blob: c56db053d80e66074473c20e4878b63ddcc155b8 (
plain)
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
|
/*
Miranda IM: the free IM client for Microsoft* Windows*
Copyright 2000-2009 Miranda ICQ/IM project,
all portions of this codebase are copyrighted to the people
listed in contributors.txt.
Copyright 2000 Alexandre Julliard of Wine project
(UTF-8 conversion routines)
This program 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 2
of the License, or (at your option) any later version.
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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include "dbtool.h"
bool is_utf8_string(const char* str)
{
int expect_bytes = 0, utf_found = 0;
if (!str) return 0;
while (*str) {
if ((*str & 0x80) == 0) {
/* Looks like an ASCII character */
if (expect_bytes)
/* byte of UTF-8 character expected */
return 0;
}
else {
/* Looks like byte of an UTF-8 character */
if (expect_bytes) {
/* expect_bytes already set: first byte of UTF-8 char already seen */
if ((*str & 0xC0) != 0x80) {
/* again first byte ?!?! */
return 0;
}
}
else {
/* First byte of the UTF-8 character */
/* count initial one bits and set expect_bytes to 1 less */
char ch = *str;
while (ch & 0x80) {
expect_bytes++;
ch = (ch & 0x7f) << 1;
}
}
/* OK, next byte of UTF-8 character */
/* Decrement number of expected bytes */
if ( --expect_bytes == 0 )
utf_found = 1;
}
str++;
}
return (utf_found && expect_bytes == 0);
}
|
