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
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
|
//
// Copyright (c) 2022-2024 Alexander Grund
//
// Distributed under the Boost Software License, Version 1.0.
// https://www.boost.org/LICENSE_1_0.txt
#include <boost/locale/hold_ptr.hpp>
#include <boost/locale/util.hpp>
#include <boost/locale/util/locale_data.hpp>
#include "boostLocale/test/test_helpers.hpp"
#include "boostLocale/test/tools.hpp"
#include "boostLocale/test/unit_test.hpp"
#include <cstdlib>
#include <stdexcept>
namespace {
struct Dummy {
int i_;
Dummy(int i) : i_(i) { ++ctr; }
~Dummy() { --ctr; }
Dummy(const Dummy&) = delete;
Dummy(Dummy&&) = delete;
int foo() { return i_; }
int foo() const { return -i_; }
static int ctr;
};
int Dummy::ctr = 0;
} // namespace
void test_hold_ptr()
{
{
boost::locale::hold_ptr<Dummy> empty;
TEST(!empty);
auto* raw = new Dummy(42);
boost::locale::hold_ptr<Dummy> ptr(raw);
const boost::locale::hold_ptr<Dummy>& const_ptr = ptr;
if TEST(ptr) {
TEST(ptr.get() == raw);
TEST(const_ptr.get() == raw);
// const propagation
TEST_EQ((*ptr).foo(), raw->i_);
TEST_EQ((*const_ptr).foo(), -raw->i_);
TEST_EQ(ptr->foo(), raw->i_);
TEST_EQ(const_ptr->foo(), -raw->i_);
TEST_EQ(ptr.get()->foo(), raw->i_);
TEST_EQ(const_ptr.get()->foo(), -raw->i_);
// move construct
boost::locale::hold_ptr<Dummy> ptr2 = std::move(ptr);
TEST(!ptr);
if TEST(ptr2) {
TEST(ptr2.get() == raw);
// move assign
ptr = std::move(ptr2);
TEST(ptr);
TEST(!ptr2);
TEST(ptr.get() == raw);
// Swap
boost::locale::hold_ptr<Dummy> ptr3(new Dummy(1337));
ptr.swap(ptr3);
TEST_EQ(ptr->foo(), 1337);
TEST_EQ(ptr3->foo(), 42);
}
}
}
TEST_EQ(Dummy::ctr, 0);
auto* raw = new Dummy(42);
{
boost::locale::hold_ptr<Dummy> ptr(new Dummy(1));
TEST_EQ(Dummy::ctr, 2);
ptr.reset(raw);
TEST_EQ(Dummy::ctr, 1);
TEST_EQ(ptr->foo(), 42);
TEST(ptr.release() == raw);
TEST_EQ(Dummy::ctr, 1);
}
TEST_EQ(Dummy::ctr, 1);
delete raw;
}
void test_get_system_locale()
{
// Clear all -> Default to C
{
using boost::locale::test::unsetenv;
unsetenv("LC_CTYPE");
unsetenv("LC_ALL");
unsetenv("LANG");
}
using boost::locale::util::get_system_locale;
#if !BOOST_LOCALE_USE_WIN32_API
TEST_EQ(get_system_locale(false), "C");
#else
// On Windows the user default name is used, so we can only test the encoding
TEST(get_system_locale(true).find(".UTF-8") != std::string::npos);
{
const std::string loc = get_system_locale(false);
const std::string enc = loc.substr(loc.find_last_of('.'));
// encoding should be a windows codepage, but in the error case can be UTF-8
if(enc.find(".windows-") != 0u)
TEST_EQ(enc, ".UTF-8"); // LCOV_EXCL_LINE
}
#endif
// LC_ALL, LC_CTYPE and LANG variables used in this order
using boost::locale::test::setenv;
setenv("LANG", "mylang.foo");
TEST_EQ(get_system_locale(true), "mylang.foo");
setenv("LC_CTYPE", "this.lang");
TEST_EQ(get_system_locale(true), "this.lang");
setenv("LC_ALL", "barlang.bar");
TEST_EQ(get_system_locale(true), "barlang.bar");
}
#ifndef BOOST_LOCALE_WITH_ICU
void verify_against_icu(){};
#else
# include <unicode/locid.h>
void verify_against_icu()
{
int32_t count;
auto* cur_locale = icu::Locale::getAvailableLocales(count);
boost::locale::util::locale_data data;
for(int i = 0; i < count; i++, cur_locale++) {
const std::string loc_name = cur_locale->getName();
if(loc_name == "en_US_POSIX")
continue; // Parsed as "C", tested elsewhere
for(const bool add_utf8 : {false, true}) {
// Also test with added encoding to verify input is fully parsed
const std::string curName = add_utf8 ? loc_name + ".UTF-8" : loc_name;
TEST_CONTEXT(curName);
TEST(data.parse(curName));
TEST_EQ(data.language(), cur_locale->getLanguage());
TEST_EQ(data.country(), cur_locale->getCountry());
TEST_EQ(data.encoding(), add_utf8 ? "UTF-8" : "US-ASCII");
TEST_EQ(data.variant(), cur_locale->getVariant());
TEST_EQ(data.to_string(), curName);
}
}
}
#endif
void test_locale_data()
{
boost::locale::util::locale_data data;
// Default is C.US-ASCII
TEST_EQ(data.language(), "C");
TEST_EQ(data.country(), "");
TEST_EQ(data.encoding(), "US-ASCII");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("en_US.UTF-8"));
TEST_EQ(data.language(), "en");
TEST_EQ(data.country(), "US");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("C"));
TEST_EQ(data.language(), "C");
TEST_EQ(data.script(), "");
TEST_EQ(data.country(), "");
TEST_EQ(data.encoding(), "US-ASCII");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("ku_TR.UTF-8@sorani"));
TEST_EQ(data.language(), "ku");
TEST_EQ(data.script(), "");
TEST_EQ(data.country(), "TR");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "sorani");
TEST(data.parse("POSIX"));
TEST_EQ(data.language(), "C");
TEST_EQ(data.country(), "");
TEST_EQ(data.encoding(), "US-ASCII");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("da_DK.ISO8859-15@euro"));
TEST_EQ(data.language(), "da");
TEST_EQ(data.country(), "DK");
TEST_EQ(data.encoding(), "ISO8859-15");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "euro");
TEST(data.parse("de_DE.ISO8859-1"));
TEST_EQ(data.language(), "de");
TEST_EQ(data.country(), "DE");
TEST_EQ(data.encoding(), "ISO8859-1");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("ja_JP.eucJP"));
TEST_EQ(data.language(), "ja");
TEST_EQ(data.country(), "JP");
TEST_EQ(data.encoding(), "EUCJP");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("ko_KR.EUC@dict"));
TEST_EQ(data.language(), "ko");
TEST_EQ(data.country(), "KR");
TEST_EQ(data.encoding(), "EUC");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "dict");
TEST(data.parse("th_TH.TIS620"));
TEST_EQ(data.language(), "th");
TEST_EQ(data.country(), "TH");
TEST_EQ(data.encoding(), "TIS620");
TEST(!data.is_utf8());
TEST_EQ(data.variant(), "");
TEST(data.parse("zh_TW.UTF-8@radical"));
TEST_EQ(data.language(), "zh");
TEST_EQ(data.country(), "TW");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "radical");
// Country can be a 3-digit value
TEST(data.parse("en_001.UTF-8"));
TEST_EQ(data.language(), "en");
TEST_EQ(data.country(), "001");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "");
// Script used, optionally with dashes instead of underscores
for(const std::string name : {"pa_Arab_PK.UTF-8", "pa-Arab_PK.UTF-8", "pa_Arab-PK.UTF-8"}) {
TEST(data.parse("pa_Arab_PK.UTF-8"));
TEST_EQ(data.language(), "pa");
TEST_EQ(data.script(), "Arab");
TEST_EQ(data.country(), "PK");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "");
}
// to_string yields the input (if format is correct already)
for(const std::string name : {"C",
"en_US.UTF-8",
"ku_TR.UTF-8@sorani",
"da_DK.ISO8859-15@euro",
"de_DE.ISO8859-1",
"en_US",
"ko_KR.EUC@dict",
"th_TH.TIS620",
"zh_TW.UTF-8@radical",
"en_001",
"en_150.UTF-8",
// Different variation with parts missing
"pa_Arab_PK.UTF-8",
"pa_Arab_PK@euro",
"pa_Arab.UTF-8",
"pa_Arab@euro",
"pa.UTF-8",
"pa@euro",
"pa_PK.UTF-8",
"pa_PK@euro"})
{
TEST_CONTEXT(name);
TEST(data.parse(name));
TEST_EQ(data.to_string(), name);
}
// US-ASCII encoding is ignored
TEST(data.parse("da_TR.US-ASCII"));
TEST_EQ(data.to_string(), "da_TR");
TEST(data.parse("da_TR.US-ASCII@dic"));
TEST_EQ(data.to_string(), "da_TR@dic");
// Unify casing:
// - language: lowercase
// - script: Capitalized
// - region: uppercase
// - encoding: uppercase
// - variant: lowercase
TEST(data.parse("EN_sCrI_us.utf-8@EUro"));
TEST_EQ(data.language(), "en");
TEST_EQ(data.script(), "Scri");
TEST_EQ(data.country(), "US");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST_EQ(data.variant(), "euro");
TEST_EQ(data.to_string(), "en_Scri_US.UTF-8@euro");
TEST(data.parse("lAnGUagE_cOunTRy.eNCo-d123inG@Va-r1_Ant"));
TEST_EQ(data.to_string(), "language_COUNTRY.ENCO-D123ING@va-r1_ant");
// Dash is allowed in addition to underscore
TEST(data.parse("de-DE.UTF-8"));
TEST_EQ(data.to_string(), "de_DE.UTF-8");
// C/POSIX is allowed to have an encoding
TEST(data.parse("C.UTF-8"));
TEST_EQ(data.to_string(), "C.UTF-8");
TEST(data.parse("POSIX.UTF-8"));
TEST_EQ(data.to_string(), "C.UTF-8");
// Special case: en_US_POSIX is an alias for "C"
TEST(data.parse("en_US_POSIX"));
TEST_EQ(data.to_string(), "C");
TEST(data.parse("En_Us_POsix.UTF-8"));
TEST_EQ(data.to_string(), "C.UTF-8");
// Missing values are defaulted
TEST(data.parse("en"));
TEST_EQ(data.to_string(), "en");
TEST_EQ(data.encoding(), "US-ASCII");
TEST(!data.is_utf8());
TEST(data.parse("en.UTF-8"));
TEST_EQ(data.to_string(), "en.UTF-8");
TEST_EQ(data.encoding(), "UTF-8");
TEST(data.is_utf8());
TEST(data.parse("en@dict"));
TEST_EQ(data.to_string(), "en@dict");
TEST_EQ(data.encoding(), "US-ASCII");
TEST_EQ(data.variant(), "dict");
TEST(data.parse("en_US@dict"));
TEST_EQ(data.to_string(), "en_US@dict");
TEST_EQ(data.encoding(), "US-ASCII");
TEST_EQ(data.variant(), "dict");
// Error cases, default values used starting from error
// Invalid language (separator at start or not an ASCII letter)
for(const std::string invalidName :
{"_en_US.UTF-8", "-en_US.UTF-8", ".en_US.UTF-8", "@en_US.UTF-8", "e1_US.UTF-8", "eö_US.UTF-8"})
{
TEST(!data.parse(invalidName));
TEST_EQ(data.to_string(), "C");
}
// Invalid country
TEST(!data.parse("en_UÖ.UTF-8"));
TEST_EQ(data.to_string(), "en");
TEST(!data.parse("en_1234.UTF-8")); // To many digits
TEST_EQ(data.to_string(), "en");
TEST(!data.parse("en_US1.UTF-8")); // digits in text
TEST_EQ(data.to_string(), "en");
TEST(!data.parse("en_1US.UTF-8")); // digits in text
TEST_EQ(data.to_string(), "en");
// Empty parts:
// Language
TEST(!data.parse("_US.UTF-8@variant"));
TEST_EQ(data.to_string(), "C");
// Country
TEST(!data.parse("en_.UTF-8@variant"));
TEST_EQ(data.to_string(), "en");
// Encoding
TEST(!data.parse("en_US.@variant"));
TEST_EQ(data.to_string(), "en_US");
// Variant
TEST(!data.parse("en_US.UTF-8@"));
TEST_EQ(data.to_string(), "en_US.UTF-8");
// C/POSIX with any other field except the encoding
for(const std::string invalidName : {"C_US", "C@variant", "POSIX_US", "POSIX@variant"}) {
TEST(!data.parse(invalidName));
TEST_EQ(data.to_string(), "C");
}
// Construct from string
TEST_EQ(boost::locale::util::locale_data("en_US.UTF-8").to_string(), "en_US.UTF-8");
TEST_THROWS(boost::locale::util::locale_data invalid("en_UÖ.UTF-8"), std::invalid_argument);
verify_against_icu();
}
void test_main(int /*argc*/, char** /*argv*/)
{
test_hold_ptr();
test_get_system_locale();
test_locale_data();
}
|
