wcsmbs/wcsrtombs.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 size_t
  43 wcsrtombs (dst, src, len, ps)
  44      char *dst;
  45      const wchar_t **src;
  46      size_t len;
  47      mbstate_t *ps;
  48 {
  49   size_t written = 0;
  50   const wchar_t *run = *src;
  51
  52   if (ps == NULL)
  53     ps = &internal;
  54
  55   if (dst == NULL)
  56     /* The LEN parameter has to be ignored if we don't actually write
  57        anything.  */
  58     len = ~0;
  59
  60   while (written < len)
  61     {
  62       wchar_t wc = *run++;
  63
  64       if (wc < 0 || wc > 0x7fffffff)
  65         {
  66           /* This is no correct ISO 10646 character.  */
  67           errno = EILSEQ;
  68           return (size_t) -1;
  69         }
  70
  71       if (wc == L'\0')
  72         {
  73           /* Found the end.  */
  74           if (dst != NULL)
  75             *dst = '\0';
  76           *src = NULL;
  77           return written;
  78         }
  79       else if (wc < 0x80)
  80         {
  81           /* It's an one byte sequence.  */
  82           if (dst != NULL)
  83             *dst++ = (char) wc;
  84           ++written;
  85         }
  86       else
  87         {
  88           size_t step;
  89
  90           for (step = 2; step < 6; ++step)
  91             if ((wc & encoding_mask[step - 2]) == 0)
  92               break;
  93
  94           if (written + step >= len)
  95             /* Too long.  */
  96             break;
  97
  98           if (dst != NULL)
  99             {
 100               size_t cnt = step;
 101
 102               dst[0] = encoding_byte[cnt - 2];
 103
 104               --cnt;
 105               do
 106                 {
 107                   dst[cnt] = 0x80 | (wc & 0x3f);
 108                   wc >>= 6;
 109                 }
 110               while (--cnt > 0);
 111               dst[0] |= wc;
 112
 113               dst += step;
 114             }
 115
 116           written += step;
 117         }
 118     }
 119
 120   /* Store position of first unprocessed word.  */
 121   *src = run;
 122
 123   return written;
 124 }