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
|
/*
* virt_mbrtowc.c
*
* $Id: virt_mbrtowc.c,v 1.1.1.1 2006/04/11 17:56:16 source Exp $
*
* This file is part of the OpenLink Software Virtuoso Open-Source (VOS)
* project.
*
* Copyright (C) 1998-2006 OpenLink Software
*
* This project is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; only version 2 of the License, dated June 1991.
*
* This program 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
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
*
*/
#include "libutil.h"
size_t
virt_mbrtowc (wchar_t *pwc, const unsigned char *s, size_t n, virt_mbstate_t *ps)
{
size_t used = 0;
static virt_mbstate_t internal;
if (ps == NULL)
ps = &internal;
if (s == NULL)
{
/* See first paragraph of description in 7.16.6.3.2. */
pwc = NULL;
s = (unsigned char *) "";
n = 1;
}
if (n > 0)
{
if (ps->count == 0)
{
unsigned char byte = (unsigned char) *s++;
++used;
/* We must look for a possible first byte of a UTF8 sequence. */
if (byte < 0x80)
{
/* One byte sequence. */
if (pwc != NULL)
*pwc = (wchar_t) byte;
return byte ? used : 0;
}
if ((byte & 0xc0) == 0x80 || (byte & 0xfe) == 0xfe)
{
/* Oh, oh. An encoding error. */
/* errno = (EILSEQ); */
return (size_t) -1;
}
if ((byte & 0xe0) == 0xc0)
{
/* We expect two bytes. */
ps->count = 1;
ps->value = byte & 0x1f;
}
else if ((byte & 0xf0) == 0xe0)
{
/* We expect three bytes. */
ps->count = 2;
ps->value = byte & 0x0f;
}
else if ((byte & 0xf8) == 0xf0)
{
/* We expect four bytes. */
ps->count = 3;
ps->value = byte & 0x07;
}
else if ((byte & 0xfc) == 0xf8)
{
/* We expect five bytes. */
ps->count = 4;
ps->value = byte & 0x03;
}
else
{
/* We expect six bytes. */
ps->count = 5;
ps->value = byte & 0x01;
}
}
/* We know we have to handle a multibyte character and there are
some more bytes to read. */
while (used < n)
{
/* The second to sixths byte must be of the form 10xxxxxx. */
unsigned char byte = (unsigned char) *s++;
++used;
if ((byte & 0xc0) != 0x80)
{
/* Oh, oh. An encoding error. */
/* errno = (EILSEQ); */
return (size_t) -1;
}
ps->value <<= 6;
ps->value |= byte & 0x3f;
if (--ps->count == 0)
{
/* The character is finished. */
if (pwc != NULL)
*pwc = (wchar_t) ps->value;
return ps->value ? used : 0;
}
}
}
return (size_t) -2;
}
|
