xref: /freebsd/lib/libc/locale/mskanji.c (revision 41059135ce931c0f1014a999ffabc6bc470ce856)
1 /*
2  * Copyright 2013 Garrett D'Amore <garrett@damore.org>
3  * Copyright 2010 Nexenta Systems, Inc.  All rights reserved.
4  * Copyright (c) 2002-2004 Tim J. Robbins. All rights reserved.
5  *
6  *    ja_JP.SJIS locale table for BSD4.4/rune
7  *    version 1.0
8  *    (C) Sin'ichiro MIYATANI / Phase One, Inc
9  *    May 12, 1995
10  *
11  * Copyright (c) 2011 The FreeBSD Foundation
12  * All rights reserved.
13  * Portions of this software were developed by David Chisnall
14  * under sponsorship from the FreeBSD Foundation.
15  *
16  * Redistribution and use in source and binary forms, with or without
17  * modification, are permitted provided that the following conditions
18  * are met:
19  * 1. Redistributions of source code must retain the above copyright
20  *    notice, this list of conditions and the following disclaimer.
21  * 2. Redistributions in binary form must reproduce the above copyright
22  *    notice, this list of conditions and the following disclaimer in the
23  *    documentation and/or other materials provided with the distribution.
24  * 3. All advertising materials mentioning features or use of this software
25  *    must display the following acknowledgement:
26  *      This product includes software developed by Phase One, Inc.
27  * 4. The name of Phase One, Inc. may be used to endorse or promote products
28  *    derived from this software without specific prior written permission.
29  *
30  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
31  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
32  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
33  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
34  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
35  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
36  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
37  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
38  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
39  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
40  * SUCH DAMAGE.
41  */
42 
43 #if defined(LIBC_SCCS) && !defined(lint)
44 static char sccsid[] = "@(#)mskanji.c	1.0 (Phase One) 5/5/95";
45 #endif /* LIBC_SCCS and not lint */
46 #include <sys/cdefs.h>
47 __FBSDID("$FreeBSD$");
48 
49 #include <sys/types.h>
50 #include <errno.h>
51 #include <runetype.h>
52 #include <stdlib.h>
53 #include <string.h>
54 #include <wchar.h>
55 #include "mblocal.h"
56 
57 extern int __mb_sb_limit;
58 
59 static size_t	_MSKanji_mbrtowc(wchar_t * __restrict, const char * __restrict,
60 		    size_t, mbstate_t * __restrict);
61 static int	_MSKanji_mbsinit(const mbstate_t *);
62 static size_t	_MSKanji_wcrtomb(char * __restrict, wchar_t,
63 		    mbstate_t * __restrict);
64 static size_t	_MSKanji_mbsnrtowcs(wchar_t * __restrict,
65 		    const char ** __restrict, size_t, size_t,
66 		    mbstate_t * __restrict);
67 static size_t	_MSKanji_wcsnrtombs(char * __restrict,
68 		    const wchar_t ** __restrict, size_t, size_t,
69 		    mbstate_t * __restrict);
70 
71 typedef struct {
72 	wchar_t	ch;
73 } _MSKanjiState;
74 
75 int
76 _MSKanji_init(struct xlocale_ctype *l, _RuneLocale *rl)
77 {
78 
79 	l->__mbrtowc = _MSKanji_mbrtowc;
80 	l->__wcrtomb = _MSKanji_wcrtomb;
81 	l->__mbsnrtowcs = _MSKanji_mbsnrtowcs;
82 	l->__wcsnrtombs = _MSKanji_wcsnrtombs;
83 	l->__mbsinit = _MSKanji_mbsinit;
84 	l->runes = rl;
85 	l->__mb_cur_max = 2;
86 	l->__mb_sb_limit = 224;
87 	return (0);
88 }
89 
90 static int
91 _MSKanji_mbsinit(const mbstate_t *ps)
92 {
93 
94 	return (ps == NULL || ((const _MSKanjiState *)ps)->ch == 0);
95 }
96 
97 static size_t
98 _MSKanji_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
99     mbstate_t * __restrict ps)
100 {
101 	_MSKanjiState *ms;
102 	wchar_t wc;
103 
104 	ms = (_MSKanjiState *)ps;
105 
106 	if ((ms->ch & ~0xFF) != 0) {
107 		/* Bad conversion state. */
108 		errno = EINVAL;
109 		return ((size_t)-1);
110 	}
111 
112 	if (s == NULL) {
113 		s = "";
114 		n = 1;
115 		pwc = NULL;
116 	}
117 
118 	if (n == 0)
119 		/* Incomplete multibyte sequence */
120 		return ((size_t)-2);
121 
122 	if (ms->ch != 0) {
123 		if (*s == '\0') {
124 			errno = EILSEQ;
125 			return ((size_t)-1);
126 		}
127 		wc = (ms->ch << 8) | (*s & 0xFF);
128 		if (pwc != NULL)
129 			*pwc = wc;
130 		ms->ch = 0;
131 		return (1);
132 	}
133 	wc = *s++ & 0xff;
134 	if ((wc > 0x80 && wc < 0xa0) || (wc >= 0xe0 && wc < 0xfd)) {
135 		if (n < 2) {
136 			/* Incomplete multibyte sequence */
137 			ms->ch = wc;
138 			return ((size_t)-2);
139 		}
140 		if (*s == '\0') {
141 			errno = EILSEQ;
142 			return ((size_t)-1);
143 		}
144 		wc = (wc << 8) | (*s++ & 0xff);
145 		if (pwc != NULL)
146 			*pwc = wc;
147 		return (2);
148 	} else {
149 		if (pwc != NULL)
150 			*pwc = wc;
151 		return (wc == L'\0' ? 0 : 1);
152 	}
153 }
154 
155 static size_t
156 _MSKanji_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
157 {
158 	_MSKanjiState *ms;
159 	int len, i;
160 
161 	ms = (_MSKanjiState *)ps;
162 
163 	if (ms->ch != 0) {
164 		errno = EINVAL;
165 		return ((size_t)-1);
166 	}
167 
168 	if (s == NULL)
169 		/* Reset to initial shift state (no-op) */
170 		return (1);
171 	len = (wc > 0x100) ? 2 : 1;
172 	for (i = len; i-- > 0; )
173 		*s++ = wc >> (i << 3);
174 	return (len);
175 }
176 
177 static size_t
178 _MSKanji_mbsnrtowcs(wchar_t * __restrict dst,
179     const char ** __restrict src, size_t nms,
180     size_t len, mbstate_t * __restrict ps)
181 {
182 	return (__mbsnrtowcs_std(dst, src, nms, len, ps, _MSKanji_mbrtowc));
183 }
184 
185 static size_t
186 _MSKanji_wcsnrtombs(char * __restrict dst,
187     const wchar_t ** __restrict src, size_t nwc,
188     size_t len, mbstate_t * __restrict ps)
189 {
190 	return (__wcsnrtombs_std(dst, src, nwc, len, ps, _MSKanji_wcrtomb));
191 }
192