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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
|
/*
* $Id$
*
* ***** BEGIN GPL LICENSE BLOCK *****
*
* 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* The Original Code is Copyright (C) 2011 Blender Foundation.
* All rights reserved.
*
* Contributor(s): Campbell Barton.
*
* ***** END GPL LICENSE BLOCK *****
*
*/
/** \file blender/blenlib/intern/string_utf8.c
* \ingroup bli
*/
#include <string.h>
#include "BLI_string.h"
/* from libswish3, originally called u8_isvalid(),
* modified to return the index of the bad character (byte index not utf).
* http://svn.swish-e.org/libswish3/trunk/src/libswish3/utf8.c r3044 - campbell */
/* based on the valid_utf8 routine from the PCRE library by Philip Hazel
length is in bytes, since without knowing whether the string is valid
it's hard to know how many characters there are! */
static const char trailingBytesForUTF8[256] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};
int BLI_utf8_invalid_byte(const char *str, int length)
{
const unsigned char *p, *pend = (unsigned char*)str + length;
unsigned char c;
int ab;
for (p = (unsigned char*)str; p < pend; p++) {
c = *p;
if (c < 128)
continue;
if ((c & 0xc0) != 0xc0)
goto utf8_error;
ab = trailingBytesForUTF8[c];
if (length < ab)
goto utf8_error;
length -= ab;
p++;
/* Check top bits in the second byte */
if ((*p & 0xc0) != 0x80)
goto utf8_error;
/* Check for overlong sequences for each different length */
switch (ab) {
/* Check for xx00 000x */
case 1:
if ((c & 0x3e) == 0) goto utf8_error;
continue; /* We know there aren't any more bytes to check */
/* Check for 1110 0000, xx0x xxxx */
case 2:
if (c == 0xe0 && (*p & 0x20) == 0) goto utf8_error;
break;
/* Check for 1111 0000, xx00 xxxx */
case 3:
if (c == 0xf0 && (*p & 0x30) == 0) goto utf8_error;
break;
/* Check for 1111 1000, xx00 0xxx */
case 4:
if (c == 0xf8 && (*p & 0x38) == 0) goto utf8_error;
break;
/* Check for leading 0xfe or 0xff,
and then for 1111 1100, xx00 00xx */
case 5:
if (c == 0xfe || c == 0xff ||
(c == 0xfc && (*p & 0x3c) == 0)) goto utf8_error;
break;
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */
while (--ab > 0) {
if ((*(p+1) & 0xc0) != 0x80) goto utf8_error;
p++; /* do this after so we get usable offset - campbell */
}
}
return -1;
utf8_error:
return (int)((char *)p - (char *)str) - 1;
}
int BLI_utf8_invalid_strip(char *str, int length)
{
int bad_char, tot= 0;
while((bad_char= BLI_utf8_invalid_byte(str, length)) != -1) {
str += bad_char;
length -= bad_char;
if(length == 0) {
/* last character bad, strip it */
*str= '\0';
tot++;
break;
}
else {
/* strip, keep looking */
memmove(str, str + 1, length);
tot++;
}
}
return tot;
}
/* compatible with BLI_strncpy, but esnure no partial utf8 chars */
/* array copied from glib's gutf8.c,
* note: this looks to be at odd's with 'trailingBytesForUTF8',
* need to find out what gives here! - campbell */
static const size_t utf8_skip_data[256] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};
char *BLI_strncpy_utf8(char *dst, const char *src, size_t maxncpy)
{
char *dst_r= dst;
size_t utf8_size;
/* note: currently we dont attempt to deal with invalid utf8 chars */
while(*src != '\0' && (utf8_size= utf8_skip_data[*src]) < maxncpy) {
maxncpy -= utf8_size;
switch(utf8_size) {
case 6: *dst ++ = *src ++;
case 5: *dst ++ = *src ++;
case 4: *dst ++ = *src ++;
case 3: *dst ++ = *src ++;
case 2: *dst ++ = *src ++;
case 1: *dst ++ = *src ++;
}
}
*dst= '\0';
return dst_r;
}
|
