summary refs log tree commit diff
path: root/wcsmbs/wcsnrtombs.c
blob: f6c80482955a6f2e617c9293c64fa833e0d1d53b (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
/* Copyright (C) 1996, 1997 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 1996.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 of the
   License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public
   License along with the GNU C Library; see the file COPYING.LIB.  If not,
   write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.  */

#include <errno.h>
#include <wchar.h>

#ifndef EILSEQ
#define EILSEQ EINVAL
#endif


static const wchar_t encoding_mask[] =
{
  ~0x7ff, ~0xffff, ~0x1fffff, ~0x3ffffff
};

static const unsigned char encoding_byte[] =
{
  0xc0, 0xe0, 0xf0, 0xf8, 0xfc
};

/* We don't need the state really because we don't have shift states
   to maintain between calls to this function.  */
static mbstate_t internal;

/* This is a non-standard function but it is very useful in the
   implementation of stdio because we have to deal with unterminated
   buffers.  At most NWC wide character will be converted.  */
size_t
__wcsnrtombs (dst, src, nwc, len, ps)
     char *dst;
     const wchar_t **src;
     size_t nwc;
     size_t len;
     mbstate_t *ps;
{
  size_t written = 0;
  const wchar_t *run = *src;

  if (ps == NULL)
    ps = &internal;

  if (dst == NULL)
    /* The LEN parameter has to be ignored if we don't actually write
       anything.  */
    len = ~0;

  while (written < len && nwc-- > 0)
    {
      wchar_t wc;

      /* Store position of first unprocessed word.  */
      *src = run;

      wc = *run++;

      if (wc < 0 || wc > 0x7fffffff)
	{
	  /* This is no correct ISO 10646 character.  */
	  __set_errno (EILSEQ);
	  return (size_t) -1;
	}

      if (wc == L'\0')
	{
	  /* Found the end.  */
	  if (dst != NULL)
	    *dst = '\0';
	  *src = NULL;
	  return written;
	}
      else if (wc < 0x80)
	{
	  /* It's an one byte sequence.  */
	  if (dst != NULL)
	    *dst++ = (char) wc;
	  ++written;
	}
      else
	{
	  size_t step;

	  for (step = 2; step < 6; ++step)
	    if ((wc & encoding_mask[step - 2]) == 0)
	      break;

	  if (written + step >= len)
	    /* Too long.  */
	    break;

	  if (dst != NULL)
	    {
	      size_t cnt = step;

	      dst[0] = encoding_byte[cnt - 2];

	      --cnt;
	      do
		{
		  dst[cnt] = 0x80 | (wc & 0x3f);
		  wc >>= 6;
		}
	      while (--cnt > 0);
	      dst[0] |= wc;

	      dst += step;
	    }

	  written += step;
	}
    }

  /* Store position of first unprocessed word.  */
  *src = run;

  return written;
}
weak_alias (__wcsnrtombs, wcsnrtombs)