blob: 0af7bf48cc083fc80bc72ce98fc95e9e38b2fa41 (
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
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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
/* "$Id: $"
*
* Author: Jean-Marc Lienher ( http://oksid.ch )
* Copyright 2000-2003 by O'ksi'D.
*
* This library is free software. Distribution and use rights are outlined in
* the file "COPYING" which should have been included with this file. If this
* file is missing or damaged, see the license at:
*
* http://www.fltk.org/COPYING.php
*
* Please report all bugs and problems on the following page:
*
* http://www.fltk.org/str.php
*/
#if defined(WIN32) || defined(__APPLE__) // PORTME: Fl_Screen_Driver - platform unicode
#elif defined(FL_PORTING)
# pragma message "FL_PORTING: utf8"
#else
#endif
/*
* Unicode to UTF-8 conversion functions.
*/
#if defined(WIN32)
#elif defined(__APPLE__)
#elif defined(FL_PORTING)
# pragma message "FL_PORTING: do you want to include Xutf8.h?"
#else
#include "../Xutf8.h"
/*** NOTE : all functions are LIMITED to 24 bits Unicode values !!! ***/
/*
* Converts the first char of the UTF-8 string to an Unicode value
* Returns the byte length of the converted UTF-8 char
* Returns -1 if the UTF-8 string is not valid
*/
int
XConvertUtf8ToUcs(const unsigned char *buf,
int len,
unsigned int *ucs) {
if (buf[0] & 0x80) {
if (buf[0] & 0x40) {
if (buf[0] & 0x20) {
if (buf[0] & 0x10) {
if (buf[0] & 0x08) {
if (buf[0] & 0x04) {
if (buf[0] & 0x02) {
/* bad UTF-8 string */
} else {
/* 0x04000000 - 0x7FFFFFFF */
}
} else if (len > 4
&& (buf[1] & 0xC0) == 0x80
&& (buf[2] & 0xC0) == 0x80
&& (buf[3] & 0xC0) == 0x80
&& (buf[4] & 0xC0) == 0x80) {
/* 0x00200000 - 0x03FFFFFF */
*ucs = ((buf[0] & ~0xF8) << 24) +
((buf[1] & ~0x80) << 18) +
((buf[2] & ~0x80) << 12) +
((buf[3] & ~0x80) << 6) +
(buf[4] & ~0x80);
if (*ucs > 0x001FFFFF && *ucs < 0x01000000) return 5;
}
} else if (len > 3
&& (buf[1] & 0xC0) == 0x80
&& (buf[2] & 0xC0) == 0x80
&& (buf[3] & 0xC0) == 0x80) {
/* 0x00010000 - 0x001FFFFF */
*ucs = ((buf[0] & ~0xF0) << 18) +
((buf[1] & ~0x80) << 12) +
((buf[2] & ~0x80) << 6) +
(buf[3] & ~0x80);
if (*ucs > 0x0000FFFF) return 4;
}
} else if (len > 2
&& (buf[1] & 0xC0) == 0x80
&& (buf[2] & 0xC0) == 0x80) {
/* 0x00000800 - 0x0000FFFF */
*ucs = ((buf[0] & ~0xE0) << 12) +
((buf[1] & ~0x80) << 6) +
(buf[2] & ~0x80);
if (*ucs > 0x000007FF) return 3;
}
} else if (len > 1 && (buf[1] & 0xC0) == 0x80) {
/* 0x00000080 - 0x000007FF */
*ucs = ((buf[0] & ~0xC0) << 6) +
(buf[1] & ~0x80);
if (*ucs > 0x0000007F) return 2;
}
}
} else if (len > 0) {
/* 0x00000000 - 0x0000007F */
*ucs = buf[0];
return 1;
}
*ucs = (unsigned int) '?'; /* bad utf-8 string */
return -1;
}
/*
* Converts an Unicode value to an UTF-8 string
* NOTE : the buffer (buf) must be at least 5 bytes long !!!
*/
int
XConvertUcsToUtf8(unsigned int ucs,
char *buf) {
if (ucs < 0x000080) {
buf[0] = ucs;
return 1;
} else if (ucs < 0x000800) {
buf[0] = 0xC0 | (ucs >> 6);
buf[1] = 0x80 | (ucs & 0x3F);
return 2;
} else if (ucs < 0x010000) {
buf[0] = 0xE0 | (ucs >> 12);
buf[1] = 0x80 | ((ucs >> 6) & 0x3F);
buf[2] = 0x80 | (ucs & 0x3F);
return 3;
} else if (ucs < 0x00200000) {
buf[0] = 0xF0 | (ucs >> 18);
buf[1] = 0x80 | ((ucs >> 12) & 0x3F);
buf[2] = 0x80 | ((ucs >> 6) & 0x3F);
buf[3] = 0x80 | (ucs & 0x3F);
return 4;
} else if (ucs < 0x01000000) {
buf[0] = 0xF8 | (ucs >> 24);
buf[1] = 0x80 | ((ucs >> 18) & 0x3F);
buf[2] = 0x80 | ((ucs >> 12) & 0x3F);
buf[3] = 0x80 | ((ucs >> 6) & 0x3F);
buf[4] = 0x80 | (ucs & 0x3F);
return 5;
}
buf[0] = '?';
return -1;
}
/*
* returns the byte length of the first UTF-8 char
* (returns -1 if not valid)
*/
int
XUtf8CharByteLen(const unsigned char *buf,
int len) {
unsigned int ucs;
return XConvertUtf8ToUcs(buf, len, &ucs);
}
/*
* returns the quantity of Unicode chars in the UTF-8 string
*/
int
XCountUtf8Char(const unsigned char *buf,
int len) {
int i = 0;
int nbc = 0;
while (i < len) {
int cl = XUtf8CharByteLen(buf + i, len - i);
if (cl < 1) cl = 1;
nbc++;
i += cl;
}
return nbc;
}
/*
* Same as XConvertUtf8ToUcs but no sanity check is done.
*/
int
XFastConvertUtf8ToUcs(const unsigned char *buf,
int len,
unsigned int *ucs) {
if (buf[0] & 0x80) {
if (buf[0] & 0x40) {
if (buf[0] & 0x20) {
if (buf[0] & 0x10) {
if (buf[0] & 0x08) {
if (buf[0] & 0x04) {
if (buf[0] & 0x02) {
/* bad UTF-8 string */
} else {
/* 0x04000000 - 0x7FFFFFFF */
}
} else if (len > 4) {
/* 0x00200000 - 0x03FFFFFF */
*ucs = ((buf[0] & ~0xF8) << 24) +
((buf[1] & ~0x80) << 18) +
((buf[2] & ~0x80) << 12) +
((buf[3] & ~0x80) << 6) +
(buf[4] & ~0x80);
return 5;
}
} else if (len > 3) {
/* 0x00010000 - 0x001FFFFF */
*ucs = ((buf[0] & ~0xF0) << 18) +
((buf[1] & ~0x80) << 12) +
((buf[2] & ~0x80) << 6) +
(buf[3] & ~0x80);
return 4;
}
} else if (len > 2) {
/* 0x00000800 - 0x0000FFFF */
*ucs = ((buf[0] & ~0xE0) << 12) +
((buf[1] & ~0x80) << 6) +
(buf[2] & ~0x80);
return 3;
}
} else if (len > 1) {
/* 0x00000080 - 0x000007FF */
*ucs = ((buf[0] & ~0xC0) << 6) +
(buf[1] & ~0x80);
return 2;
}
}
} else if (len > 0) {
/* 0x00000000 - 0x0000007F */
*ucs = buf[0];
return 1;
}
*ucs = (unsigned int) '?'; /* bad utf-8 string */
return -1;
}
#endif /* X11 only */
/*
* End of "$Id: $".
*/
|
