xref: /freebsd/lib/libc/locale/mskanji.c (revision 370e009188ba90c3290b1479aa06ec98b66e140a)
1 /*-
2  * SPDX-License-Identifier: BSD-4-Clause
3  *
4  * Copyright 2013 Garrett D'Amore <garrett@damore.org>
5  * Copyright 2010 Nexenta Systems, Inc.  All rights reserved.
6  * Copyright (c) 2002-2004 Tim J. Robbins. All rights reserved.
7  *
8  *    ja_JP.SJIS locale table for BSD4.4/rune
9  *    version 1.0
10  *    (C) Sin'ichiro MIYATANI / Phase One, Inc
11  *    May 12, 1995
12  *
13  * Copyright (c) 2011 The FreeBSD Foundation
14  *
15  * Portions of this software were developed by David Chisnall
16  * under sponsorship from the FreeBSD Foundation.
17  *
18  * Redistribution and use in source and binary forms, with or without
19  * modification, are permitted provided that the following conditions
20  * are met:
21  * 1. Redistributions of source code must retain the above copyright
22  *    notice, this list of conditions and the following disclaimer.
23  * 2. Redistributions in binary form must reproduce the above copyright
24  *    notice, this list of conditions and the following disclaimer in the
25  *    documentation and/or other materials provided with the distribution.
26  * 3. All advertising materials mentioning features or use of this software
27  *    must display the following acknowledgement:
28  *      This product includes software developed by Phase One, Inc.
29  * 4. The name of Phase One, Inc. may be used to endorse or promote products
30  *    derived from this software without specific prior written permission.
31  *
32  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
33  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
34  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
35  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
36  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
37  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
38  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
39  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
40  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
41  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
42  * SUCH DAMAGE.
43  */
44 
45 #if defined(LIBC_SCCS) && !defined(lint)
46 static char sccsid[] = "@(#)mskanji.c	1.0 (Phase One) 5/5/95";
47 #endif /* LIBC_SCCS and not lint */
48 #include <sys/cdefs.h>
49 __FBSDID("$FreeBSD$");
50 
51 #include <sys/types.h>
52 #include <errno.h>
53 #include <runetype.h>
54 #include <stdlib.h>
55 #include <string.h>
56 #include <wchar.h>
57 #include "mblocal.h"
58 
59 extern int __mb_sb_limit;
60 
61 static size_t	_MSKanji_mbrtowc(wchar_t * __restrict, const char * __restrict,
62 		    size_t, mbstate_t * __restrict);
63 static int	_MSKanji_mbsinit(const mbstate_t *);
64 static size_t	_MSKanji_wcrtomb(char * __restrict, wchar_t,
65 		    mbstate_t * __restrict);
66 static size_t	_MSKanji_mbsnrtowcs(wchar_t * __restrict,
67 		    const char ** __restrict, size_t, size_t,
68 		    mbstate_t * __restrict);
69 static size_t	_MSKanji_wcsnrtombs(char * __restrict,
70 		    const wchar_t ** __restrict, size_t, size_t,
71 		    mbstate_t * __restrict);
72 
73 typedef struct {
74 	wchar_t	ch;
75 } _MSKanjiState;
76 
77 int
78 _MSKanji_init(struct xlocale_ctype *l, _RuneLocale *rl)
79 {
80 
81 	l->__mbrtowc = _MSKanji_mbrtowc;
82 	l->__wcrtomb = _MSKanji_wcrtomb;
83 	l->__mbsnrtowcs = _MSKanji_mbsnrtowcs;
84 	l->__wcsnrtombs = _MSKanji_wcsnrtombs;
85 	l->__mbsinit = _MSKanji_mbsinit;
86 	l->runes = rl;
87 	l->__mb_cur_max = 2;
88 	l->__mb_sb_limit = 224;
89 	return (0);
90 }
91 
92 static int
93 _MSKanji_mbsinit(const mbstate_t *ps)
94 {
95 
96 	return (ps == NULL || ((const _MSKanjiState *)ps)->ch == 0);
97 }
98 
99 static size_t
100 _MSKanji_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
101     mbstate_t * __restrict ps)
102 {
103 	_MSKanjiState *ms;
104 	wchar_t wc;
105 
106 	ms = (_MSKanjiState *)ps;
107 
108 	if ((ms->ch & ~0xFF) != 0) {
109 		/* Bad conversion state. */
110 		errno = EINVAL;
111 		return ((size_t)-1);
112 	}
113 
114 	if (s == NULL) {
115 		s = "";
116 		n = 1;
117 		pwc = NULL;
118 	}
119 
120 	if (n == 0)
121 		/* Incomplete multibyte sequence */
122 		return ((size_t)-2);
123 
124 	if (ms->ch != 0) {
125 		if (*s == '\0') {
126 			errno = EILSEQ;
127 			return ((size_t)-1);
128 		}
129 		wc = (ms->ch << 8) | (*s & 0xFF);
130 		if (pwc != NULL)
131 			*pwc = wc;
132 		ms->ch = 0;
133 		return (1);
134 	}
135 	wc = *s++ & 0xff;
136 	if ((wc > 0x80 && wc < 0xa0) || (wc >= 0xe0 && wc < 0xfd)) {
137 		if (n < 2) {
138 			/* Incomplete multibyte sequence */
139 			ms->ch = wc;
140 			return ((size_t)-2);
141 		}
142 		if (*s == '\0') {
143 			errno = EILSEQ;
144 			return ((size_t)-1);
145 		}
146 		wc = (wc << 8) | (*s++ & 0xff);
147 		if (pwc != NULL)
148 			*pwc = wc;
149 		return (2);
150 	} else {
151 		if (pwc != NULL)
152 			*pwc = wc;
153 		return (wc == L'\0' ? 0 : 1);
154 	}
155 }
156 
157 static size_t
158 _MSKanji_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
159 {
160 	_MSKanjiState *ms;
161 	int len, i;
162 
163 	ms = (_MSKanjiState *)ps;
164 
165 	if (ms->ch != 0) {
166 		errno = EINVAL;
167 		return ((size_t)-1);
168 	}
169 
170 	if (s == NULL)
171 		/* Reset to initial shift state (no-op) */
172 		return (1);
173 	len = (wc > 0x100) ? 2 : 1;
174 	for (i = len; i-- > 0; )
175 		*s++ = wc >> (i << 3);
176 	return (len);
177 }
178 
179 static size_t
180 _MSKanji_mbsnrtowcs(wchar_t * __restrict dst,
181     const char ** __restrict src, size_t nms,
182     size_t len, mbstate_t * __restrict ps)
183 {
184 	return (__mbsnrtowcs_std(dst, src, nms, len, ps, _MSKanji_mbrtowc));
185 }
186 
187 static size_t
188 _MSKanji_wcsnrtombs(char * __restrict dst,
189     const wchar_t ** __restrict src, size_t nwc,
190     size_t len, mbstate_t * __restrict ps)
191 {
192 	return (__wcsnrtombs_std(dst, src, nwc, len, ps, _MSKanji_wcrtomb));
193 }
194