wcsmbs/mbrtowc.c

   1 /* Copyright (C) 1996-2017 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Contributed by Ulrich Drepper <drepper@gnu.org>, 1996.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <http://www.gnu.org/licenses/>.  */
  18
  19 #include <assert.h>
  20 #include <dlfcn.h>
  21 #include <errno.h>
  22 #include <gconv.h>
  23 #include <wchar.h>
  24 #include <wcsmbsload.h>
  25
  26 #include <sysdep.h>
  27
  28 #ifndef EILSEQ
  29 # define EILSEQ EINVAL
  30 #endif
  31
  32 /* This is the private state used if PS is NULL.  */
  33 static mbstate_t state;
  34
  35 size_t
  36 __mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
  37 {
  38   wchar_t buf[1];
  39   struct __gconv_step_data data;
  40   int status;
  41   size_t result;
  42   size_t dummy;
  43   const unsigned char *inbuf, *endbuf;
  44   unsigned char *outbuf = (unsigned char *) (pwc ?: buf);
  45   const struct gconv_fcts *fcts;
  46
  47   /* Set information for this step.  */
  48   data.__invocation_counter = 0;
  49   data.__internal_use = 1;
  50   data.__flags = __GCONV_IS_LAST;
  51   data.__statep = ps ?: &state;
  52
  53   /* A first special case is if S is NULL.  This means put PS in the
  54      initial state.  */
  55   if (s == NULL)
  56     {
  57       outbuf = (unsigned char *) buf;
  58       s = "";
  59       n = 1;
  60     }
  61
  62   if (n == 0)
  63     return (size_t) -2;
  64
  65   /* Tell where we want the result.  */
  66   data.__outbuf = outbuf;
  67   data.__outbufend = outbuf + sizeof (wchar_t);
  68
  69   /* Get the conversion functions.  */
  70   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
  71
  72   /* Do a normal conversion.  */
  73   inbuf = (const unsigned char *) s;
  74   endbuf = inbuf + n;
  75   if (__glibc_unlikely (endbuf < inbuf))
  76     {
  77       endbuf = (const unsigned char *) ~(uintptr_t) 0;
  78       if (endbuf == inbuf)
  79         goto ilseq;
  80     }
  81   __gconv_fct fct = fcts->towc->__fct;
  82 #ifdef PTR_DEMANGLE
  83   if (fcts->towc->__shlib_handle != NULL)
  84     PTR_DEMANGLE (fct);
  85 #endif
  86   status = DL_CALL_FCT (fct, (fcts->towc, &data, &inbuf, endbuf,
  87                               NULL, &dummy, 0, 1));
  88
  89   /* There must not be any problems with the conversion but illegal input
  90      characters.  The output buffer must be large enough, otherwise the
  91      definition of MB_CUR_MAX is not correct.  All the other possible
  92      errors also must not happen.  */
  93   assert (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
  94           || status == __GCONV_ILLEGAL_INPUT
  95           || status == __GCONV_INCOMPLETE_INPUT
  96           || status == __GCONV_FULL_OUTPUT);
  97
  98   if (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
  99       || status == __GCONV_FULL_OUTPUT)
 100     {
 101       if (data.__outbuf != (unsigned char *) outbuf
 102           && *(wchar_t *) outbuf == L'\0')
 103         {
 104           /* The converted character is the NUL character.  */
 105           assert (__mbsinit (data.__statep));
 106           result = 0;
 107         }
 108       else
 109         result = inbuf - (const unsigned char *) s;
 110     }
 111   else if (status == __GCONV_INCOMPLETE_INPUT)
 112     result = (size_t) -2;
 113   else
 114     {
 115     ilseq:
 116       result = (size_t) -1;
 117       __set_errno (EILSEQ);
 118     }
 119
 120   return result;
 121 }
 122 libc_hidden_def (__mbrtowc)
 123 weak_alias (__mbrtowc, mbrtowc)
 124 libc_hidden_weak (mbrtowc)
 125
 126 /* There should be no difference between the UTF-32 handling required
 127    by mbrtoc32 and the wchar_t handling which has long since been
 128    implemented in mbrtowc.  */
 129 weak_alias (__mbrtowc, mbrtoc32)