wcsmbs/mbrtowc.c

   1 /* Copyright (C) 1996, 1997, 1998, 1999, 2000, 2002, 2004, 2005, 2011, 2012
   2    Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4    Contributed by Ulrich Drepper <drepper@gnu.org>, 1996.
   5
   6    The GNU C Library is free software; you can redistribute it and/or
   7    modify it under the terms of the GNU Lesser General Public
   8    License as published by the Free Software Foundation; either
   9    version 2.1 of the License, or (at your option) any later version.
  10
  11    The GNU C Library is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public
  17    License along with the GNU C Library; if not, see
  18    <http://www.gnu.org/licenses/>.  */
  19
  20 #include <assert.h>
  21 #include <dlfcn.h>
  22 #include <errno.h>
  23 #include <gconv.h>
  24 #include <wchar.h>
  25 #include <wcsmbsload.h>
  26
  27 #include <sysdep.h>
  28
  29 #ifndef EILSEQ
  30 # define EILSEQ EINVAL
  31 #endif
  32
  33 /* This is the private state used if PS is NULL.  */
  34 static mbstate_t state;
  35
  36 size_t
  37 __mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
  38 {
  39   wchar_t buf[1];
  40   struct __gconv_step_data data;
  41   int status;
  42   size_t result;
  43   size_t dummy;
  44   const unsigned char *inbuf, *endbuf;
  45   unsigned char *outbuf = (unsigned char *) (pwc ?: buf);
  46   const struct gconv_fcts *fcts;
  47
  48   /* Set information for this step.  */
  49   data.__invocation_counter = 0;
  50   data.__internal_use = 1;
  51   data.__flags = __GCONV_IS_LAST;
  52   data.__statep = ps ?: &state;
  53   data.__trans = NULL;
  54
  55   /* A first special case is if S is NULL.  This means put PS in the
  56      initial state.  */
  57   if (s == NULL)
  58     {
  59       outbuf = (unsigned char *) buf;
  60       s = "";
  61       n = 1;
  62     }
  63
  64   /* Tell where we want the result.  */
  65   data.__outbuf = outbuf;
  66   data.__outbufend = outbuf + sizeof (wchar_t);
  67
  68   /* Get the conversion functions.  */
  69   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
  70
  71   /* Do a normal conversion.  */
  72   inbuf = (const unsigned char *) s;
  73   endbuf = inbuf + n;
  74   if (__builtin_expect (endbuf < inbuf, 0))
  75     {
  76       endbuf = (const unsigned char *) ~(uintptr_t) 0;
  77       if (endbuf == inbuf)
  78         goto ilseq;
  79     }
  80   __gconv_fct fct = fcts->towc->__fct;
  81 #ifdef PTR_DEMANGLE
  82   if (fcts->towc->__shlib_handle != NULL)
  83     PTR_DEMANGLE (fct);
  84 #endif
  85   status = DL_CALL_FCT (fct, (fcts->towc, &data, &inbuf, endbuf,
  86                               NULL, &dummy, 0, 1));
  87
  88   /* There must not be any problems with the conversion but illegal input
  89      characters.  The output buffer must be large enough, otherwise the
  90      definition of MB_CUR_MAX is not correct.  All the other possible
  91      errors also must not happen.  */
  92   assert (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
  93           || status == __GCONV_ILLEGAL_INPUT
  94           || status == __GCONV_INCOMPLETE_INPUT
  95           || status == __GCONV_FULL_OUTPUT);
  96
  97   if (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
  98       || status == __GCONV_FULL_OUTPUT)
  99     {
 100       if (data.__outbuf != (unsigned char *) outbuf
 101           && *(wchar_t *) outbuf == L'\0')
 102         {
 103           /* The converted character is the NUL character.  */
 104           assert (__mbsinit (data.__statep));
 105           result = 0;
 106         }
 107       else
 108         result = inbuf - (const unsigned char *) s;
 109     }
 110   else if (status == __GCONV_INCOMPLETE_INPUT)
 111     result = (size_t) -2;
 112   else
 113     {
 114     ilseq:
 115       result = (size_t) -1;
 116       __set_errno (EILSEQ);
 117     }
 118
 119   return result;
 120 }
 121 libc_hidden_def (__mbrtowc)
 122 weak_alias (__mbrtowc, mbrtowc)
 123 libc_hidden_weak (mbrtowc)
 124
 125 /* There should be no difference between the UTF-32 handling required
 126    by mbrtoc32 and the wchar_t handling which has long since been
 127    implemented in mbrtowc.  */
 128 weak_alias (__mbrtowc, mbrtoc32)