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
|
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.
/*============================================================================
**
** Source: test4.c
**
** Purpose: Tests MultiByteToWideChar with a UTF-8 encoding
**
**
**==========================================================================*/
#include <palsuite.h>
int __cdecl main(int argc, char *argv[])
{
int ret;
int ret2;
if (PAL_Initialize(argc, argv))
{
return FAIL;
}
const char * const utf8Strings[] =
{
// Correct strings
// Empty string
"",
// 1 byte encoded 1 character long string
"A",
// 2 byte encoded 1 character long string
"\xC2\x80",
// 3 byte encoded 1 character long string
"\xE0\xA0\x80",
// 1 byte encoded characters only
"ABCDEFGHIJKLMNOPQRSTUVWXYZ",
// valid 2 byte encoded characters only
"\xC2\x80\xC3\xBF\xC7\x81\xDF\xBF",
// valid 3 byte encoded characters only
"\xE0\xA0\x80\xE1\xB6\x88\xE1\x80\x80\xEF\xBF\xBF",
// 1 byte and 2 byte encoded characters interleaved 1:1 starting and ending with 1 byte char
"\x41\xC2\x80\x42\xC3\xBF\x43\xC7\x81\x44\xDF\xBF\x45",
// 1 byte and 2 byte encoded characters interleaved 1:1 starting with 1 byte char, ending with 2 byte one
"\x41\xC2\x80\x42\xC3\xBF\x43\xC7\x81\x44\xDF\xBF",
// 1 byte and 2 byte encoded characters interleaved 1:1 starting with 2 byte char, ending with 1 byte one
"\xC2\x80\x42\xC3\xBF\x43\xC7\x81\x44\xDF\xBF\x45",
// 1 byte and 2 byte encoded characters interleaved 1:1 starting and ending with 2 byte char
"\xC2\x80\x42\xC3\xBF\x43\xC7\x81\x44\xDF\xBF",
// 1 byte and 2 byte encoded characters interleaved 2:2 starting and ending with 1 byte char
"\x41\x42\xC2\x80\xC3\xBF\x43\x44\xC7\x81\xDF\xBF\x45\x46",
// 1 byte and 2 byte encoded characters interleaved 2:2 starting with 1 byte char, ending with 2 byte one
"\x41\x42\xC2\x80\xC3\xBF\x43\x44\xC7\x81\xDF\xBF",
// 1 byte and 2 byte encoded characters interleaved 2:2 starting with 2 byte char, ending with 1 byte one
"\xC2\x80\xC3\xBF\x43\x44\xC7\x81\xDF\xBF\x45\x46",
// 1 byte and 2 byte encoded characters interleaved 2:2 starting and ending with 2 byte char
"\xC2\x80\xC3\xBF\x43\x44\xC7\x81\xDF\xBF",
// surrogates
"\xF0\x90\x80\x80\xF0\x90\x89\x80\xF3\x80\x8E\xB0\xF4\x8F\xBF\xBF",
// Strings with errors
// Incomplete 2 byte encoded character 1 byte missing standalone
"\xC2",
// Incomplete 3 byte encoded character 1 byte missing standalone
"\xE0\xA0",
// Incomplete 3 byte encoded character 2 bytes missing standalone
"\xE0",
// Incomplete surrogate character 1 byte missing standalone
"\xF0\x90\x80",
// Incomplete surrogate character 2 bytes missing standalone
"\xF0\x90",
// Incomplete surrogate character 3 bytes missing standalone
"\xF0",
// Trailing byte with no lead byte standalone
"\x80",
// Incomplete 2 byte encoded character 1 byte missing between 1 byte chars
"\x41\xC2\x42",
// Incomplete 3 byte encoded character 1 byte missing between 1 byte chars
"\x41\xE0\xA0\x42",
// Incomplete 3 byte encoded character 2 bytes missing between 1 byte chars
"\x41\xE0\x42",
// Trailing byte with no lead byte between 1 byte chars
"\x41\x80\x42",
// Incomplete 2 byte encoded character 1 byte missing before 1 byte char
"\xC2\x42",
// Incomplete 3 byte encoded character 1 byte missing before 1 byte char
"\xE0\xA0\x42",
// Incomplete 3 byte encoded character 2 bytes missing before 1 byte char
"\xE0\x42",
// Trailing byte with no lead byte before 1 byte char
"\x80\x42",
// Incomplete 2 byte encoded character 1 byte missing after 1 byte char
"\x41\xC2",
// Incomplete 3 byte encoded character 1 byte missing after 1 byte char
"\x41\xE0\xA0",
// Incomplete 3 byte encoded character 2 bytes missing after 1 byte char
"\x41\xE0",
// Trailing byte with no lead byte after 1 byte char
"\x41\x80",
// Incomplete 2 byte encoded character 1 byte missing between 2 byte chars
"\xC2\x80\xC2\xC3\xBF",
// Incomplete 3 byte encoded character 1 byte missing between 2 byte chars
"\xC2\x80\xE0\xA0\xC3\xBF",
// Incomplete 3 byte encoded character 2 bytes missing between 2 byte chars
"\xC2\x80\xE0\xC3\xBF",
// Trailing byte with no lead byte between 2 byte chars
"\xC2\x80\x80\xC3\xBF",
// 2 byte encoded character in non-shortest form encodings (these are not allowed)
"\xC0\x80",
// 3 byte encoded character in non-shortest form encodings (these are not allowed)
"\xE0\x80\x80",
// 4 byte encoded character in non-shortest form encodings (these are not allowed)
"\xF0\x80\x80\x80",
};
const WCHAR * const unicodeStrings[] =
{
// Empty string
W(""),
// 1 byte encoded 1 character long string
W("A"),
// 2 byte encoded 1 character long string
W("\x0080"),
// 3 byte encoded 1 character long string
W("\x0800"),
// 1 byte encoded characters only
W("ABCDEFGHIJKLMNOPQRSTUVWXYZ"),
// 2 byte encoded characters only
W("\x0080\x00FF\x01C1\x07FF"),
// valid 3 byte encoded characters only
W("\x0800\x1D88\x1000\xFFFF"),
// 1 byte and 2 byte encoded characters interleaved 1:1 starting and ending with 1 byte char
W("\x0041\x0080\x0042\x00FF\x0043\x01C1\x0044\x07FF\x0045"),
// 1 byte and 2 byte encoded characters interleaved 1:1 starting with 1 byte char, ending with 2 byte one
W("\x0041\x0080\x0042\x00FF\x0043\x01C1\x0044\x07FF"),
// 1 byte and 2 byte encoded characters interleaved 1:1 starting with 2 byte char, ending with 1 byte one
W("\x0080\x0042\x00FF\x0043\x01C1\x0044\x07FF\x0045"),
// 1 byte and 2 byte encoded characters interleaved 1:1 starting and ending with 2 byte char
W("\x0080\x0042\x00FF\x0043\x01C1\x0044\x07FF"),
// 1 byte and 2 byte encoded characters interleaved 2:2 starting and ending with 1 byte char
W("\x0041\x0042\x0080\x00FF\x0043\x0044\x01C1\x07FF\x0045\x0046"),
// 1 byte and 2 byte encoded characters interleaved 2:2 starting with 1 byte char, ending with 2 byte one
W("\x0041\x0042\x0080\x00FF\x0043\x0044\x01C1\x07FF"),
// 1 byte and 2 byte encoded characters interleaved 2:2 starting with 2 byte char, ending with 1 byte one
W("\x0080\x00FF\x0043\x0044\x01C1\x07FF\x0045\x0046"),
// 1 byte and 2 byte encoded characters interleaved 2:2 starting and ending with 2 byte char
W("\x0080\x00FF\x0043\x0044\x01C1\x07FF"),
// surrogates
W("\xD800\xDC00\xD800\xDE40\xDAC0\xDFB0\xDBFF\xDFFF"),
// Strings with errors
// Incomplete 2 byte encoded character standalone
W(""),
// Incomplete 3 byte encoded character 1 byte missing standalone
W(""),
// Incomplete 3 byte encoded character 2 bytes missing standalone
W(""),
// Incomplete surrogate character 1 byte missing standalone
W(""),
// Incomplete surrogate character 2 bytes missing standalone
W(""),
// Incomplete surrogate character 3 bytes missing standalone
W(""),
// Trailing byte with no lead byte standalone
W(""),
// Incomplete 2 byte encoded character 1 byte missing between 1 byte chars
W("\x0041\x0042"),
// Incomplete 3 byte encoded character 1 byte missing between 1 byte chars
W("\x0041\x0042"),
// Incomplete 3 byte encoded character 2 bytes missing between 1 byte chars
W("\x0041\x0042"),
// Trailing byte with no lead byte between 1 byte chars
W("\x0041\x0042"),
// Incomplete 2 byte encoded character 1 byte missing before 1 byte char
W("\x0042"),
// Incomplete 3 byte encoded character 1 byte missing before 1 byte char
W("\x0042"),
// Incomplete 3 byte encoded character 2 bytes missing before 1 byte char
W("\x0042"),
// Trailing byte with no lead byte before 1 byte char
W("\x0042"),
// Incomplete 2 byte encoded character 1 byte missing after 1 byte char
W("\x0041"),
// Incomplete 3 byte encoded character 1 byte missing after 1 byte char
W("\x0041"),
// Incomplete 3 byte encoded character 2 bytes missing after 1 byte char
W("\x0041"),
// Trailing byte with no lead byte after 1 byte char
W("\x0041"),
// Incomplete 2 byte encoded character 1 byte missing between 2 byte chars
W("\x0080\x00FF"),
// Incomplete 3 byte encoded character 1 byte missing between 2 byte chars
W("\x0080\x00FF"),
// Incomplete 3 byte encoded character 2 bytes missing between 2 byte chars
W("\x0080\x00FF"),
// Trailing byte with no lead byte between 2 byte chars
W("\x0080\x00FF"),
// 2 byte encoded character in non-shortest form encodings (these are not allowed)
W(""),
// 3 byte encoded character in non-shortest form encodings (these are not allowed)
W(""),
// 4 byte encoded character in non-shortest form encodings (these are not allowed)
W(""),
};
for (int i = 0; i < (sizeof(utf8Strings) / sizeof(utf8Strings[0])); i++)
{
ret = MultiByteToWideChar(CP_UTF8, 0, utf8Strings[i], -1, NULL, 0);
WCHAR* wideBuffer = malloc(ret * sizeof(WCHAR));
ret2 = MultiByteToWideChar(CP_UTF8, 0, utf8Strings[i], -1, wideBuffer, ret);
if (ret != ret2)
{
Fail("MultiByteToWideChar string %d: returned different string length for empty and real dest buffers!\n"
"Got %d for the empty one, %d for real one.\n", i, ret2, ret);
}
if (wcscmp(wideBuffer, unicodeStrings[i]) != 0)
{
Fail("MultiByteToWideChar string %d: the resulting string doesn't match the expected one!\n", i);
}
free(wideBuffer);
}
PAL_Terminate();
return PASS;
}
|
