xref: /freebsd/lib/libc/locale/mskanji.c (revision dc36d6f9bb1753f3808552f3afd30eda9a7b206a)
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 #include <sys/types.h>
46 #include <errno.h>
47 #include <runetype.h>
48 #include <stdlib.h>
49 #include <string.h>
50 #include <wchar.h>
51 #include "mblocal.h"
52 
53 extern int __mb_sb_limit;
54 
55 static size_t	_MSKanji_mbrtowc(wchar_t * __restrict, const char * __restrict,
56 		    size_t, mbstate_t * __restrict);
57 static int	_MSKanji_mbsinit(const mbstate_t *);
58 static size_t	_MSKanji_wcrtomb(char * __restrict, wchar_t,
59 		    mbstate_t * __restrict);
60 static size_t	_MSKanji_mbsnrtowcs(wchar_t * __restrict,
61 		    const char ** __restrict, size_t, size_t,
62 		    mbstate_t * __restrict);
63 static size_t	_MSKanji_wcsnrtombs(char * __restrict,
64 		    const wchar_t ** __restrict, size_t, size_t,
65 		    mbstate_t * __restrict);
66 
67 typedef struct {
68 	wchar_t	ch;
69 } _MSKanjiState;
70 
71 int
_MSKanji_init(struct xlocale_ctype * l,_RuneLocale * rl)72 _MSKanji_init(struct xlocale_ctype *l, _RuneLocale *rl)
73 {
74 
75 	l->__mbrtowc = _MSKanji_mbrtowc;
76 	l->__wcrtomb = _MSKanji_wcrtomb;
77 	l->__mbsnrtowcs = _MSKanji_mbsnrtowcs;
78 	l->__wcsnrtombs = _MSKanji_wcsnrtombs;
79 	l->__mbsinit = _MSKanji_mbsinit;
80 	l->runes = rl;
81 	l->__mb_cur_max = 2;
82 	l->__mb_sb_limit = 224;
83 	return (0);
84 }
85 
86 static int
_MSKanji_mbsinit(const mbstate_t * ps)87 _MSKanji_mbsinit(const mbstate_t *ps)
88 {
89 
90 	return (ps == NULL || ((const _MSKanjiState *)ps)->ch == 0);
91 }
92 
93 static size_t
_MSKanji_mbrtowc(wchar_t * __restrict pwc,const char * __restrict s,size_t n,mbstate_t * __restrict ps)94 _MSKanji_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
95     mbstate_t * __restrict ps)
96 {
97 	_MSKanjiState *ms;
98 	wchar_t wc;
99 
100 	ms = (_MSKanjiState *)ps;
101 
102 	if ((ms->ch & ~0xFF) != 0) {
103 		/* Bad conversion state. */
104 		errno = EINVAL;
105 		return ((size_t)-1);
106 	}
107 
108 	if (s == NULL) {
109 		s = "";
110 		n = 1;
111 		pwc = NULL;
112 	}
113 
114 	if (n == 0)
115 		/* Incomplete multibyte sequence */
116 		return ((size_t)-2);
117 
118 	if (ms->ch != 0) {
119 		if (*s == '\0') {
120 			errno = EILSEQ;
121 			return ((size_t)-1);
122 		}
123 		wc = (ms->ch << 8) | (*s & 0xFF);
124 		if (pwc != NULL)
125 			*pwc = wc;
126 		ms->ch = 0;
127 		return (1);
128 	}
129 	wc = *s++ & 0xff;
130 	if ((wc > 0x80 && wc < 0xa0) || (wc >= 0xe0 && wc < 0xfd)) {
131 		if (n < 2) {
132 			/* Incomplete multibyte sequence */
133 			ms->ch = wc;
134 			return ((size_t)-2);
135 		}
136 		if (*s == '\0') {
137 			errno = EILSEQ;
138 			return ((size_t)-1);
139 		}
140 		wc = (wc << 8) | (*s++ & 0xff);
141 		if (pwc != NULL)
142 			*pwc = wc;
143 		return (2);
144 	} else {
145 		if (pwc != NULL)
146 			*pwc = wc;
147 		return (wc == L'\0' ? 0 : 1);
148 	}
149 }
150 
151 static size_t
_MSKanji_wcrtomb(char * __restrict s,wchar_t wc,mbstate_t * __restrict ps)152 _MSKanji_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
153 {
154 	_MSKanjiState *ms;
155 	int len, i;
156 
157 	ms = (_MSKanjiState *)ps;
158 
159 	if (ms->ch != 0) {
160 		errno = EINVAL;
161 		return ((size_t)-1);
162 	}
163 
164 	if (s == NULL)
165 		/* Reset to initial shift state (no-op) */
166 		return (1);
167 	len = (wc > 0x100) ? 2 : 1;
168 	for (i = len; i-- > 0; )
169 		*s++ = wc >> (i << 3);
170 	return (len);
171 }
172 
173 static size_t
_MSKanji_mbsnrtowcs(wchar_t * __restrict dst,const char ** __restrict src,size_t nms,size_t len,mbstate_t * __restrict ps)174 _MSKanji_mbsnrtowcs(wchar_t * __restrict dst,
175     const char ** __restrict src, size_t nms,
176     size_t len, mbstate_t * __restrict ps)
177 {
178 	return (__mbsnrtowcs_std(dst, src, nms, len, ps, _MSKanji_mbrtowc));
179 }
180 
181 static size_t
_MSKanji_wcsnrtombs(char * __restrict dst,const wchar_t ** __restrict src,size_t nwc,size_t len,mbstate_t * __restrict ps)182 _MSKanji_wcsnrtombs(char * __restrict dst,
183     const wchar_t ** __restrict src, size_t nwc,
184     size_t len, mbstate_t * __restrict ps)
185 {
186 	return (__wcsnrtombs_std(dst, src, nwc, len, ps, _MSKanji_wcrtomb));
187 }
188