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
|
/* FriBidi
* fribidi-char-sets-utf8.c - UTF-8 character set conversion routines
*
* Authors:
* Behdad Esfahbod, 2001, 2002, 2004
* Dov Grobgeld, 1999, 2000
*
* Copyright (C) 2004 Sharif FarsiWeb, Inc
* Copyright (C) 2001,2002 Behdad Esfahbod
* Copyright (C) 1999,2000 Dov Grobgeld
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this library, in a file named COPYING; if not, write to the
* Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA
*
* For licensing issues, contact <fribidi.license@gmail.com>.
*/
#include <common.h>
#include <fribidi-char-sets-utf8.h>
#include <fribidi-unicode.h>
FriBidiStrIndex
fribidi_utf8_to_unicode (
/* input */
const char *ss,
FriBidiStrIndex len,
/* output */
FriBidiChar *us
)
{
FriBidiStrIndex length;
const unsigned char *s = (unsigned const char *) ss;
const unsigned char *t = s;
length = 0;
while ((FriBidiStrIndex) (s - t) < len)
{
register unsigned char ch = *s;
if (ch <= 0x7f) /* one byte */
{
*us++ = *s++;
}
else if (ch <= 0xdf) /* 2 byte */
{
*us++ = ((*s & 0x1f) << 6) + (*(s + 1) & 0x3f);
s += 2;
}
else if (ch <= 0xef) /* 3 byte */
{
*us++ =
((int) (*s & 0x0f) << 12) +
((*(s + 1) & 0x3f) << 6) + (*(s + 2) & 0x3f);
s += 3;
}
else /* 4 byte */
{
*us++ =
((int) (*s & 0x07) << 18) +
((*(s + 1) & 0x3f) << 12) +
((*(s + 2) & 0x3f) << 6) +
((*(s + 3) & 0x3f) << 0);
s += 4;
}
length++;
}
return (length);
}
FriBidiStrIndex
fribidi_unicode_to_utf8 (
/* input */
const FriBidiChar *us,
FriBidiStrIndex len,
/* output */
char *ss
)
{
FriBidiStrIndex i;
unsigned char *s = (unsigned char *) ss;
unsigned char *t = s;
for (i = 0; i < len; i++)
{
FriBidiChar mychar = us[i];
if (mychar <= 0x7F)
{ /* 7 sig bits */
*t++ = mychar;
}
else if (mychar <= 0x7FF)
{ /* 11 sig bits */
*t++ = 0xC0 | (unsigned char) (mychar >> 6); /* upper 5 bits */
*t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lower 6 bits */
}
else if (mychar <= 0xFFFF)
{ /* 16 sig bits */
*t++ = 0xE0 | (unsigned char) (mychar >> 12); /* upper 4 bits */
*t++ = 0x80 | (unsigned char) ((mychar >> 6) & 0x3F); /* next 6 bits */
*t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lowest 6 bits */
}
else if (mychar < FRIBIDI_UNICODE_CHARS)
{ /* 21 sig bits */
*t++ = 0xF0 | (unsigned char) ((mychar >> 18) & 0x07); /* upper 3 bits */
*t++ = 0x80 | (unsigned char) ((mychar >> 12) & 0x3F); /* next 6 bits */
*t++ = 0x80 | (unsigned char) ((mychar >> 6) & 0x3F); /* next 6 bits */
*t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lowest 6 bits */
}
}
*t = 0;
return (t - s);
}
/* Editor directions:
* vim:textwidth=78:tabstop=8:shiftwidth=2:autoindent:cindent
*/
|