1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
/* Convert 32-bit wide character to multibyte character.
Copyright (C) 2020-2024 Free Software Foundation, Inc.
This file is free software: you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as
published by the Free Software Foundation; either version 2.1 of the
License, or (at your option) any later version.
This file is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
/* Written by Bruno Haible <bruno@clisp.org>, 2020. */
#include <config.h>
/* Specification. */
#include <uchar.h>
#include <errno.h>
#include <wchar.h>
#include "attribute.h" /* FALLTHROUGH */
#include "localcharset.h"
#include "streq.h"
#if GL_CHAR32_T_IS_UNICODE
# include "lc-charset-unicode.h"
#endif
size_t
c32rtomb (char *s, char32_t wc, mbstate_t *ps)
#undef c32rtomb
{
#if HAVE_WORKING_MBRTOC32
# if C32RTOMB_RETVAL_BUG
if (s == NULL)
/* We know the NUL wide character corresponds to the NUL character. */
return 1;
# endif
return c32rtomb (s, wc, ps);
#elif _GL_SMALL_WCHAR_T
if (s == NULL)
return wcrtomb (NULL, 0, ps);
else
{
/* Special-case all encodings that may produce wide character values
> WCHAR_MAX. */
const char *encoding = locale_charset ();
if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
{
/* Special-case the UTF-8 encoding. Assume that the wide-character
encoding in a UTF-8 locale is UCS-2 or, equivalently, UTF-16. */
if (wc < 0x80)
{
s[0] = (unsigned char) wc;
return 1;
}
else
{
int count;
if (wc < 0x800)
count = 2;
else if (wc < 0x10000)
{
if (wc < 0xd800 || wc >= 0xe000)
count = 3;
else
{
errno = EILSEQ;
return (size_t)(-1);
}
}
else if (wc < 0x110000)
count = 4;
else
{
errno = EILSEQ;
return (size_t)(-1);
}
switch (count) /* note: code falls through cases! */
{
case 4: s[3] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x10000;
FALLTHROUGH;
case 3: s[2] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x800;
FALLTHROUGH;
case 2: s[1] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0xc0;
/*case 1:*/ s[0] = wc;
}
return count;
}
}
else
{
if ((wchar_t) wc == wc)
return wcrtomb (s, (wchar_t) wc, ps);
else
{
errno = EILSEQ;
return (size_t)(-1);
}
}
}
#else
/* char32_t and wchar_t are equivalent. */
# if GL_CHAR32_T_IS_UNICODE && GL_CHAR32_T_VS_WCHAR_T_NEEDS_CONVERSION
if (wc != 0)
{
wc = unicode_to_locale_encoding (wc);
if (wc == 0)
{
errno = EILSEQ;
return (size_t)(-1);
}
}
# endif
return wcrtomb (s, (wchar_t) wc, ps);
#endif
}
|
