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
249
250
251
252
253
254
255
256
257
258
259
260
261
|
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=8 sts=2 et sw=2 tw=80: */
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
#include <stdio.h>
#include <stdlib.h>
#include "nsString.h"
#include "nsReadableUtils.h"
#include "UTFStrings.h"
#include "nsUnicharUtils.h"
#include "mozilla/HashFunctions.h"
#include "nsUTF8Utils.h"
#include "gtest/gtest.h"
using namespace mozilla;
namespace TestUTF {
TEST(UTF, Valid)
{
for (unsigned int i = 0; i < std::size(ValidStrings); ++i) {
nsDependentCString str8(ValidStrings[i].m8);
nsDependentString str16(ValidStrings[i].m16);
EXPECT_TRUE(NS_ConvertUTF16toUTF8(str16).Equals(str8));
EXPECT_TRUE(NS_ConvertUTF8toUTF16(str8).Equals(str16));
nsCString tmp8("string ");
AppendUTF16toUTF8(str16, tmp8);
EXPECT_TRUE(tmp8.Equals("string "_ns + str8));
nsString tmp16(u"string "_ns);
AppendUTF8toUTF16(str8, tmp16);
EXPECT_TRUE(tmp16.Equals(u"string "_ns + str16));
EXPECT_EQ(CompareUTF8toUTF16(str8, str16), 0);
}
}
TEST(UTF, Invalid16)
{
for (unsigned int i = 0; i < std::size(Invalid16Strings); ++i) {
nsDependentString str16(Invalid16Strings[i].m16);
nsDependentCString str8(Invalid16Strings[i].m8);
EXPECT_TRUE(NS_ConvertUTF16toUTF8(str16).Equals(str8));
nsCString tmp8("string ");
AppendUTF16toUTF8(str16, tmp8);
EXPECT_TRUE(tmp8.Equals("string "_ns + str8));
EXPECT_EQ(CompareUTF8toUTF16(str8, str16), 0);
}
}
TEST(UTF, Invalid8)
{
for (unsigned int i = 0; i < std::size(Invalid8Strings); ++i) {
nsDependentString str16(Invalid8Strings[i].m16);
nsDependentCString str8(Invalid8Strings[i].m8);
EXPECT_TRUE(NS_ConvertUTF8toUTF16(str8).Equals(str16));
nsString tmp16(u"string "_ns);
AppendUTF8toUTF16(str8, tmp16);
EXPECT_TRUE(tmp16.Equals(u"string "_ns + str16));
EXPECT_EQ(CompareUTF8toUTF16(str8, str16), 0);
}
}
TEST(UTF, Malformed8)
{
for (unsigned int i = 0; i < std::size(Malformed8Strings); ++i) {
nsDependentString str16(Malformed8Strings[i].m16);
nsDependentCString str8(Malformed8Strings[i].m8);
EXPECT_TRUE(NS_ConvertUTF8toUTF16(str8).Equals(str16));
nsString tmp16(u"string "_ns);
AppendUTF8toUTF16(str8, tmp16);
EXPECT_TRUE(tmp16.Equals(u"string "_ns + str16));
EXPECT_EQ(CompareUTF8toUTF16(str8, str16), 0);
}
}
TEST(UTF, Hash16)
{
for (unsigned int i = 0; i < std::size(ValidStrings); ++i) {
nsDependentCString str8(ValidStrings[i].m8);
bool err;
EXPECT_EQ(HashString(ValidStrings[i].m16),
HashUTF8AsUTF16(str8.get(), str8.Length(), &err));
EXPECT_FALSE(err);
}
for (unsigned int i = 0; i < std::size(Invalid8Strings); ++i) {
nsDependentCString str8(Invalid8Strings[i].m8);
bool err;
EXPECT_EQ(HashUTF8AsUTF16(str8.get(), str8.Length(), &err), 0u);
EXPECT_TRUE(err);
}
for (unsigned int i = 0; i < std::size(Malformed8Strings); ++i) {
nsDependentCString str8(Malformed8Strings[i].m8);
bool err;
EXPECT_EQ(HashUTF8AsUTF16(str8.get(), str8.Length(), &err), 0u);
EXPECT_TRUE(err);
}
}
/**
* This tests the handling of a non-ascii character at various locations in a
* UTF-16 string that is being converted to UTF-8.
*/
static void NonASCII16_helper(const size_t aStrSize) {
const size_t kTestSize = aStrSize;
const size_t kMaxASCII = 0x80;
const char16_t kUTF16Char = 0xC9;
const char kUTF8Surrogates[] = {char(0xC3), char(0x89)};
// Generate a string containing only ASCII characters.
nsString asciiString;
asciiString.SetLength(kTestSize);
nsCString asciiCString;
asciiCString.SetLength(kTestSize);
auto str_buff = asciiString.BeginWriting();
auto cstr_buff = asciiCString.BeginWriting();
for (size_t i = 0; i < kTestSize; i++) {
str_buff[i] = i % kMaxASCII;
cstr_buff[i] = i % kMaxASCII;
}
// Now go through and test conversion when exactly one character will
// result in a multibyte sequence.
for (size_t i = 0; i < kTestSize; i++) {
// Setup the UTF-16 string.
nsString unicodeString(asciiString);
auto buff = unicodeString.BeginWriting();
buff[i] = kUTF16Char;
// Do the conversion, make sure the length increased by 1.
nsCString dest;
AppendUTF16toUTF8(unicodeString, dest);
EXPECT_EQ(dest.Length(), unicodeString.Length() + 1);
// Build up the expected UTF-8 string.
nsCString expected;
// First add the leading ASCII chars.
expected.Append(asciiCString.BeginReading(), i);
// Now append the UTF-8 pair we expect the UTF-16 unicode char to
// be converted to.
for (auto& c : kUTF8Surrogates) {
expected.Append(c);
}
// And finish with the trailing ASCII chars.
expected.Append(asciiCString.BeginReading() + i + 1, kTestSize - i - 1);
EXPECT_STREQ(dest.BeginReading(), expected.BeginReading());
}
}
TEST(UTF, NonASCII16)
{
// Test with various string sizes to catch any special casing.
NonASCII16_helper(1);
NonASCII16_helper(8);
NonASCII16_helper(16);
NonASCII16_helper(32);
NonASCII16_helper(512);
}
TEST(UTF, UTF8CharEnumerator)
{
const char* p =
"\x61\xC0\xC2\xC2\x80\xE0\x80\x80\xE0\xA0\x80\xE1\x80\x80\xED\xBF\xBF\xED"
"\x9F\xBF\xEE\x80\x80\xEE\x80\xFF\xF0\x90\x80\x80\xF0\x80\x80\x80\xF1\x80"
"\x80\x80\xF4\x8F\xBF\xF4\x8F\xBF\xBF\xF4\xBF\xBF\xBF";
const char* end = p + 49;
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x0061U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x0080U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x0800U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x1000U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xD7FFU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xE000U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x10000U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x40000U);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0x10FFFFU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
p = "\xC2\xB6";
end = p + 1;
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
p = "\xE2\x98\x83";
end = p + 2;
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
p = "\xF0\x9F\x92\xA9";
end = p + 2;
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
p = "\xF0\x9F\x92\xA9";
end = p + 3;
EXPECT_EQ(UTF8CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
}
TEST(UTF, UTF16CharEnumerator)
{
const char16_t* p = u"\u0061\U0001F4A9";
const char16_t* end = p + 3;
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0x0061U);
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0x1F4A9U);
EXPECT_EQ(p, end);
const char16_t loneHigh = 0xD83D;
p = &loneHigh;
end = p + 1;
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
const char16_t loneLow = 0xDCA9;
p = &loneLow;
end = p + 1;
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(p, end);
const char16_t loneHighStr[] = {0xD83D, 0x0061};
p = loneHighStr;
end = p + 2;
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0xFFFDU);
EXPECT_EQ(UTF16CharEnumerator::NextChar(&p, end), 0x0061U);
EXPECT_EQ(p, end);
}
} // namespace TestUTF
|
