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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
|
#include "../lib/libfilezilla/encode.hpp"
#include "../lib/libfilezilla/string.hpp"
#include "test_utils.hpp"
using namespace std::literals;
/*
* This testsuite asserts the correctness of the
* string functions
*/
class string_test final : public CppUnit::TestFixture
{
CPPUNIT_TEST_SUITE(string_test);
CPPUNIT_TEST(test_conversion);
CPPUNIT_TEST(test_conversion2);
CPPUNIT_TEST(test_conversion_utf8);
CPPUNIT_TEST(test_conversion_null);
CPPUNIT_TEST(test_base64);
CPPUNIT_TEST(test_trim);
CPPUNIT_TEST(test_strtok);
CPPUNIT_TEST(test_startsendswith);
CPPUNIT_TEST(test_normalize_hyphens);
CPPUNIT_TEST(test_is_valid_utf8);
CPPUNIT_TEST(test_utf16_to_utf8_append);
CPPUNIT_TEST(test_to_integral);
CPPUNIT_TEST_SUITE_END();
public:
void setUp() {}
void tearDown() {}
void test_conversion();
void test_conversion2();
void test_conversion_utf8();
void test_conversion_null();
void test_base64();
void test_trim();
void test_strtok();
void test_startsendswith();
void test_normalize_hyphens();
void test_is_valid_utf8();
void test_utf16_to_utf8_append();
void test_to_integral();
};
CPPUNIT_TEST_SUITE_REGISTRATION(string_test);
void string_test::test_conversion()
{
std::string const s("hello world!");
std::wstring const w = fz::to_wstring(s);
CPPUNIT_ASSERT_EQUAL(s.size(), w.size());
for (size_t i = 0; i < s.size(); ++i) {
CPPUNIT_ASSERT_EQUAL(static_cast<wchar_t>(s[i]), w[i]);
}
std::string const s2 = fz::to_string(s);
CPPUNIT_ASSERT_EQUAL(s, s2);
}
void string_test::test_conversion2()
{
wchar_t const p[] = { 'M', 'o', 't', 0xf6, 'r', 'h', 'e', 'a', 'd', 0 };
std::wstring const w(p);
std::string const s = fz::to_string(w);
CPPUNIT_ASSERT(s.size() >= w.size());
std::wstring const w2 = fz::to_wstring(s);
ASSERT_EQUAL(w, w2);
}
void string_test::test_conversion_utf8()
{
wchar_t const p[] = { 'M', 'o', 't', 0xf6, 'r', 'h', 'e', 'a', 'd', 0 };
unsigned char const p_utf8[] = { 'M', 'o', 't', 0xc3, 0xb6, 'r', 'h', 'e', 'a', 'd', 0 };
std::wstring const w(p);
std::string const u(reinterpret_cast<char const*>(p_utf8));
std::string const s = fz::to_utf8(w);
CPPUNIT_ASSERT(s.size() >= w.size());
ASSERT_EQUAL(s, u);
std::wstring const w2 = fz::to_wstring_from_utf8(s);
ASSERT_EQUAL(w, w2);
}
void string_test::test_conversion_null()
{
wchar_t const w[7] = {'A', 0, 'B', 0, 0, 'C', 0};
unsigned char const n[7] = {'A', 0, 'B', 0, 0, 'C', 0};
{
std::wstring const in(w, w + 7);
std::string const ref(n, n + 7);
std::string const out = fz::to_string(in);
CPPUNIT_ASSERT(out.size() >= in.size());
ASSERT_EQUAL(ref, out);
std::wstring const out2 = fz::to_wstring(out);
CPPUNIT_ASSERT(out2.size() <= out.size());
ASSERT_EQUAL(in, out2);
}
{
std::wstring const in(w, w + 7);
std::string const ref(n, n + 7);
std::string const out = fz::to_utf8(in);
CPPUNIT_ASSERT(out.size() >= in.size());
ASSERT_EQUAL(ref, out);
std::wstring const out2 = fz::to_wstring_from_utf8(out);
CPPUNIT_ASSERT(out2.size() <= out.size());
ASSERT_EQUAL(in, out2);
}
}
void string_test::test_base64()
{
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::base64_encode(""));
CPPUNIT_ASSERT_EQUAL(std::string("Zg=="), fz::base64_encode("f"));
CPPUNIT_ASSERT_EQUAL(std::string("Zm8="), fz::base64_encode("fo"));
CPPUNIT_ASSERT_EQUAL(std::string("Zm9v"), fz::base64_encode("foo"));
CPPUNIT_ASSERT_EQUAL(std::string("Zm9vbA=="), fz::base64_encode("fool"));
CPPUNIT_ASSERT_EQUAL(std::string("Zm9vbHM="), fz::base64_encode("fools"));
CPPUNIT_ASSERT_EQUAL(std::string("Zg"), fz::base64_encode("f", fz::base64_type::standard, false));
CPPUNIT_ASSERT_EQUAL(std::string("Zm8"), fz::base64_encode("fo", fz::base64_type::standard, false));
CPPUNIT_ASSERT_EQUAL(std::string("Zm9vbA"), fz::base64_encode("fool", fz::base64_type::standard, false));
CPPUNIT_ASSERT_EQUAL(std::string("Zm9vbHM"), fz::base64_encode("fools", fz::base64_type::standard, false));
CPPUNIT_ASSERT_EQUAL(std::string("AAECA/3+/w=="), fz::base64_encode(std::string({0, 1, 2, 3, '\xfd', '\xfe', '\xff'})));
CPPUNIT_ASSERT_EQUAL(std::string("AAECA_3-_w=="), fz::base64_encode(std::string({0, 1, 2, 3, '\xfd', '\xfe', '\xff'}), fz::base64_type::url));
// decode
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::base64_decode_s(""));
CPPUNIT_ASSERT_EQUAL(std::string("f"), fz::base64_decode_s("Zg=="));
CPPUNIT_ASSERT_EQUAL(std::string("fo"), fz::base64_decode_s("Zm8="));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::base64_decode_s("Zm9v"));
CPPUNIT_ASSERT_EQUAL(std::string("fool"), fz::base64_decode_s("Zm9vbA=="));
CPPUNIT_ASSERT_EQUAL(std::string("fools"), fz::base64_decode_s("Zm9vbHM="));
CPPUNIT_ASSERT_EQUAL(std::string("f"), fz::base64_decode_s("Zg"));
CPPUNIT_ASSERT_EQUAL(std::string("fo"), fz::base64_decode_s("Zm8"));
CPPUNIT_ASSERT_EQUAL(std::string("fool"), fz::base64_decode_s("Zm9vbA"));
CPPUNIT_ASSERT_EQUAL(std::string("fools"), fz::base64_decode_s("Zm9vbHM"));
CPPUNIT_ASSERT_EQUAL(std::string({0, 1, 2, 3, '\xfd', '\xfe', '\xff'}), fz::base64_decode_s("AAECA/3+/w=="));
CPPUNIT_ASSERT_EQUAL(std::string({0, 1, 2, 3, '\xfd', '\xfe', '\xff'}), fz::base64_decode_s("AAECA_3-_w"));
// with whitespace
CPPUNIT_ASSERT_EQUAL(std::string("Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua."),
fz::base64_decode_s(" TG9yZW0gaXBzdW0gZG9sb3Igc2l0I\nGFtZXQsIGNvbnNlY3Rld\rHVyIGFkaXBpc2NpbmcgZWxpd \tCwgc2VkIGRvIGVpdXNtb2QgdGVtcG9yIGluY2lkaWR1bnQgdXQgbGFib3JlIGV0IGRvbG9yZSBtYWduYSBhbGlxdWEu "));
// invalid
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::base64_decode_s("Zm9vbHM=="));
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::base64_decode_s("Zm9vb==="));
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::base64_decode_s("Zm9vbHM=Zg=="));
}
void string_test::test_trim()
{
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("foo")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string(" foo")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("\t foo")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("foo ")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("foo \n")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string(" foo\n")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("\t foo\r")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string(" foo ")));
CPPUNIT_ASSERT_EQUAL(std::string("foo"), fz::trimmed(std::string("\t foo ")));
CPPUNIT_ASSERT_EQUAL(std::string(""), fz::trimmed(std::string(" \t\r \n \t")));
}
void string_test::test_strtok()
{
auto tokens = fz::strtok("hello world", ' ');
CPPUNIT_ASSERT_EQUAL(size_t(2), tokens.size());
CPPUNIT_ASSERT_EQUAL(std::string("hello"), tokens[0]);
CPPUNIT_ASSERT_EQUAL(std::string("world"), tokens[1]);
tokens = fz::strtok(" hello world ", " eo");
CPPUNIT_ASSERT_EQUAL(size_t(4), tokens.size());
CPPUNIT_ASSERT_EQUAL(std::string("h"), tokens[0]);
CPPUNIT_ASSERT_EQUAL(std::string("ll"), tokens[1]);
CPPUNIT_ASSERT_EQUAL(std::string("w"), tokens[2]);
CPPUNIT_ASSERT_EQUAL(std::string("rld"), tokens[3]);
tokens = fz::strtok("a b c", ' ');
CPPUNIT_ASSERT_EQUAL(size_t(3), tokens.size());
CPPUNIT_ASSERT_EQUAL(std::string("a"), tokens[0]);
CPPUNIT_ASSERT_EQUAL(std::string("b"), tokens[1]);
CPPUNIT_ASSERT_EQUAL(std::string("c"), tokens[2]);
tokens = fz::strtok("a b c d ", ' ', false);
CPPUNIT_ASSERT_EQUAL(size_t(8), tokens.size());
CPPUNIT_ASSERT_EQUAL(std::string("a"), tokens[0]);
CPPUNIT_ASSERT_EQUAL(std::string("b"), tokens[1]);
CPPUNIT_ASSERT_EQUAL(std::string(""), tokens[2]);
CPPUNIT_ASSERT_EQUAL(std::string("c"), tokens[3]);
CPPUNIT_ASSERT_EQUAL(std::string(""), tokens[4]);
CPPUNIT_ASSERT_EQUAL(std::string("d"), tokens[5]);
CPPUNIT_ASSERT_EQUAL(std::string(""), tokens[6]);
CPPUNIT_ASSERT_EQUAL(std::string(""), tokens[7]);
}
void string_test::test_startsendswith()
{
CPPUNIT_ASSERT_EQUAL(false, fz::starts_with(std::string("hello"), std::string("world")));
CPPUNIT_ASSERT_EQUAL(true, fz::starts_with(std::string("hello"), std::string("hell")));
CPPUNIT_ASSERT_EQUAL(false, fz::starts_with(std::string("hell"), std::string("hello")));
CPPUNIT_ASSERT_EQUAL(false, fz::starts_with(std::string("hello"), std::string("HELL")));
CPPUNIT_ASSERT_EQUAL(false, fz::starts_with<true>(std::string("hello"), std::string("world")));
CPPUNIT_ASSERT_EQUAL(true, fz::starts_with<true>(std::string("hello"), std::string("hell")));
CPPUNIT_ASSERT_EQUAL(false, fz::starts_with<true>(std::string("hell"), std::string("hello")));
CPPUNIT_ASSERT_EQUAL(true, fz::starts_with<true>(std::string("hello"), std::string("HELL")));
CPPUNIT_ASSERT_EQUAL(false, fz::ends_with(std::string("hello"), std::string("world")));
CPPUNIT_ASSERT_EQUAL(true, fz::ends_with(std::string("hello"), std::string("ello")));
CPPUNIT_ASSERT_EQUAL(false, fz::ends_with(std::string("ello"), std::string("HELLO")));
CPPUNIT_ASSERT_EQUAL(false, fz::ends_with(std::string("hello"), std::string("ELLO")));
CPPUNIT_ASSERT_EQUAL(false, fz::ends_with<true>(std::string("hello"), std::string("world")));
CPPUNIT_ASSERT_EQUAL(true, fz::ends_with<true>(std::string("hello"), std::string("ello")));
CPPUNIT_ASSERT_EQUAL(false, fz::ends_with<true>(std::string("ello"), std::string("HELLO")));
CPPUNIT_ASSERT_EQUAL(true, fz::ends_with<true>(std::string("hello"), std::string("ELLO")));
}
void string_test::test_normalize_hyphens()
{
CPPUNIT_ASSERT_EQUAL(std::string("--------"), fz::normalize_hyphens(fz::percent_decode_s("-" "%e2%80%90" "%e2%80%91" "%e2%80%92" "%e2%80%93" "%e2%80%94" "%e2%80%95" "%e2%88%92")));
ASSERT_EQUAL(std::wstring(L"--------"), fz::normalize_hyphens(fz::to_wstring_from_utf8(fz::percent_decode_s("-" "%e2%80%90" "%e2%80%91" "%e2%80%92" "%e2%80%93" "%e2%80%94" "%e2%80%95" "%e2%88%92"))));
}
void string_test::test_is_valid_utf8()
{
auto const utf8 = "Das bl\xc3\xb6" "de SCHEI\xe1\xba\x9e" "EMOJI \xf0\x9f\x92\xa9, ein Haufen Mist."sv;
size_t state{};
CPPUNIT_ASSERT(fz::is_valid_utf8(utf8, state));
CPPUNIT_ASSERT_EQUAL(size_t(0), state);
for (size_t i = 0; i < utf8.size(); ++i) {
CPPUNIT_ASSERT(fz::is_valid_utf8(utf8.substr(i, 1), state));
}
CPPUNIT_ASSERT_EQUAL(size_t(0), state);
auto const valid1 = "\xed\x9f\xbf"sv; // Technically undefined, but valid. Just before surrogates
auto const valid2 = "\xee\x80\x80"sv; // Private use area. Just after surrogates
CPPUNIT_ASSERT(fz::is_valid_utf8(valid1));
CPPUNIT_ASSERT(fz::is_valid_utf8(valid2));
auto const invalid1 = "\xc3\xc3"sv; // Two starting bytes
auto const invalid2 = "\xed\xa0\x80"sv; // Surrogate
auto const invalid3 = "\xed\xbf\xbf"sv; // Surrogate
CPPUNIT_ASSERT(!fz::is_valid_utf8(invalid1));
CPPUNIT_ASSERT(!fz::is_valid_utf8(invalid2));
CPPUNIT_ASSERT(!fz::is_valid_utf8(invalid3));
}
namespace {
void do_test_utf16_to_utf8_append(std::string_view be, std::string_view expected)
{
CPPUNIT_ASSERT(!(be.size() % 2));
std::string le;
le.resize(be.size());
for (size_t i = 0; i < be.size(); i += 2) {
le[i] = be[i+1];
le[i+1] = be[i];
}
std::string out;
uint32_t state{};
CPPUNIT_ASSERT(fz::utf16be_to_utf8_append(out, be, state));
CPPUNIT_ASSERT_EQUAL(uint32_t(0), state);
CPPUNIT_ASSERT(expected == out);
out.clear();
CPPUNIT_ASSERT(fz::utf16le_to_utf8_append(out, le, state));
CPPUNIT_ASSERT_EQUAL(uint32_t(0), state);
CPPUNIT_ASSERT(expected == out);
out.clear();
for (size_t i = 0; i < be.size(); ++i) {
CPPUNIT_ASSERT(fz::utf16be_to_utf8_append(out, be.substr(i, 1), state));
}
CPPUNIT_ASSERT_EQUAL(uint32_t(0), state);
CPPUNIT_ASSERT(expected == out);
out.clear();
for (size_t i = 0; i < le.size(); ++i) {
CPPUNIT_ASSERT(fz::utf16le_to_utf8_append(out, le.substr(i, 1), state));
}
CPPUNIT_ASSERT_EQUAL(uint32_t(0), state);
CPPUNIT_ASSERT(expected == out);
out.clear();
}
}
void string_test::test_utf16_to_utf8_append()
{
// Big-endian
auto const poop = "\xd8\x3d\xdc\xa9"sv;
auto const cheese = "\0K\0\xe4\0s\0e"sv;
auto const poop_utf8 = "\xf0\x9f\x92\xa9"sv;
auto const cheese_utf8 = "K\xc3\xa4se"sv;
do_test_utf16_to_utf8_append(poop, poop_utf8);
do_test_utf16_to_utf8_append(cheese, cheese_utf8);
{
std::string out;
uint32_t state{};
CPPUNIT_ASSERT(fz::utf16be_to_utf8_append(out, poop.substr(0, 2), state));
CPPUNIT_ASSERT(state != 0);
CPPUNIT_ASSERT(!fz::utf16be_to_utf8_append(out, cheese.substr(0, 2), state));
state = 0;
CPPUNIT_ASSERT(!fz::utf16be_to_utf8_append(out, poop.substr(2), state));
}
}
void string_test::test_to_integral()
{
short v = std::numeric_limits<short>::min();
for (size_t i = 0; i < 65536; ++i, ++v) {
// signed
auto s = fz::to_string(v);
auto v2 = fz::to_integral_o<short>(s);
CPPUNIT_ASSERT(v2);
CPPUNIT_ASSERT(v == v2);
// unsigned
s = fz::to_string(i);
auto v3 = fz::to_integral_o<unsigned short>(s);
CPPUNIT_ASSERT(v3);
CPPUNIT_ASSERT(i == v3);
}
CPPUNIT_ASSERT(!fz::to_integral_o<short>("32768"sv));
CPPUNIT_ASSERT(!fz::to_integral_o<short>("-32769"sv));
CPPUNIT_ASSERT(!fz::to_integral_o<unsigned short>("-1"sv));
CPPUNIT_ASSERT(!fz::to_integral_o<unsigned short>("65536"sv));
}
|
