wcsmbs/mbsrtowcs.c

   1 /* Copyright (C) 1996 Free Software Foundation, Inc.
   2 This file is part of the GNU C Library.
   3 Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 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 Library General Public License as
   7 published by the Free Software Foundation; either version 2 of the
   8 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 Library General Public License for more details.
  14
  15 You should have received a copy of the GNU Library General Public
  16 License along with the GNU C Library; see the file COPYING.LIB.  If
  17 not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  18 Boston, MA 02111-1307, USA.  */
  19
  20 #include <errno.h>
  21 #include <wchar.h>
  22
  23 #ifndef EILSEQ
  24 #define EILSEQ EINVAL
  25 #endif
  26
  27
  28 /* We don't need the state really because we don't have shift states
  29    to maintain between calls to this function.  */
  30 static mbstate_t internal;
  31
  32 size_t
  33 mbsrtowcs (dst, src, len, ps)
  34      wchar_t *dst;
  35      const char **src;
  36      size_t len;
  37      mbstate_t *ps;
  38 {
  39   size_t written = 0;
  40   const char *run = *src;
  41
  42   if (ps == NULL)
  43     ps = &internal;
  44
  45   if (dst == NULL)
  46     /* The LEN parameter has to be ignored if we don't actually write
  47        anything.  */
  48     len = ~0;
  49
  50   /* Copy all words.  */
  51   while (written < len)
  52     {
  53       wchar_t value;
  54       size_t count;
  55       unsigned char byte = *run++;
  56
  57       /* We expect a start of a new multibyte character.  */
  58       if (byte < 0x80)
  59         {
  60           /* One byte sequence.  */
  61           count = 0;
  62           value = byte;
  63         }
  64       else if ((byte & 0xe0) == 0xc0)
  65         {
  66           count = 1;
  67           value = byte & 0x1f;
  68         }
  69       else if ((byte & 0xf0) == 0xe0)
  70         {
  71           /* We expect three bytes.  */
  72           count = 2;
  73           value = byte & 0x0f;
  74         }
  75       else if ((byte & 0xf8) == 0xf0)
  76         {
  77           /* We expect four bytes.  */
  78           count = 3;
  79           value = byte & 0x07;
  80         }
  81       else if ((byte & 0xfc) == 0xf8)
  82         {
  83           /* We expect five bytes.  */
  84           count = 4;
  85           value = byte & 0x03;
  86         }
  87       else if ((byte & 0xfe) == 0xfc)
  88         {
  89           /* We expect six bytes.  */
  90           count = 5;
  91           value = byte & 0x01;
  92         }
  93       else
  94         {
  95           /* This is an illegal encoding.  */
  96           errno = EILSEQ;
  97           return (size_t) -1;
  98         }
  99
 100       /* Read the possible remaining bytes.  */
 101       while (count-- > 0)
 102         {
 103           byte = *run++;
 104
 105           if ((byte & 0xc0) != 0x80)
 106             {
 107               /* This is an illegal encoding.  */
 108               errno = EILSEQ;
 109               return (size_t) -1;
 110             }
 111
 112           value <<= 6;
 113           value |= byte & 0x3f;
 114         }
 115
 116       /* Store value is required.  */
 117       if (dst != NULL)
 118         *dst++ = value;
 119
 120       /* The whole sequence is read.  Check whether end of string is
 121          reached.  */
 122       if (value == L'\0')
 123         {
 124           /* Found the end of the string.  */
 125           *src = NULL;
 126           return written;
 127         }
 128
 129       /* Increment counter of produced words.  */
 130       ++written;
 131     }
 132
 133   /* Store address of next byte to process.  */
 134   *src = run;
 135
 136   return written;
 137 }