wcsmbs/mbrtoc16.c

   1 /* Copyright (C) 2011-2015 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, 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 <uchar.h>
  24 #include <wcsmbsload.h>
  25
  26 #include <sysdep.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 size_t
  37 mbrtoc16 (char16_t *pc16, const char *s, size_t n, mbstate_t *ps)
  38 {
  39   if (ps == NULL)
  40     ps = &state;
  41
  42   /* The standard text does not say that S being NULL means the state
  43      is reset even if the second half of a surrogate still have to be
  44      returned.  In fact, the error code description indicates
  45      otherwise.  Therefore always first try to return a second
  46      half.  */
  47   if (ps->__count & 0x80000000)
  48     {
  49       /* We have to return the second word for a surrogate.  */
  50       ps->__count &= 0x7fffffff;
  51       *pc16 = ps->__value.__wch;
  52       ps->__value.__wch = L'\0';
  53       return (size_t) -3;
  54     }
  55
  56   wchar_t wc;
  57   struct __gconv_step_data data;
  58   int status;
  59   size_t result;
  60   size_t dummy;
  61   const unsigned char *inbuf, *endbuf;
  62   unsigned char *outbuf = (unsigned char *) &wc;
  63   const struct gconv_fcts *fcts;
  64
  65   /* Set information for this step.  */
  66   data.__invocation_counter = 0;
  67   data.__internal_use = 1;
  68   data.__flags = __GCONV_IS_LAST;
  69   data.__statep = ps;
  70
  71   /* A first special case is if S is NULL.  This means put PS in the
  72      initial state.  */
  73   if (s == NULL)
  74     {
  75       pc16 = NULL;
  76       s = "";
  77       n = 1;
  78     }
  79
  80   /* Tell where we want the result.  */
  81   data.__outbuf = outbuf;
  82   data.__outbufend = outbuf + sizeof (wchar_t);
  83
  84   /* Get the conversion functions.  */
  85   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
  86
  87   /* Do a normal conversion.  */
  88   inbuf = (const unsigned char *) s;
  89   endbuf = inbuf + n;
  90   if (__glibc_unlikely (endbuf < inbuf))
  91     {
  92       endbuf = (const unsigned char *) ~(uintptr_t) 0;
  93       if (endbuf == inbuf)
  94         goto ilseq;
  95     }
  96   __gconv_fct fct = fcts->towc->__fct;
  97 #ifdef PTR_DEMANGLE
  98   if (fcts->towc->__shlib_handle != NULL)
  99     PTR_DEMANGLE (fct);
 100 #endif
 101
 102   status = DL_CALL_FCT (fct, (fcts->towc, &data, &inbuf, endbuf,
 103                               NULL, &dummy, 0, 1));
 104
 105   /* There must not be any problems with the conversion but illegal input
 106      characters.  The output buffer must be large enough, otherwise the
 107      definition of MB_CUR_MAX is not correct.  All the other possible
 108      errors also must not happen.  */
 109   assert (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
 110           || status == __GCONV_ILLEGAL_INPUT
 111           || status == __GCONV_INCOMPLETE_INPUT
 112           || status == __GCONV_FULL_OUTPUT);
 113
 114   if (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
 115       || status == __GCONV_FULL_OUTPUT)
 116     {
 117       result = inbuf - (const unsigned char *) s;
 118
 119       if (wc < 0x10000)
 120         {
 121           if (pc16 != NULL)
 122             *pc16 = wc;
 123
 124           if (data.__outbuf != outbuf && wc == L'\0')
 125             {
 126               /* The converted character is the NUL character.  */
 127               assert (__mbsinit (data.__statep));
 128               result = 0;
 129             }
 130         }
 131       else
 132         {
 133           /* This is a surrogate.  */
 134           if (pc16 != NULL)
 135             *pc16 = 0xd7c0 + (wc >> 10);
 136
 137           ps->__count |= 0x80000000;
 138           ps->__value.__wch = 0xdc00 + (wc & 0x3ff);
 139         }
 140     }
 141   else if (status == __GCONV_INCOMPLETE_INPUT)
 142     result = (size_t) -2;
 143   else
 144     {
 145     ilseq:
 146       result = (size_t) -1;
 147       __set_errno (EILSEQ);
 148     }
 149
 150   return result;
 151 }