wcsmbs/mbsnrtowcs.c

   1 /* Copyright (C) 1996-2024 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3
   4    The GNU C Library is free software; you can redistribute it and/or
   5    modify it under the terms of the GNU Lesser General Public
   6    License as published by the Free Software Foundation; either
   7    version 2.1 of the License, or (at your option) any later version.
   8
   9    The GNU C Library is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12    Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public
  15    License along with the GNU C Library; if not, see
  16    <https://www.gnu.org/licenses/>.  */
  17
  18 #include <assert.h>
  19 #include <dlfcn.h>
  20 #include <errno.h>
  21 #include <gconv.h>
  22 #include <string.h>
  23 #include <wchar.h>
  24 #include <wcsmbsload.h>
  25
  26 #include <pointer_guard.h>
  27
  28 #ifndef EILSEQ
  29 # define EILSEQ EINVAL
  30 #endif
  31
  32
  33 /* This is the private state used if PS is NULL.  */
  34 static mbstate_t state;
  35
  36 /* This is a non-standard function but it is very useful in the
  37    implementation of stdio because we have to deal with unterminated
  38    buffers.  At most NMC bytes will be converted.  */
  39 size_t
  40 __mbsnrtowcs (wchar_t *dst, const char **src, size_t nmc, size_t len,
  41               mbstate_t *ps)
  42 {
  43   const unsigned char *srcend;
  44   struct __gconv_step_data data;
  45   size_t result;
  46   int status;
  47   struct __gconv_step *towc;
  48   size_t dummy;
  49   const struct gconv_fcts *fcts;
  50
  51   /* Tell where we want the result.  */
  52   data.__invocation_counter = 0;
  53   data.__internal_use = 1;
  54   data.__flags = __GCONV_IS_LAST;
  55   data.__statep = ps ?: &state;
  56
  57   if (nmc == 0)
  58     return 0;
  59   srcend = (const unsigned char *) *src + __strnlen (*src, nmc - 1) + 1;
  60
  61   /* Get the conversion functions.  */
  62   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
  63
  64   /* Get the structure with the function pointers.  */
  65   towc = fcts->towc;
  66   __gconv_fct fct = towc->__fct;
  67   if (towc->__shlib_handle != NULL)
  68     PTR_DEMANGLE (fct);
  69
  70   /* We have to handle DST == NULL special.  */
  71   if (dst == NULL)
  72     {
  73       mbstate_t temp_state;
  74       wchar_t buf[64];          /* Just an arbitrary size.  */
  75       const unsigned char *inbuf = (const unsigned char *) *src;
  76
  77       temp_state = *data.__statep;
  78       data.__statep = &temp_state;
  79
  80       result = 0;
  81       data.__outbufend = (unsigned char *) buf + sizeof (buf);
  82       do
  83         {
  84           data.__outbuf = (unsigned char *) buf;
  85
  86           status = DL_CALL_FCT (fct, (towc, &data, &inbuf, srcend, NULL,
  87                                       &dummy, 0, 1));
  88
  89           result += (wchar_t *) data.__outbuf - buf;
  90         }
  91       while (status == __GCONV_FULL_OUTPUT);
  92
  93       if ((status == __GCONV_OK || status == __GCONV_EMPTY_INPUT)
  94           && ((wchar_t *) data.__outbuf)[-1] == L'\0')
  95         /* Don't count the NUL character in.  */
  96         --result;
  97     }
  98   else
  99     {
 100       /* This code is based on the safe assumption that all internal
 101          multi-byte encodings use the NUL byte only to mark the end
 102          of the string.  */
 103       data.__outbuf = (unsigned char *) dst;
 104       data.__outbufend = data.__outbuf + len * sizeof (wchar_t);
 105
 106       status = DL_CALL_FCT (fct,
 107                             (towc, &data, (const unsigned char **) src, srcend,
 108                              NULL, &dummy, 0, 1));
 109
 110       result = (wchar_t *) data.__outbuf - dst;
 111
 112       /* We have to determine whether the last character converted
 113          is the NUL character.  */
 114       if ((status == __GCONV_OK || status == __GCONV_EMPTY_INPUT)
 115           && (assert (result > 0),
 116               ((wchar_t *) dst)[result - 1] == L'\0'))
 117         {
 118           assert (__mbsinit (data.__statep));
 119           *src = NULL;
 120           --result;
 121         }
 122     }
 123
 124   /* There must not be any problems with the conversion but illegal input
 125      characters.  */
 126   assert (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
 127           || status == __GCONV_ILLEGAL_INPUT
 128           || status == __GCONV_INCOMPLETE_INPUT
 129           || status == __GCONV_FULL_OUTPUT);
 130
 131   if (status != __GCONV_OK && status != __GCONV_FULL_OUTPUT
 132       && status != __GCONV_EMPTY_INPUT && status != __GCONV_INCOMPLETE_INPUT)
 133     {
 134       result = (size_t) -1;
 135       __set_errno (EILSEQ);
 136     }
 137
 138   return result;
 139 }
 140 weak_alias (__mbsnrtowcs, mbsnrtowcs)