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
|
#include "WChar.class.h"
WChar WChar::CP437[] = { //These are the UTF8 equivalents for the 128 extra characters of code page 850
"Ç", "ü", "é", "â", "ä", "à", "å", "ç", "ê", "ë", "è", "ï", "î", "ì", "Ä", "Å",
"É", "æ", "Æ", "ô", "ö", "ò", "û", "ù", "ÿ", "Ö", "Ü", "¢", "£", "¥", "₧", "ƒ",
"á", "í", "ó", "ú", "ñ", "Ñ", "ª", "º", "¿", "⌐", "¬", "½", "¼", "¡", "«", "»",
"░", "▒", "▓", "│", "┤", "╡", "╢", "╖", "╕", "╣", "║", "╗", "╝", "╜", "╛", "┐",
"└", "┴", "┬", "├", "─", "┼", "╞", "╟", "╚", "╔", "╩", "╦", "╠", "═", "╬", "¤",
"╨", "╤", "╥", "╙", "╘", "╒", "╓", "╫", "╪", "┘", "┌", "█", "▄", "▌", "▐", "▀",
"α", "ß", "Γ", "π", "Σ", "σ", "µ", "τ", "Φ", "Θ", "Ω", "δ", "∞", "φ", "ε", "∩",
"≡", "±", "≥", "≤", "⌠", "⌡", "÷", "≈", "°", "∙", "·", "√", "ⁿ", "²", "■", "⍽"
};
WChar::WChar() {
value = 0;
}
WChar::WChar(char c) {
affectAscii(c);
}
WChar::WChar(const char* c, u8int encoding) {
if (encoding == UE_UTF8) affectUtf8(c);
if (encoding == UE_UTF16) affectUtf16(c);
if (encoding == UE_UTF32) affectUtf32(c);
}
u32int WChar::utfLen(const char* c, u8int encoding) {
int i = 0, l = CMem::strlen(c), co = 0;
while (i < l) {
if (encoding == UE_UTF8) {
if ((c[i] & 0x80) == 0) i += 1;
else if ((c[i] & 0xE0) == 0xC0) i += 2;
else if ((c[i] & 0xF0) == 0xE0) i += 3;
else if ((c[i] & 0xF8) == 0xF0) i += 4;
else i += 1;
co++;
} else if (encoding == UE_UTF16) {
if ((c[i] & 0xFC) == 0xD8 and (c[i + 2] & 0xFC) == 0xDC) i += 4;
else i += 2;
} else if (encoding == UE_UTF32) {
i += 4;
}
}
return co;
}
void WChar::affectAscii(char c) {
if (c >= 0) value = c;
else value = CP437[c + 128];
}
u32int WChar::affectUtf8(const char* c) { //Returns the number of bytes for the character
if ((c[0] & 0x80) == 0) {
value = c[0]; //0x80 = 10000000b
return 1;
}
if ((c[0] & 0xE0) == 0xC0) { // 11100000b, 11000000b
value = ((c[0] & 0x1F) << 6) | (c[1] & 0x3F);
if (value < 128) value = 0; //Bad value
return 2;
}
if ((c[0] & 0xF0) == 0xE0) { // 11110000b, 11100000b
value = ((c[0] & 0x0F) << 12) | ((c[1] & 0x3F) << 6) | (c[2] & 0x3F);
if (value < 2048) value = 0; //Bad value
if (value >= 0xD800 and value <= 0xDFFF) value = 0; //These values are unallowed
if (value >= 0xFFFE and value <= 0xFFFF) value = 0;
return 3;
}
if ((c[0] & 0xF8) == 0xF0) { // 11111000b, 11110000b
value = ((c[0] & 0x0E) << 18) | ((c[1] & 0x3F) << 12) | ((c[2] & 0x3F) << 6) | (c[3] & 0x3F);
if (value < 65536) value = 0; //Bad value
return 4;
}
value = 0; //Something wrong happenned
return 1;
}
u32int WChar::affectUtf16(const char* c) {
if ((c[0] & 0xFC) == 0xD8 and // 11111100b, 11011000b
(c[2] & 0xFC) == 0xDC) { // 11111100b, 11011100b
u32int w = ((c[0] & 0x03) << 2) | ((c[1] & 0xC0) >> 6);
u32int x = (c[1] & 0x3F);
u32int y = ((c[2] & 0x03) << 8) | (c[2]);
value = ((w + 1) << 16) | (x << 10) | y;
if (value >= 0xD800 and value <= 0xDFFF) value = 0; //These values are unallowed
if (value >= 0xFFFE and value <= 0xFFFF) value = 0;
return 4;
} else {
value = (c[0] << 8) | (c[1]);
if (value >= 0xD800 and value <= 0xDFFF) value = 0; //These values are unallowed
if (value >= 0xFFFE and value <= 0xFFFF) value = 0;
return 2;
}
}
u32int WChar::affectUtf32(const char* c) {
value = (c[0] << 24) | (c[1] << 16) | (c[2] << 8) | c[3];
if (value >= 0xD800 and value <= 0xDFFF) value = 0; //These values are unallowed
if (value >= 0xFFFE and value <= 0xFFFF) value = 0;
return 4;
}
u8int WChar::toAscii() {
if (value < 128) return (char)value;
for (int i = 0; i < 128; i++) {
if (CP437[i] == value) return (i + 128);
}
return '?';
}
uchar_repr_t WChar::toUtf8() {
uchar_repr_t r;
r.i = 0;
if (value < 128) {
r.c[0] = value;
} else if (value < 4096) {
r.c[0] = 0xC0 | ((value & 0x07C0) >> 6);
r.c[1] = 0x80 | (value & 0x3F);
} else if (value < 65536) {
r.c[0] = 0xE0 | ((value & 0xF000) >> 12);
r.c[1] = 0x80 | ((value & 0x0FC0) >> 6);
r.c[2] = 0x80 | (value & 0x003F);
} else {
r.c[0] = 0xF0 | ((value & 0x1C0000) >> 18);
r.c[1] = 0x80 | ((value & 0x3F000) >> 12);
r.c[2] = 0x80 | ((value & 0x0FC0) >> 6);
r.c[3] = 0x80 | (value & 0x003F);
}
return r;
}
//TODO : code WChar::toUtf16
uchar_repr_t WChar::toUtf32() {
uchar_repr_t r;
r.c[0] = (value >> 24) & 0xFF;
r.c[1] = (value >> 16) & 0xFF;
r.c[2] = (value >> 8) & 0xFF;
r.c[3] = value & 0xFF;
return r;
}
|
