debian/pkg-monitoring-plugins
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

New upstream version 2.3.4

Browse source
This commit is contained in:
Jan Wagner 2023-10-18 07:29:37 +00:00
parent e7bdd1c6c6
commit de72f6f588
556 changed files with 90432 additions and 53391 deletions
Download patch file Download diff file Expand all files Collapse all files

401
gl/mbrtowc.c
View file

@ -1,19 +1,19 @@
/* Convert multibyte character to wide character.
Copyright (C) 1999-2002, 2005-2013 Free Software Foundation, Inc.
Copyright (C) 1999-2002, 2005-2023 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2008.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
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 program is distributed in the hope that it will be useful,
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 General Public License for more details.
GNU Lesser General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
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/>. */
#include <config.h>
@ -21,314 +21,66 @@
#include <wchar.h>
#if GNULIB_defined_mbstate_t
/* Implement mbrtowc() on top of mbtowc(). */
/* Implement mbrtowc() on top of mbtowc() for the non-UTF-8 locales
and directly for the UTF-8 locales. */
# include <errno.h>
# include <stdint.h>
# include <stdlib.h>
# include "localcharset.h"
# include "streq.h"
# include "verify.h"
# if defined _WIN32 && !defined __CYGWIN__
# define WIN32_LEAN_AND_MEAN /* avoid including junk */
# include <windows.h>
verify (sizeof (mbstate_t) >= 4);
# 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 "attribute.h"
# include "lc-charset-dispatch.h"
# include "mbtowc-lock.h"
static_assert (sizeof (mbstate_t) >= 4);
static char internal_state[4];
size_t
mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
{
char *pstate = (char *)ps;
if (s == NULL)
{
pwc = NULL;
s = "";
n = 1;
}
if (n == 0)
return (size_t)(-2);
/* Here n > 0. */
if (pstate == NULL)
pstate = internal_state;
{
size_t nstate = pstate[0];
char buf[4];
const char *p;
size_t m;
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. */
# if __GLIBC__ || defined __UCLIBC__
/* Work around bug <http://sourceware.org/bugzilla/show_bug.cgi?id=9674> */
mbtowc (NULL, NULL, 0);
# endif
{
int res = mbtowc (pwc, p, m);
if (res >= 0)
{
if (pwc != NULL && ((*pwc == 0) != (res == 0)))
abort ();
if (nstate >= (res > 0 ? res : 1))
abort ();
res -= nstate;
pstate[0] = 0;
return res;
}
/* mbtowc does not distinguish between invalid and incomplete multibyte
sequences. But mbrtowc needs to make this distinction.
There are two possible approaches:
- Use iconv() and its return value.
- Use built-in knowledge about the possible encodings.
Given the low quality of implementation of iconv() on the systems that
lack mbrtowc(), we use the second approach.
The possible encodings are:
- 8-bit encodings,
- EUC-JP, EUC-KR, GB2312, EUC-TW, BIG5, GB18030, SJIS,
- UTF-8.
Use specialized code for each. */
if (m >= 4 || m >= MB_CUR_MAX)
goto invalid;
/* Here MB_CUR_MAX > 1 and 0 < m < 4. */
{
const char *encoding = locale_charset ();
if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
{
/* Cf. unistr/u8-mblen.c. */
unsigned char c = (unsigned char) p[0];
if (c >= 0xc2)
{
if (c < 0xe0)
{
if (m == 1)
goto incomplete;
}
else if (c < 0xf0)
{
if (m == 1)
goto incomplete;
if (m == 2)
{
unsigned char c2 = (unsigned char) p[1];
if ((c2 ^ 0x80) < 0x40
&& (c >= 0xe1 || c2 >= 0xa0)
&& (c != 0xed || c2 < 0xa0))
goto incomplete;
}
}
else if (c <= 0xf4)
{
if (m == 1)
goto incomplete;
else /* m == 2 || m == 3 */
{
unsigned char c2 = (unsigned char) p[1];
if ((c2 ^ 0x80) < 0x40
&& (c >= 0xf1 || c2 >= 0x90)
&& (c < 0xf4 || (c == 0xf4 && c2 < 0x90)))
{
if (m == 2)
goto incomplete;
else /* m == 3 */
{
unsigned char c3 = (unsigned char) p[2];
if ((c3 ^ 0x80) < 0x40)
goto incomplete;
}
}
}
}
}
goto invalid;
}
/* As a reference for this code, you can use the GNU libiconv
implementation. Look for uses of the RET_TOOFEW macro. */
if (STREQ_OPT (encoding,
"EUC-JP", 'E', 'U', 'C', '-', 'J', 'P', 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0xa1 && c < 0xff) || c == 0x8e || c == 0x8f)
goto incomplete;
}
if (m == 2)
{
unsigned char c = (unsigned char) p[0];
if (c == 0x8f)
{
unsigned char c2 = (unsigned char) p[1];
if (c2 >= 0xa1 && c2 < 0xff)
goto incomplete;
}
}
goto invalid;
}
if (STREQ_OPT (encoding,
"EUC-KR", 'E', 'U', 'C', '-', 'K', 'R', 0, 0, 0)
|| STREQ_OPT (encoding,
"GB2312", 'G', 'B', '2', '3', '1', '2', 0, 0, 0)
|| STREQ_OPT (encoding,
"BIG5", 'B', 'I', 'G', '5', 0, 0, 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if (c >= 0xa1 && c < 0xff)
goto incomplete;
}
goto invalid;
}
if (STREQ_OPT (encoding,
"EUC-TW", 'E', 'U', 'C', '-', 'T', 'W', 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0xa1 && c < 0xff) || c == 0x8e)
goto incomplete;
}
else /* m == 2 || m == 3 */
{
unsigned char c = (unsigned char) p[0];
if (c == 0x8e)
goto incomplete;
}
goto invalid;
}
if (STREQ_OPT (encoding,
"GB18030", 'G', 'B', '1', '8', '0', '3', '0', 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0x90 && c <= 0xe3) || (c >= 0xf8 && c <= 0xfe))
goto incomplete;
}
else /* m == 2 || m == 3 */
{
unsigned char c = (unsigned char) p[0];
if (c >= 0x90 && c <= 0xe3)
{
unsigned char c2 = (unsigned char) p[1];
if (c2 >= 0x30 && c2 <= 0x39)
{
if (m == 2)
goto incomplete;
else /* m == 3 */
{
unsigned char c3 = (unsigned char) p[2];
if (c3 >= 0x81 && c3 <= 0xfe)
goto incomplete;
}
}
}
}
goto invalid;
}
if (STREQ_OPT (encoding, "SJIS", 'S', 'J', 'I', 'S', 0, 0, 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xea)
|| (c >= 0xf0 && c <= 0xf9))
goto incomplete;
}
goto invalid;
}
/* An unknown multibyte encoding. */
goto incomplete;
}
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);
}
}
# define FITS_IN_CHAR_TYPE(wc) ((wc) <= WCHAR_MAX)
# include "mbrtowc-impl.h"
}
#else
/* Override the system's mbrtowc() function. */
# if MBRTOWC_IN_C_LOCALE_MAYBE_EILSEQ
# include "hard-locale.h"
# include <locale.h>
# endif
# undef mbrtowc
size_t
rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
{
# if MBRTOWC_NULL_ARG2_BUG || MBRTOWC_RETVAL_BUG
size_t ret;
wchar_t wc;
# if MBRTOWC_NULL_ARG2_BUG || MBRTOWC_RETVAL_BUG || MBRTOWC_EMPTY_INPUT_BUG
if (s == NULL)
{
pwc = NULL;
@ -337,6 +89,14 @@ rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
}
# endif
# if MBRTOWC_EMPTY_INPUT_BUG
if (n == 0)
return (size_t) -2;
# endif
if (! pwc)
pwc = &wc;
# if MBRTOWC_RETVAL_BUG
{
static mbstate_t internal_state;
@ -352,8 +112,7 @@ rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
size_t count = 0;
for (; n > 0; s++, n--)
{
wchar_t wc;
size_t ret = mbrtowc (&wc, s, 1, ps);
ret = mbrtowc (&wc, s, 1, ps);
if (ret == (size_t)(-1))
return (size_t)(-1);
@ -361,8 +120,7 @@ rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
if (ret != (size_t)(-2))
{
/* The multibyte character has been completed. */
if (pwc != NULL)
*pwc = wc;
*pwc = wc;
return (wc == 0 ? 0 : count);
}
}
@ -371,32 +129,29 @@ rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
}
# endif
# if MBRTOWC_NUL_RETVAL_BUG
{
wchar_t wc;
size_t ret = mbrtowc (&wc, s, n, ps);
if (ret != (size_t)(-1) && ret != (size_t)(-2))
{
if (pwc != NULL)
*pwc = wc;
if (wc == 0)
ret = 0;
}
return ret;
}
# if MBRTOWC_STORES_INCOMPLETE_BUG
ret = mbrtowc (&wc, s, n, ps);
if (ret < (size_t) -2 && pwc != NULL)
*pwc = wc;
# else
{
# if MBRTOWC_NULL_ARG1_BUG
wchar_t dummy;
if (pwc == NULL)
pwc = &dummy;
# endif
return mbrtowc (pwc, s, n, ps);
}
ret = mbrtowc (pwc, s, n, ps);
# endif
# if MBRTOWC_NUL_RETVAL_BUG
if (ret < (size_t) -2 && !*pwc)
return 0;
# endif
# if MBRTOWC_IN_C_LOCALE_MAYBE_EILSEQ
if ((size_t) -2 <= ret && n != 0 && ! hard_locale (LC_CTYPE))
{
unsigned char uc = *s;
*pwc = uc;
return 1;
}
# endif
return ret;
}
#endif