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
|
/* This file is (c) 2008-2012 Konstantin Isakov <ikm@goldendict.org>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "utf8.hh"
#include <vector>
#include <algorithm>
namespace Utf8 {
size_t encode( wchar const * in, size_t inSize, char * out_ )
{
unsigned char * out = (unsigned char *) out_;
while( inSize-- )
{
if ( *in < 0x80 )
*out++ = *in++;
else
if ( *in < 0x800 )
{
*out++ = 0xC0 | ( *in >> 6 );
*out++ = 0x80 | ( *in++ & 0x3F );
}
else
if ( *in < 0x10000 )
{
*out++ = 0xE0 | ( *in >> 12 );
*out++ = 0x80 | ( ( *in >> 6 ) & 0x3F );
*out++ = 0x80 | ( *in++ & 0x3F );
}
else
{
*out++ = 0xF0 | ( *in >> 18 );
*out++ = 0x80 | ( ( *in >> 12 ) & 0x3F );
*out++ = 0x80 | ( ( *in >> 6 ) & 0x3F );
*out++ = 0x80 | ( *in++ & 0x3F );
}
}
return out - (unsigned char *) out_;
}
long decode( char const * in_, size_t inSize, wchar * out_ )
{
unsigned char const * in = (unsigned char const *) in_;
wchar * out = out_;
while( inSize-- )
{
wchar result;
if ( *in & 0x80 )
{
if ( *in & 0x40 )
{
if ( *in & 0x20 )
{
if ( *in & 0x10 )
{
// Four-byte sequence
if ( *in & 8 )
// This can't be
return -1;
if ( inSize < 3 )
return -1;
inSize -= 3;
result = ( (wchar )*in++ & 7 ) << 18;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= ( (wchar)*in++ & 0x3F ) << 12;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= ( (wchar)*in++ & 0x3F ) << 6;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= (wchar)*in++ & 0x3F;
}
else
{
// Three-byte sequence
if ( inSize < 2 )
return -1;
inSize -= 2;
result = ( (wchar )*in++ & 0xF ) << 12;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= ( (wchar)*in++ & 0x3F ) << 6;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= (wchar)*in++ & 0x3F;
}
}
else
{
// Two-byte sequence
if ( !inSize )
return -1;
--inSize;
result = ( (wchar )*in++ & 0x1F ) << 6;
if ( ( *in & 0xC0 ) != 0x80 )
return -1;
result |= (wchar)*in++ & 0x3F;
}
}
else
{
// This char is from the middle of encoding, it can't be leading
return -1;
}
}
else
// One-byte encoding
result = *in++;
*out++ = result;
}
return out - out_;
}
string encode( wstring const & in ) noexcept
{
if( in.size() == 0 )
return string();
std::vector< char > buffer( in.size() * 4 );
return string( &buffer.front(),
encode( in.data(), in.size(), &buffer.front() ) );
}
wstring decode( string const & in )
{
if ( in.size() == 0 )
return wstring();
std::vector< wchar > buffer( in.size() );
long result = decode( in.data(), in.size(), &buffer.front() );
if ( result < 0 )
throw exCantDecode( in );
return wstring( &buffer.front(), result );
}
bool isspace( int c )
{
switch( c )
{
case ' ':
case '\f':
case '\n':
case '\r':
case '\t':
case '\v':
return true;
default:
return false;
}
}
//get the first line in string s1. -1 if not found
int findFirstLinePosition( char* s1,int s1length, const char* s2,int s2length)
{
char* pos = std::search(s1,s1+s1length, s2, s2+s2length);
if (pos == s1 + s1length)
return pos-s1;
//the line size.
return pos- s1+ s2length;
}
char const* getEncodingNameFor(Encoding e)
{
switch (e)
{
case Utf16LE:
return "UTF-16LE";
case Utf16BE:
return "UTF-16BE";
case Windows1252:
return "WINDOWS-1252";
case Windows1251:
return "WINDOWS-1251";
case Utf8:
return "UTF-8";
case Windows1250:
default:
return "WINDOWS-1250";
}
}
LineFeed initLineFeed(Encoding e)
{
LineFeed lf;
switch (e)
{
case Utf8::Utf16LE:
lf.lineFeed= new char[2]{ 0x0A,0 };
lf.length = 2;
break;
case Utf8::Utf16BE:
lf.lineFeed = new char[2]{ 0,0x0A };
lf.length = 2;
break;
case Utf8::Windows1252:
case Utf8::Windows1251:
case Utf8::Utf8:
case Utf8::Windows1250:
default:
lf.length = 1;
lf.lineFeed = new char[1]{ 0x0A };
}
return lf;
}
}
|
