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
|
// **********************************************************************
//
// Copyright (c) 2003-2014 ZeroC, Inc. All rights reserved.
//
// This copy of Ice is licensed to you under the terms described in the
// ICE_LICENSE file included in this distribution.
//
// **********************************************************************
#include <IceUtil/IceUtil.h>
#include <TestCommon.h>
#ifdef _WIN32
# include <io.h>
#else
# include <unistd.h>
#endif
#include <fstream>
using namespace IceUtil;
using namespace std;
//
// Note that each file starts with a BOM; stringToWstring and wstringToString
// converts these BOMs back and forth.
//
//COMPILERFIX: MINGW doesn't support wmain for console applications.
#if defined(_WIN32) && !defined(__MINGW32__)
int
wmain(int argc, wchar_t* argv[])
#else
int
main(int argc, char* argv[])
#endif
{
string dir = "";
if(argc > 1)
{
#ifdef _WIN32
# ifdef __MINGW32__
dir = argv[1];
# else
dir = IceUtil::wstringToString(argv[1]);
# endif
dir += "\\";
#else
dir = argv[1];
dir += "/";
#endif
}
ostringstream os;
os << "utf" << sizeof(wchar_t) * 8;
#ifdef ICE_LITTLE_ENDIAN
os << "le";
#else
os << "be";
#endif
string wstringEncoding = os.str();
string wcoeurFile = string("coeur.") + wstringEncoding;
{
cout << "testing UTF-8 to wstring (" << wstringEncoding << ") conversion... ";
ifstream is((dir + "coeur.utf8").c_str());
test(is.good());
ifstream bis((dir + wcoeurFile).c_str(), ios_base::binary);
test(bis.good());
int lineNumber = 0;
do
{
string line;
getline(is, line, '\n');
test(isLegalUTF8Sequence(reinterpret_cast<const Byte*>(line.data()),
reinterpret_cast<const Byte*>(line.data() + line.size())));
lineNumber++;
wstring wline = stringToWstring(line);
for(size_t i = 0; i < wline.length(); ++i)
{
wchar_t wc = wline[i];
const char* buffer = reinterpret_cast<char*>(&wc);
for(size_t j = 0; j < sizeof(wchar_t); ++j)
{
test(bis.good());
char c;
bis.get(c);
if(buffer[j] != c)
{
cerr << "Error at line " << lineNumber << " column " << i << endl;
cerr << "buffer[j] == " << hex << (int)static_cast<unsigned char>(buffer[j]) << endl;
cerr << "c == " << hex << (int)static_cast<unsigned char>(c) << endl;
}
test(buffer[j] == c);
}
}
//
// Skip newline character (Unix-style newline)
//
if(is.good())
{
for(size_t j = 0; j < sizeof(wchar_t); ++j)
{
test(bis.good());
char c;
bis.get(c);
}
}
else
{
char c;
bis.get(c);
test(bis.eof());
}
} while(is.good());
cout << "ok" << endl;
}
{
cout << "testing wstring (" << wstringEncoding << ") to UTF-8 conversion... ";
ifstream bis((dir + wcoeurFile).c_str(), ios_base::binary);
test(bis.good());
wstring ws;
char c;
do
{
wchar_t wc;
char* buffer = reinterpret_cast<char*>(&wc);
for(size_t j = 0; j < sizeof(wchar_t); ++j)
{
if(!bis.good())
{
break;
}
bis.get(c);
buffer[j] = c;
}
if(bis.good())
{
ws.push_back(wc);
}
} while(bis.good());
string s = wstringToString(ws);
ifstream nbis((dir + "coeur.utf8").c_str(), ios_base::binary);
test(nbis.good());
for(size_t i = 0; i < s.size(); ++i)
{
test(nbis.good());
nbis.get(c);
char ci = s[i];
if(c != ci)
{
cerr << "i == " << i << endl;
cerr << "ci == " << hex << (int)static_cast<unsigned char>(ci) << endl;
cerr << "c == " << hex << (int)static_cast<unsigned char>(c) << endl;
}
test(c == s[i]);
}
test(!nbis.eof());
nbis.get(c);
test(nbis.eof());
cout << "ok" << endl;
}
{
cout << "testing error handling... ";
// From http://stackoverflow.com/questions/1301402/example-invalid-utf8-string
string badUTF8[] = {
"\xc3\x28",
"\xa0\xa1",
"\xe2\x28\xa1",
"\xe2\x82\x28",
"\xf0\x28\x8c\xbc",
"\xf0\x90\x28\xbc",
"\xf0\x28\x8c\x28",
"\xf8\xa1\xa1\xa1\xa1",
"\xfc\xa1\xa1\xa1\xa1\xa1",
""
};
for(size_t i = 0; badUTF8[i] != ""; ++i)
{
test(isLegalUTF8Sequence(reinterpret_cast<const Byte*>(badUTF8[i].data()),
reinterpret_cast<const Byte*>(badUTF8[i].data() + badUTF8[i].size())) == false);
try
{
wstring ws = IceUtil::stringToWstring(badUTF8[i]);
test(false);
}
catch(const IceUtil::IllegalConversionException&)
{}
}
// TODO: need test for bad UTF-32 strings
#ifdef _WIN32
wstring badWstring[] = {
wstring(1, wchar_t(0xD800)),
wstring(2, wchar_t(0xDB7F)),
L""
};
for(size_t i = 0; badWstring[i] != L""; ++i)
{
try
{
string s = IceUtil::wstringToString(badWstring[i]);
test(false);
}
catch(const IceUtil::IllegalConversionException&)
{}
}
#endif
cout << "ok" << endl;
}
return EXIT_SUCCESS;
}
|
