xref: /freebsd/lib/libc/locale/mbrtoc16.c (revision 2e3507c25e42292b45a5482e116d278f5515d04d)
1 /*-
2  * SPDX-License-Identifier: BSD-2-Clause
3  *
4  * Copyright (c) 2013 Ed Schouten <ed@FreeBSD.org>
5  * All rights reserved.
6  *
7  * Redistribution and use in source and binary forms, with or without
8  * modification, are permitted provided that the following conditions
9  * are met:
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.
15  *
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
26  * SUCH DAMAGE.
27  */
28 
29 #include <uchar.h>
30 #include "mblocal.h"
31 
32 typedef struct {
33 	char16_t	trail_surrogate;
34 	mbstate_t	c32_mbstate;
35 } _Char16State;
36 
37 size_t
38 mbrtoc16_l(char16_t * __restrict pc16, const char * __restrict s, size_t n,
39     mbstate_t * __restrict ps, locale_t locale)
40 {
41 	_Char16State *cs;
42 	char32_t c32;
43 	ssize_t len;
44 
45 	FIX_LOCALE(locale);
46 	if (ps == NULL)
47 		ps = &(XLOCALE_CTYPE(locale)->mbrtoc16);
48 	cs = (_Char16State *)ps;
49 
50 	/*
51 	 * Call straight into mbrtoc32_l() if we don't need to return a
52 	 * character value. According to the spec, if s is a null
53 	 * pointer, the value of parameter pc16 is also ignored.
54 	 */
55 	if (pc16 == NULL || s == NULL) {
56 		cs->trail_surrogate = 0;
57 		return (mbrtoc32_l(NULL, s, n, &cs->c32_mbstate, locale));
58 	}
59 
60 	/* Return the trail surrogate from the previous invocation. */
61 	if (cs->trail_surrogate >= 0xdc00 && cs->trail_surrogate <= 0xdfff) {
62 		*pc16 = cs->trail_surrogate;
63 		cs->trail_surrogate = 0;
64 		return ((size_t)-3);
65 	}
66 
67 	len = mbrtoc32_l(&c32, s, n, &cs->c32_mbstate, locale);
68 	if (len >= 0) {
69 		if (c32 < 0x10000) {
70 			/* Fits in one UTF-16 character. */
71 			*pc16 = c32;
72 		} else {
73 			/* Split up in a surrogate pair. */
74 			c32 -= 0x10000;
75 			*pc16 = 0xd800 | (c32 >> 10);
76 			cs->trail_surrogate = 0xdc00 | (c32 & 0x3ff);
77 		}
78 	}
79 	return (len);
80 }
81 
82 size_t
83 mbrtoc16(char16_t * __restrict pc16, const char * __restrict s, size_t n,
84     mbstate_t * __restrict ps)
85 {
86 
87 	return (mbrtoc16_l(pc16, s, n, ps, __get_locale()));
88 }
89