_##_func_
108
109#define _FUNCNAME(m)			_citrus_BIG5_##m
110#define _ENCODING_INFO			_BIG5EncodingInfo
111#define _ENCODING_STATE			_BIG5State
112#define _ENCODING_MB_CUR_MAX(_ei_)	2
113#define _ENCODING_IS_STATE_DEPENDENT	0
114#define _STATE_NEEDS_EXPLICIT_INIT(_ps_)	0
115
116
117static __inline void
118/*ARGSUSED*/
119_citrus_BIG5_init_state(_BIG5EncodingInfo * __restrict ei __unused,
120    _BIG5State * __restrict s)
121{
122
123	memset(s, 0, sizeof(*s));
124}
125
126static __inline void
127/*ARGSUSED*/
128_citrus_BIG5_pack_state(_BIG5EncodingInfo * __restrict ei __unused,
129    void * __restrict pspriv,
130    const _BIG5State * __restrict s)
131{
132
133	memcpy(pspriv, (const void *)s, sizeof(*s));
134}
135
136static __inline void
137/*ARGSUSED*/
138_citrus_BIG5_unpack_state(_BIG5EncodingInfo * __restrict ei __unused,
139    _BIG5State * __restrict s,
140    const void * __restrict pspriv)
141{
142
143	memcpy((void *)s, pspriv, sizeof(*s));
144}
145
146static __inline int
147_citrus_BIG5_check(_BIG5EncodingInfo *ei, unsigned int c)
148{
149
150	return ((ei->cell[c & 0xFF] & 0x1) ? 2 : 1);
151}
152
153static __inline int
154_citrus_BIG5_check2(_BIG5EncodingInfo *ei, unsigned int c)
155{
156
157	return ((ei->cell[c & 0xFF] & 0x2) ? 1 : 0);
158}
159
160static __inline int
161_citrus_BIG5_check_excludes(_BIG5EncodingInfo *ei, wint_t c)
162{
163	_BIG5Exclude *exclude;
164
165	TAILQ_FOREACH(exclude, &ei->excludes, entry) {
166		if (c >= exclude->start && c <= exclude->end)
167			return (EILSEQ);
168	}
169	return (0);
170}
171
172static int
173_citrus_BIG5_fill_rowcol(void ** __restrict ctx, const char * __restrict s,
174    uint64_t start, uint64_t end)
175{
176	_BIG5EncodingInfo *ei;
177	uint64_t n;
178	int i;
179
180	if (start > 0xFF || end > 0xFF)
181		return (EINVAL);
182	ei = (_BIG5EncodingInfo *)ctx;
183	i = strcmp("row", s) ? 1 : 0;
184	i = 1 << i;
185	for (n = start; n <= end; ++n)
186		ei->cell[n & 0xFF] |= i;
187	return (0);
188}
189
190static int
191/*ARGSUSED*/
192_citrus_BIG5_fill_excludes(void ** __restrict ctx,
193    const char * __restrict s __unused, uint64_t start, uint64_t end)
194{
195	_BIG5EncodingInfo *ei;
196	_BIG5Exclude *exclude;
197
198	if (start > 0xFFFF || end > 0xFFFF)
199		return (EINVAL);
200	ei = (_BIG5EncodingInfo *)ctx;
201	exclude = TAILQ_LAST(&ei->excludes, _BIG5ExcludeList);
202	if (exclude != NULL && (wint_t)start <= exclude->end)
203		return (EINVAL);
204	exclude = (void *)malloc(sizeof(*exclude));
205	if (exclude == NULL)
206		return (ENOMEM);
207	exclude->start = (wint_t)start;
208	exclude->end = (wint_t)end;
209	TAILQ_INSERT_TAIL(&ei->excludes, exclude, entry);
210
211	return (0);
212}
213
214static const _citrus_prop_hint_t root_hints[] = {
215    _CITRUS_PROP_HINT_NUM("row", &_citrus_BIG5_fill_rowcol),
216    _CITRUS_PROP_HINT_NUM("col", &_citrus_BIG5_fill_rowcol),
217    _CITRUS_PROP_HINT_NUM("excludes", &_citrus_BIG5_fill_excludes),
218    _CITRUS_PROP_HINT_END
219};
220
221static void
222/*ARGSUSED*/
223_citrus_BIG5_encoding_module_uninit(_BIG5EncodingInfo *ei)
224{
225	_BIG5Exclude *exclude;
226
227	while ((exclude = TAILQ_FIRST(&ei->excludes)) != NULL) {
228		TAILQ_REMOVE(&ei->excludes, exclude, entry);
229		free(exclude);
230	}
231}
232
233static int
234/*ARGSUSED*/
235_citrus_BIG5_encoding_module_init(_BIG5EncodingInfo * __restrict ei,
236    const void * __restrict var, size_t lenvar)
237{
238	void *ctx = (void *)ei;
239	const char *s;
240	int err;
241
242	memset((void *)ei, 0, sizeof(*ei));
243	TAILQ_INIT(&ei->excludes);
244
245	if (lenvar > 0 && var != NULL) {
246		s = _bcs_skip_ws_len((const char *)var, &lenvar);
247		if (lenvar > 0 && *s != '\0') {
248			err = _citrus_prop_parse_variable(
249			    root_hints, (void *)ei, s, lenvar);
250			if (err == 0)
251				return (0);
252
253			_citrus_BIG5_encoding_module_uninit(ei);
254			memset((void *)ei, 0, sizeof(*ei));
255			TAILQ_INIT(&ei->excludes);
256		}
257	}
258
259	/* fallback Big5-1984, for backward compatibility. */
260	_citrus_BIG5_fill_rowcol((void **)&ctx, "row", 0xA1, 0xFE);
261	_citrus_BIG5_fill_rowcol((void **)&ctx, "col", 0x40, 0x7E);
262	_citrus_BIG5_fill_rowcol((void **)&ctx, "col", 0xA1, 0xFE);
263
264	return (0);
265}
266
267static int
268/*ARGSUSED*/
269_citrus_BIG5_mbrtowc_priv(_BIG5EncodingInfo * __restrict ei,
270    wchar_t * __restrict pwc,
271    const char ** __restrict s, size_t n,
272    _BIG5State * __restrict psenc,
273    size_t * __restrict nresult)
274{
275	wchar_t wchar;
276	const char *s0;
277	int c, chlenbak;
278
279	s0 = *s;
280
281	if (s0 == NULL) {
282		_citrus_BIG5_init_state(ei, psenc);
283		*nresult = 0;
284		return (0);
285	}
286
287	chlenbak = psenc->chlen;
288
289	/* make sure we have the first byte in the buffer */
290	switch (psenc->chlen) {
291	case 0:
292		if (n < 1)
293			goto restart;
294		psenc->ch[0] = *s0++;
295		psenc->chlen = 1;
296		n--;
297		break;
298	case 1:
299		break;
300	default:
301		/* illegal state */
302		goto ilseq;
303	}
304
305	c = _citrus_BIG5_check(ei, psenc->ch[0] & 0xff);
306	if (c == 0)
307		goto ilseq;
308	while (psenc->chlen < c) {
309		if (n < 1) {
310			goto restart;
311		}
312		psenc->ch[psenc->chlen] = *s0++;
313		psenc->chlen++;
314		n--;
315	}
316
317	switch (c) {
318	case 1:
319		wchar = psenc->ch[0] & 0xff;
320		break;
321	case 2:
322		if (!_citrus_BIG5_check2(ei, psenc->ch[1] & 0xff))
323			goto ilseq;
324		wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff);
325		break;
326	default:
327		/* illegal state */
328		goto ilseq;
329	}
330
331	if (_citrus_BIG5_check_excludes(ei, (wint_t)wchar) != 0)
332		goto ilseq;
333
334	*s = s0;
335	psenc->chlen = 0;
336	if (pwc)
337		*pwc = wchar;
338	*nresult = wchar ? c - chlenbak : 0;
339
340	return (0);
341
342ilseq:
343	psenc->chlen = 0;
344	*nresult = (size_t)-1;
345	return (EILSEQ);
346
347restart:
348	*s = s0;
349	*nresult = (size_t)-2;
350	return (0);
351}
352
353static int
354/*ARGSUSED*/
355_citrus_BIG5_wcrtomb_priv(_BIG5EncodingInfo * __restrict ei,
356    char * __restrict s,
357    size_t n, wchar_t wc, _BIG5State * __restrict psenc __unused,
358    size_t * __restrict nresult)
359{
360	unsigned char l;
361	int ret;
362
363	/* check invalid sequence */
364	if (wc & ~0xffff ||
365	    _citrus_BIG5_check_excludes(ei, (wint_t)wc) != 0) {
366		ret = EILSEQ;
367		goto err;
368	}
369
370	if (wc & 0x8000) {
371		if (_citrus_BIG5_check(ei, (wc >> 8) & 0xff) != 2 ||
372		    !_citrus_BIG5_check2(ei, wc & 0xff)) {
373			ret = EILSEQ;
374			goto err;
375		}
376		l = 2;
377	} else {
378		if (wc & ~0xff || !_citrus_BIG5_check(ei, wc & 0xff)) {
379			ret = EILSEQ;
380			goto err;
381		}
382		l = 1;
383	}
384
385	if (n < l) {
386		/* bound check failure */
387		ret = E2BIG;
388		goto err;
389	}
390
391	if (l == 2) {
392		s[0] = (wc >> 8) & 0xff;
393		s[1] = wc & 0xff;
394	} else
395		s[0] = wc & 0xff;
396
397	*nresult = l;
398
399	return (0);
400
401err:
402	*nresult = (size_t)-1;
403	return (ret);
404}
405
406static __inline int
407/*ARGSUSED*/
408_citrus_BIG5_stdenc_wctocs(_BIG5EncodingInfo * __restrict ei __unused,
409    _csid_t * __restrict csid,
410    _index_t * __restrict idx, wchar_t wc)
411{
412
413	*csid = (wc < 0x100) ? 0 : 1;
414	*idx = (_index_t)wc;
415
416	return (0);
417}
418
419static __inline int
420/*ARGSUSED*/
421_citrus_BIG5_stdenc_cstowc(_BIG5EncodingInfo * __restrict ei __unused,
422    wchar_t * __restrict wc,
423    _csid_t csid, _index_t idx)
424{
425
426	switch (csid) {
427	case 0:
428	case 1:
429		*wc = (wchar_t)idx;
430		break;
431	default:
432		return (EILSEQ);
433	}
434
435	return (0);
436}
437
438static __inline int
439/*ARGSUSED*/
440_citrus_BIG5_stdenc_get_state_desc_generic(_BIG5EncodingInfo * __restrict ei __unused,
441    _BIG5State * __restrict psenc,
442    int * __restrict rstate)
443{
444
445	*rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL :
446	    _STDENC_SDGEN_INCOMPLETE_CHAR;
447	return (0);
448}
449
450/* ----------------------------------------------------------------------
451 * public interface for stdenc
452 */
453
454_CITRUS_STDENC_DECLS(BIG5);
455_CITRUS_STDENC_DEF_OPS(BIG5);
456
457#include "citrus_stdenc_template.h"
458