xref: /freebsd/lib/libc/locale/mbrtoc16.c (revision 4d846d260e2b9a3d4d0a701462568268cbfe7a5b)
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 <sys/cdefs.h>
30 __FBSDID("$FreeBSD$");
31 
32 #include <uchar.h>
33 #include "mblocal.h"
34 
35 typedef struct {
36 	char16_t	trail_surrogate;
37 	mbstate_t	c32_mbstate;
38 } _Char16State;
39 
40 size_t
41 mbrtoc16_l(char16_t * __restrict pc16, const char * __restrict s, size_t n,
42     mbstate_t * __restrict ps, locale_t locale)
43 {
44 	_Char16State *cs;
45 	char32_t c32;
46 	ssize_t len;
47 
48 	FIX_LOCALE(locale);
49 	if (ps == NULL)
50 		ps = &(XLOCALE_CTYPE(locale)->mbrtoc16);
51 	cs = (_Char16State *)ps;
52 
53 	/*
54 	 * Call straight into mbrtoc32_l() if we don't need to return a
55 	 * character value. According to the spec, if s is a null
56 	 * pointer, the value of parameter pc16 is also ignored.
57 	 */
58 	if (pc16 == NULL || s == NULL) {
59 		cs->trail_surrogate = 0;
60 		return (mbrtoc32_l(NULL, s, n, &cs->c32_mbstate, locale));
61 	}
62 
63 	/* Return the trail surrogate from the previous invocation. */
64 	if (cs->trail_surrogate >= 0xdc00 && cs->trail_surrogate <= 0xdfff) {
65 		*pc16 = cs->trail_surrogate;
66 		cs->trail_surrogate = 0;
67 		return ((size_t)-3);
68 	}
69 
70 	len = mbrtoc32_l(&c32, s, n, &cs->c32_mbstate, locale);
71 	if (len >= 0) {
72 		if (c32 < 0x10000) {
73 			/* Fits in one UTF-16 character. */
74 			*pc16 = c32;
75 		} else {
76 			/* Split up in a surrogate pair. */
77 			c32 -= 0x10000;
78 			*pc16 = 0xd800 | (c32 >> 10);
79 			cs->trail_surrogate = 0xdc00 | (c32 & 0x3ff);
80 		}
81 	}
82 	return (len);
83 }
84 
85 size_t
86 mbrtoc16(char16_t * __restrict pc16, const char * __restrict s, size_t n,
87     mbstate_t * __restrict ps)
88 {
89 
90 	return (mbrtoc16_l(pc16, s, n, ps, __get_locale()));
91 }
92