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
240
241
242
243
244
245
246
247
248
|
/////////1/////////2/////////3/////////4/////////5/////////6/////////7/////////8
// test_utf8_codecvt.cpp
// (C) Copyright 2002-4 Robert Ramey - http://www.rrsd.com .
// Use, modification and distribution is subject to the Boost Software
// License, Version 1.0. (See accompanying file LICENSE_1_0.txt or copy at
// http://www.boost.org/LICENSE_1_0.txt)
#include <algorithm>
#include <fstream>
#include <iostream>
#include <iterator>
#include <locale>
#include <vector>
#include <string>
#include <cstddef> // size_t
#include <boost/config.hpp>
#if defined(BOOST_NO_STDC_NAMESPACE)
namespace std{
using ::size_t;
} // namespace std
#endif
#include <cwchar>
#ifdef BOOST_NO_STDC_NAMESPACE
namespace std{ using ::wcslen; }
#endif
#include "../test/test_tools.hpp"
#include <boost/archive/iterators/istream_iterator.hpp>
#include <boost/archive/iterators/ostream_iterator.hpp>
#include <boost/archive/add_facet.hpp>
#include <boost/archive/detail/utf8_codecvt_facet.hpp>
template<std::size_t s>
struct test_data
{
static unsigned char utf8_encoding[];
static wchar_t wchar_encoding[];
};
template<>
unsigned char test_data<2>::utf8_encoding[] = {
0x01,
0x7f,
0xc2, 0x80,
0xdf, 0xbf,
0xe0, 0xa0, 0x80,
0xe7, 0xbf, 0xbf
};
template<>
wchar_t test_data<2>::wchar_encoding[] = {
0x0001,
0x007f,
0x0080,
0x07ff,
0x0800,
0x7fff
};
template<>
unsigned char test_data<4>::utf8_encoding[] = {
0x01,
0x7f,
0xc2, 0x80,
0xdf, 0xbf,
0xe0, 0xa0, 0x80,
0xef, 0xbf, 0xbf,
0xf0, 0x90, 0x80, 0x80,
0xf4, 0x8f, 0xbf, 0xbf,
0xf7, 0xbf, 0xbf, 0xbf,
0xf8, 0x88, 0x80, 0x80, 0x80,
0xfb, 0xbf, 0xbf, 0xbf, 0xbf,
0xfc, 0x84, 0x80, 0x80, 0x80, 0x80,
0xfd, 0xbf, 0xbf, 0xbf, 0xbf, 0xbf
};
template<>
wchar_t test_data<4>::wchar_encoding[] = {
0x00000001,
0x0000007f,
0x00000080,
0x000007ff,
0x00000800,
0x0000ffff,
0x00010000,
0x0010ffff,
0x001fffff,
0x00200000,
0x03ffffff,
0x04000000,
0x7fffffff
};
int
test_main(int /* argc */, char * /* argv */[]) {
std::locale old_loc;
std::locale * utf8_locale
= boost::archive::add_facet(
old_loc,
new boost::archive::detail::utf8_codecvt_facet
);
typedef char utf8_t;
typedef test_data<sizeof(wchar_t)> td;
// Send our test UTF-8 data to file
{
std::ofstream ofs;
ofs.open("test.dat", std::ios::binary);
std::copy(
td::utf8_encoding,
#if ! defined(__BORLANDC__)
// borland 5.60 complains about this
td::utf8_encoding + sizeof(td::utf8_encoding) / sizeof(unsigned char),
#else
// so use this instead
td::utf8_encoding + 12,
#endif
boost::archive::iterators::ostream_iterator<utf8_t>(ofs)
);
}
// Read the test data back in, converting to UCS-4 on the way in
std::vector<wchar_t> from_file;
{
std::wifstream ifs;
ifs.imbue(*utf8_locale);
ifs.open("test.dat");
wchar_t item = 0;
// note can't use normal vector from iterator constructor because
// dinkumware doesn't have it.
for(;;){
item = ifs.get();
if(item == WEOF)
break;
//ifs >> item;
//if(ifs.eof())
// break;
from_file.push_back(item);
}
}
// compare the data read back in with the orginal
#if ! defined(__BORLANDC__)
// borland 5.60 complains about this
BOOST_CHECK(from_file.size() == sizeof(td::wchar_encoding)/sizeof(wchar_t));
#else
// so use this instead
BOOST_CHECK(from_file.size() == 6);
#endif
BOOST_CHECK(std::equal(from_file.begin(), from_file.end(), td::wchar_encoding));
// Send the UCS4_data back out, converting to UTF-8
{
std::wofstream ofs;
ofs.imbue(*utf8_locale);
ofs.open("test2.dat");
std::copy(
from_file.begin(),
from_file.end(),
boost::archive::iterators::ostream_iterator<wchar_t>(ofs)
);
}
// Make sure that both files are the same
{
typedef boost::archive::iterators::istream_iterator<utf8_t> is_iter;
is_iter end_iter;
std::ifstream ifs1("test.dat");
is_iter it1(ifs1);
std::vector<utf8_t> data1;
std::copy(it1, end_iter, std::back_inserter(data1));
std::ifstream ifs2("test2.dat");
is_iter it2(ifs2);
std::vector<utf8_t> data2;
std::copy(it2, end_iter, std::back_inserter(data2));
BOOST_CHECK(data1 == data2);
}
// some libraries have trouble that only shows up with longer strings
wchar_t * test3_data = L"\
<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\" ?>\
<!DOCTYPE boost_serialization>\
<boost_serialization signature=\"serialization::archive\" version=\"3\">\
<a class_id=\"0\" tracking_level=\"0\">\
<b>1</b>\
<f>96953204</f>\
<g>177129195</g>\
<l>1</l>\
<m>5627</m>\
<n>23010</n>\
<o>7419</o>\
<p>16212</p>\
<q>4086</q>\
<r>2749</r>\
<c>-33</c>\
<s>124</s>\
<t>28</t>\
<u>32225</u>\
<v>17543</v>\
<w>0.84431422</w>\
<x>1.0170664757130923</x>\
<y>tjbx</y>\
<z>cuwjentqpkejp</z>\
</a>\
</boost_serialization>\
";
// Send the UCS4_data back out, converting to UTF-8
std::size_t l = std::wcslen(test3_data);
{
std::wofstream ofs;
ofs.imbue(*utf8_locale);
ofs.open("test3.dat");
std::copy(
test3_data,
test3_data + l,
boost::archive::iterators::ostream_iterator<wchar_t>(ofs)
);
}
// Make sure that both files are the same
{
std::wifstream ifs;
ifs.imbue(*utf8_locale);
ifs.open("test3.dat");
BOOST_CHECK(
std::equal(
test3_data,
test3_data + l,
boost::archive::iterators::istream_iterator<wchar_t>(ifs)
)
);
}
delete utf8_locale;
return EXIT_SUCCESS;
}
|
