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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
|
/* Convert multibyte character to 32-bit wide 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 "attribute.h"
#include <errno.h>
#include <stdlib.h>
#if GL_CHAR32_T_IS_UNICODE
# include "lc-charset-unicode.h"
#endif
#if GNULIB_defined_mbstate_t /* AIX, IRIX */
/* Implement mbrtoc32() on top of mbtowc() for the non-UTF-8 locales
and directly for the UTF-8 locales. */
/* Note: On AIX (64-bit) we can implement mbrtoc32 in two equivalent ways:
- in a way that parallels the override of mbrtowc; this is the code branch
here;
- in a way that invokes the overridden mbrtowc; this would be the #else
branch below.
They are equivalent. */
# if AVOID_ANY_THREADS
/* The option '--disable-threads' explicitly requests no locking. */
# elif defined _WIN32 && !defined __CYGWIN__
# define WIN32_LEAN_AND_MEAN /* avoid including junk */
# include <windows.h>
# elif HAVE_PTHREAD_API
# include <pthread.h>
# if HAVE_THREADS_H && HAVE_WEAK_SYMBOLS
# include <threads.h>
# pragma weak thrd_exit
# define c11_threads_in_use() (thrd_exit != NULL)
# else
# define c11_threads_in_use() 0
# endif
# elif HAVE_THREADS_H
# include <threads.h>
# endif
# include "lc-charset-dispatch.h"
# include "mbtowc-lock.h"
static_assert (sizeof (mbstate_t) >= 4);
static char internal_state[4];
size_t
mbrtoc32 (char32_t *pwc, const char *s, size_t n, mbstate_t *ps)
{
# define FITS_IN_CHAR_TYPE(wc) 1
# include "mbrtowc-impl.h"
}
#else /* glibc, macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Cygwin, mingw, MSVC, Minix, Android */
/* Implement mbrtoc32() based on the original mbrtoc32() or on mbrtowc(). */
# include <wchar.h>
# include "localcharset.h"
# include "streq.h"
# if MBRTOC32_IN_C_LOCALE_MAYBE_EILSEQ
# include "hard-locale.h"
# include <locale.h>
# endif
static mbstate_t internal_state;
size_t
mbrtoc32 (char32_t *pwc, const char *s, size_t n, mbstate_t *ps)
# undef mbrtoc32
{
/* It's simpler to handle the case s == NULL upfront, than to worry about
this case later, before every test of pwc and n. */
if (s == NULL)
{
pwc = NULL;
s = "";
n = 1;
}
# if MBRTOC32_EMPTY_INPUT_BUG || _GL_SMALL_WCHAR_T
if (n == 0)
return (size_t) -2;
# endif
if (ps == NULL)
ps = &internal_state;
# if HAVE_WORKING_MBRTOC32 && HAVE_WORKING_C32RTOMB && !MBRTOC32_MULTIBYTE_LOCALE_BUG
/* mbrtoc32() may produce different values for wc than mbrtowc(). Therefore
use mbrtoc32(). */
# if defined _WIN32 && !defined __CYGWIN__
char32_t wc;
size_t ret = mbrtoc32 (&wc, s, n, ps);
if (ret < (size_t) -2 && pwc != NULL)
*pwc = wc;
# else
size_t ret = mbrtoc32 (pwc, s, n, ps);
# endif
# if GNULIB_MBRTOC32_REGULAR
/* Verify that mbrtoc32 is regular. */
if (ret < (size_t) -3 && ! mbsinit (ps))
/* This occurs on glibc 2.36. */
mbszero (ps);
if (ret == (size_t) -3)
abort ();
# endif
# if MBRTOC32_IN_C_LOCALE_MAYBE_EILSEQ
if ((size_t) -2 <= ret && n != 0 && ! hard_locale (LC_CTYPE))
{
if (pwc != NULL)
*pwc = (unsigned char) *s;
return 1;
}
# endif
return ret;
# elif _GL_SMALL_WCHAR_T
/* 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. */
/* Here n > 0. */
char *pstate = (char *)ps;
size_t nstate = pstate[0];
char buf[4];
const char *p;
size_t m;
int res;
switch (nstate)
{
case 0:
p = s;
m = n;
break;
case 3:
buf[2] = pstate[3];
FALLTHROUGH;
case 2:
buf[1] = pstate[2];
FALLTHROUGH;
case 1:
buf[0] = pstate[1];
p = buf;
m = nstate;
buf[m++] = s[0];
if (n >= 2 && m < 4)
{
buf[m++] = s[1];
if (n >= 3 && m < 4)
buf[m++] = s[2];
}
break;
default:
errno = EINVAL;
return (size_t)(-1);
}
/* Here m > 0. */
{
# define FITS_IN_CHAR_TYPE(wc) 1
# include "mbrtowc-impl-utf8.h"
}
success:
if (nstate >= (res > 0 ? res : 1))
abort ();
res -= nstate;
/* Set *ps to an initial state. */
# if defined _WIN32 && !defined __CYGWIN__
/* Native Windows. */
/* MSVC defines 'mbstate_t' as an 8-byte struct; the first 4 bytes matter.
On mingw, 'mbstate_t' is sometimes defined as 'int', sometimes defined
as an 8-byte struct, of which the first 4 bytes matter. */
*(unsigned int *)pstate = 0;
# elif defined __CYGWIN__
/* Cygwin defines 'mbstate_t' as an 8-byte struct; the first 4 bytes
matter. */
ps->__count = 0;
# else
pstate[0] = 0;
# endif
return res;
incomplete:
{
size_t k = nstate;
/* Here 0 <= k < m < 4. */
pstate[++k] = s[0];
if (k < m)
{
pstate[++k] = s[1];
if (k < m)
pstate[++k] = s[2];
}
if (k != m)
abort ();
}
pstate[0] = m;
return (size_t)(-2);
invalid:
errno = EILSEQ;
/* The conversion state is undefined, says POSIX. */
return (size_t)(-1);
}
else
{
wchar_t wc;
size_t ret = mbrtowc (&wc, s, n, ps);
if (ret < (size_t) -2 && pwc != NULL)
*pwc = wc;
return ret;
}
# else
/* char32_t and wchar_t are equivalent. Use mbrtowc(). */
wchar_t wc;
size_t ret = mbrtowc (&wc, s, n, ps);
# if GNULIB_MBRTOC32_REGULAR
/* Ensure that mbrtoc32 is regular. */
if (ret < (size_t) -2 && ! mbsinit (ps))
/* This occurs on glibc 2.12. */
mbszero (ps);
# endif
# if GL_CHAR32_T_IS_UNICODE && GL_CHAR32_T_VS_WCHAR_T_NEEDS_CONVERSION
if (ret < (size_t) -2 && wc != 0)
{
wc = locale_encoding_to_unicode (wc);
if (wc == 0)
{
ret = (size_t) -1;
errno = EILSEQ;
}
}
# endif
if (ret < (size_t) -2 && pwc != NULL)
*pwc = wc;
return ret;
# endif
}
#endif
|