wcsmbs/mbrtoc16.c

   1 /* Copyright (C) 2011, 2012 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Contributed by Ulrich Drepper <drepper@gmail.com>, 2011.
   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, write to the Free
  17    Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
  18    02111-1307 USA.  */
  19
  20 #include <assert.h>
  21 #include <dlfcn.h>
  22 #include <errno.h>
  23 #include <gconv.h>
  24 #include <uchar.h>
  25 #include <wcsmbsload.h>
  26
  27 #include <sysdep.h>
  28
  29 #ifndef EILSEQ
  30 # define EILSEQ EINVAL
  31 #endif
  32
  33
  34 /* This is the private state used if PS is NULL.  */
  35 static mbstate_t state;
  36
  37 size_t
  38 mbrtoc16 (char16_t *pc16, const char *s, size_t n, mbstate_t *ps)
  39 {
  40   if (ps == NULL)
  41     ps = &state;
  42
  43   /* The standard text does not say that S being NULL means the state
  44      is reset even if the second half of a surrogate still have to be
  45      returned.  In fact, the error code description indicates
  46      otherwise.  Therefore always first try to return a second
  47      half.  */
  48   if (ps->__count & 0x80000000)
  49     {
  50       /* We have to return the second word for a surrogate.  */
  51       ps->__count &= 0x7fffffff;
  52       *pc16 = ps->__value.__wch;
  53       ps->__value.__wch = L'\0';
  54       return (size_t) -3;
  55     }
  56
  57   wchar_t wc;
  58   struct __gconv_step_data data;
  59   int status;
  60   size_t result;
  61   size_t dummy;
  62   const unsigned char *inbuf, *endbuf;
  63   unsigned char *outbuf = (unsigned char *) &wc;
  64   const struct gconv_fcts *fcts;
  65
  66   /* Set information for this step.  */
  67   data.__invocation_counter = 0;
  68   data.__internal_use = 1;
  69   data.__flags = __GCONV_IS_LAST;
  70   data.__statep = ps;
  71   data.__trans = NULL;
  72
  73   /* A first special case is if S is NULL.  This means put PS in the
  74      initial state.  */
  75   if (s == NULL)
  76     {
  77       pc16 = NULL;
  78       s = "";
  79       n = 1;
  80     }
  81
  82   /* Tell where we want the result.  */
  83   data.__outbuf = outbuf;
  84   data.__outbufend = outbuf + sizeof (wchar_t);
  85
  86   /* Get the conversion functions.  */
  87   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
  88
  89   /* Do a normal conversion.  */
  90   inbuf = (const unsigned char *) s;
  91   endbuf = inbuf + n;
  92   if (__builtin_expect (endbuf < inbuf, 0))
  93     {
  94       endbuf = (const unsigned char *) ~(uintptr_t) 0;
  95       if (endbuf == inbuf)
  96         goto ilseq;
  97     }
  98   __gconv_fct fct = fcts->towc->__fct;
  99 #ifdef PTR_DEMANGLE
 100   if (fcts->towc->__shlib_handle != NULL)
 101     PTR_DEMANGLE (fct);
 102 #endif
 103
 104   status = DL_CALL_FCT (fct, (fcts->towc, &data, &inbuf, endbuf,
 105                               NULL, &dummy, 0, 1));
 106
 107   /* There must not be any problems with the conversion but illegal input
 108      characters.  The output buffer must be large enough, otherwise the
 109      definition of MB_CUR_MAX is not correct.  All the other possible
 110      errors also must not happen.  */
 111   assert (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
 112           || status == __GCONV_ILLEGAL_INPUT
 113           || status == __GCONV_INCOMPLETE_INPUT
 114           || status == __GCONV_FULL_OUTPUT);
 115
 116   if (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
 117       || status == __GCONV_FULL_OUTPUT)
 118     {
 119       result = inbuf - (const unsigned char *) s;
 120
 121       if (wc < 0x10000)
 122         {
 123           if (pc16 != NULL)
 124             *pc16 = wc;
 125
 126           if (data.__outbuf != outbuf && wc == L'\0')
 127             {
 128               /* The converted character is the NUL character.  */
 129               assert (__mbsinit (data.__statep));
 130               result = 0;
 131             }
 132         }
 133       else
 134         {
 135           /* This is a surrogate.  */
 136           if (pc16 != NULL)
 137             *pc16 = 0xd7c0 + (wc >> 10);
 138
 139           ps->__count |= 0x80000000;
 140           ps->__value.__wch = 0xdc00 + (wc & 0x3ff);
 141         }
 142     }
 143   else if (status == __GCONV_INCOMPLETE_INPUT)
 144     result = (size_t) -2;
 145   else
 146     {
 147     ilseq:
 148       result = (size_t) -1;
 149       __set_errno (EILSEQ);
 150     }
 151
 152   return result;
 153 }