wcsmbs/wcsnrtombs.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 static const wchar_t encoding_mask[] =
  29 {
  30   ~0x7ff, ~0xffff, ~0x1fffff, ~0x3ffffff
  31 };
  32
  33 static const unsigned char encoding_byte[] =
  34 {
  35   0xc0, 0xe0, 0xf0, 0xf8, 0xfc
  36 };
  37
  38 /* We don't need the state really because we don't have shift states
  39    to maintain between calls to this function.  */
  40 static mbstate_t internal;
  41
  42 /* This is a non-standard function but it is very useful in the
  43    implementation of stdio because we have to deal with unterminated
  44    buffers.  At most NWC wide character will be converted.  */
  45 size_t
  46 __wcsnrtombs (dst, src, nwc, len, ps)
  47      char *dst;
  48      const wchar_t **src;
  49      size_t nwc;
  50      size_t len;
  51      mbstate_t *ps;
  52 {
  53   size_t written = 0;
  54   const wchar_t *run = *src;
  55
  56   if (ps == NULL)
  57     ps = &internal;
  58
  59   if (dst == NULL)
  60     /* The LEN parameter has to be ignored if we don't actually write
  61        anything.  */
  62     len = ~0;
  63
  64   while (written < len && nwc-- > 0)
  65     {
  66       wchar_t wc = *run++;
  67
  68       if (wc < 0 || wc > 0x7fffffff)
  69         {
  70           /* This is no correct ISO 10646 character.  */
  71           __set_errno (EILSEQ);
  72           return (size_t) -1;
  73         }
  74
  75       if (wc == L'\0')
  76         {
  77           /* Found the end.  */
  78           if (dst != NULL)
  79             *dst = '\0';
  80           *src = NULL;
  81           return written;
  82         }
  83       else if (wc < 0x80)
  84         {
  85           /* It's an one byte sequence.  */
  86           if (dst != NULL)
  87             *dst++ = (char) wc;
  88           ++written;
  89         }
  90       else
  91         {
  92           size_t step;
  93
  94           for (step = 2; step < 6; ++step)
  95             if ((wc & encoding_mask[step - 2]) == 0)
  96               break;
  97
  98           if (written + step >= len)
  99             /* Too long.  */
 100             break;
 101
 102           if (dst != NULL)
 103             {
 104               size_t cnt = step;
 105
 106               dst[0] = encoding_byte[cnt - 2];
 107
 108               --cnt;
 109               do
 110                 {
 111                   dst[cnt] = 0x80 | (wc & 0x3f);
 112                   wc >>= 6;
 113                 }
 114               while (--cnt > 0);
 115               dst[0] |= wc;
 116
 117               dst += step;
 118             }
 119
 120           written += step;
 121         }
 122     }
 123
 124   /* Store position of first unprocessed word.  */
 125   *src = run;
 126
 127   return written;
 128 }
 129 weak_alias (__wcsnrtombs, wcsnrtombs)