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
135
136
137
138
139
140
141
142
143
144
145
146
147
|
/* utf8.c - UTF-8 character handling functions */
/* Copyright (C) 2018 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
Bash 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, either version 3 of the License, or
(at your option) any later version.
Bash 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 Bash. If not, see <http://www.gnu.org/licenses/>.
*/
#include <config.h>
#ifdef HAVE_STDLIB_H
# include <stdlib.h>
#endif
#include "bashansi.h"
#include "shmbutil.h"
extern int locale_mb_cur_max;
extern int locale_utf8locale;
#if defined (HANDLE_MULTIBYTE)
char *
utf8_mbschr (s, c)
const char *s;
int c;
{
return strchr (s, c); /* for now */
}
int
utf8_mbscmp (s1, s2)
const char *s1, *s2;
{
/* Use the fact that the UTF-8 encoding preserves lexicographic order. */
return strcmp (s1, s2);
}
char *
utf8_mbsmbchar (str)
const char *str;
{
register char *s;
for (s = (char *)str; *s; s++)
if ((*s & 0xc0) == 0x80)
return s;
return (0);
}
int
utf8_mbsnlen(src, srclen, maxlen)
const char *src;
size_t srclen;
int maxlen;
{
register int sind, count;
for (sind = count = 0; src[sind] && sind <= maxlen; sind++)
{
if ((src[sind] & 0xc0) != 0x80)
count++;
}
return (count);
}
/* Adapted from GNU gnulib */
int
utf8_mblen (s, n)
const char *s;
size_t n;
{
unsigned char c, c1;
if (s == 0)
return (0); /* no shift states */
if (n <= 0)
return (-1);
c = (unsigned char)*s;
if (c < 0x80)
return (c != 0);
if (c >= 0xc2)
{
c1 = (unsigned char)s[1];
if (c < 0xe0)
{
if (n >= 2 && (s[1] ^ 0x80) < 0x40)
return 2;
}
else if (c < 0xf0)
{
if (n >= 3
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (c >= 0xe1 || c1 >= 0xa0)
&& (c != 0xed || c1 < 0xa0))
return 3;
}
else if (c < 0xf8)
{
if (n >= 4
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (s[3] ^ 0x80) < 0x40
&& (c >= 0xf1 || c1 >= 0x90)
&& (c < 0xf4 || (c == 0xf4 && c1 < 0x90)))
return 4;
}
}
/* invalid or incomplete multibyte character */
return -1;
}
/* We can optimize this if we know the locale is UTF-8, but needs to handle
malformed byte sequences. */
size_t
utf8_mbstrlen(s)
const char *s;
{
size_t clen, nc;
int mb_cur_max;
nc = 0;
mb_cur_max = MB_CUR_MAX;
while (*s && (clen = (size_t)utf8_mblen(s, mb_cur_max)) != 0)
{
if (MB_INVALIDCH(clen))
clen = 1; /* assume single byte */
s += clen;
nc++;
}
return nc;
}
#endif
|
