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
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
|
// Copyright (C) 2018 ycmd contributors
//
// This file is part of ycmd.
//
// ycmd is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// ycmd is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with ycmd. If not, see <http://www.gnu.org/licenses/>.
#include "Character.h"
#include "Repository.h"
#include "CodePoint.h"
#include "TestUtils.h"
#include <array>
#include <gtest/gtest.h>
#include <gmock/gmock.h>
using ::testing::TestWithParam;
using ::testing::ValuesIn;
namespace YouCompleteMe {
// Check that characters equalities and inequalities are symmetric (a == b if
// and only if b == a).
MATCHER( CharactersAreEqual, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( !( *arg[ i ] == *arg[ j ] ) || !( *arg[ j ] == *arg[ i ] ) ) {
return false;
}
}
}
return true;
}
MATCHER( CharactersAreNotEqual, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( *arg[ i ] == *arg[ j ] || *arg[ j ] == *arg[ i ] ) {
return false;
}
}
}
return true;
}
MATCHER( CharactersAreEqualWhenCaseIsIgnored, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( !( arg[ i ]->EqualsIgnoreCase( *arg[ j ] ) ) ||
!( arg[ j ]->EqualsIgnoreCase( *arg[ i ] ) ) ) {
return false;
}
}
}
return true;
}
MATCHER( CharactersAreNotEqualWhenCaseIsIgnored, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( arg[ i ]->EqualsIgnoreCase( *arg[ j ] ) ||
arg[ j ]->EqualsIgnoreCase( *arg[ i ] ) ) {
return false;
}
}
}
return true;
}
MATCHER( BaseCharactersAreEqual, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( !( arg[ i ]->EqualsBase( *arg[ j ] ) ) ||
!( arg[ j ]->EqualsBase( *arg[ i ] ) ) ) {
return false;
}
}
}
return true;
}
MATCHER( BaseCharactersAreNotEqual, "" ) {
for ( size_t i = 0; i < arg.size() - 1; ++i ) {
for ( size_t j = i + 1; j < arg.size(); ++j ) {
if ( arg[ i ]->EqualsBase( *arg[ j ] ) ||
arg[ j ]->EqualsBase( *arg[ i ] ) ) {
return false;
}
}
}
return true;
}
struct TextCharacterPair {
const char* text;
CharacterTuple character_tuple;
};
std::ostream& operator<<( std::ostream& os,
const TextCharacterPair &pair ) {
os << "{ " << PrintToString( pair.text ) << ", "
<< PrintToString( pair.character_tuple ) << " }";
return os;
}
class CharacterTest : public TestWithParam< TextCharacterPair > {
protected:
CharacterTest()
: repo_( Repository< Character >::Instance() ) {
}
virtual void SetUp() {
repo_.ClearElements();
pair_ = GetParam();
}
Repository< Character > &repo_;
const char* text_;
TextCharacterPair pair_;
};
TEST( CharacterTest, ExceptionThrownWhenLeadingByteInCodePointIsInvalid ) {
try {
// Leading byte cannot start with bits '10'.
Character( NormalizeInput( "\xaf" ) );
FAIL() << "Expected UnicodeDecodeError exception.";
} catch ( const UnicodeDecodeError &error ) {
EXPECT_STREQ( error.what(), "Invalid leading byte in code point." );
} catch ( ... ) {
FAIL() << "Expected UnicodeDecodeError exception.";
}
}
TEST( CharacterTest, ExceptionThrownWhenCodePointIsOutOfBound ) {
try {
// Leading byte indicates a sequence of three bytes but only two are given.
Character( NormalizeInput( "\xe4\xbf" ) );
FAIL() << "Expected UnicodeDecodeError exception.";
} catch ( const UnicodeDecodeError &error ) {
EXPECT_STREQ( error.what(), "Invalid code point length." );
} catch ( ... ) {
FAIL() << "Expected UnicodeDecodeError exception.";
}
}
TEST_P( CharacterTest, PropertiesAreCorrect ) {
EXPECT_THAT( Character( NormalizeInput( pair_.text ) ),
IsCharacterWithProperties( pair_.character_tuple ) );
}
const std::array< TextCharacterPair, 13 > tests = { {
// Musical symbol eighth note (three code points)
{ "𝅘𝅥𝅮", { "𝅘𝅥𝅮", "𝅘", "𝅘𝅥𝅮", "𝅘𝅥𝅮", false, false, false, false } },
// Punctuations
// Fullwidth low line
{ "＿", { "＿", "＿", "＿", "＿", true, false, true, false } },
// Wavy dash
{ "〰", { "〰", "〰", "〰", "〰", true, false, true, false } },
// Left floor
{ "⌊", { "⌊", "⌊", "⌊", "⌊", true, false, true, false } },
// Fullwidth right square bracket
{ "］", { "］", "］", "］", "］", true, false, true, false } },
{ "«", { "«", "«", "«", "«", true, false, true, false } },
// Right substitution bracket
{ "⸃", { "⸃", "⸃", "⸃", "⸃", true, false, true, false } },
// Large one dot over two dots punctuation
{ "𐬽", { "𐬽", "𐬽", "𐬽", "𐬽", true, false, true, false } },
// Letters
// Latin capital letter S with dot below and dot above (three code points)
{ "Ṩ", { "Ṩ", "s", "ṩ", "ṩ", false, true, false, true } },
// Greek small letter alpha with psili and varia and ypogegrammeni (four code
// points)
{ "ᾂ", { "ᾂ", "α", "ἂι", "ἊΙ", false, true, false, false } },
// Greek capital letter eta with dasia and perispomeni and prosgegrammeni
// (four code points)
{ "ᾟ", { "ᾟ", "η", "ἧι", "ἧΙ", false, true, false, true } },
// Hiragana voiced iteration mark (two code points)
{ "ゞ", { "ゞ", "ゝ", "ゞ", "ゞ", false, true, false, false } },
// Hebrew letter shin with Dagesh and Shin dot (three code points)
{ "שּׁ", { "שּׁ", "ש", "שּׁ", "שּׁ", false, true, false, false } }
} };
INSTANTIATE_TEST_SUITE_P( UnicodeTest, CharacterTest, ValuesIn( tests ) );
TEST( CharacterTest, Equality ) {
Repository< Character >& repo( Repository< Character >::Instance() );
// The lowercase of the Latin capital letter e with acute "É" (which can be
// represented as the Latin capital letter "E" plus the combining acute
// character) is the Latin small letter e with acute "é".
EXPECT_THAT( repo.GetElements( { NormalizeInput( "e" ),
NormalizeInput( "é" ),
NormalizeInput( "E" ),
NormalizeInput( "É" ) } ),
CharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "é" ),
NormalizeInput( "é" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "É" ),
NormalizeInput( "É" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "e" ),
NormalizeInput( "E" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "é" ),
NormalizeInput( "É" ),
NormalizeInput( "É" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "e" ),
NormalizeInput( "é" ),
NormalizeInput( "é" ),
NormalizeInput( "E" ),
NormalizeInput( "É" ),
NormalizeInput( "É" ) } ),
BaseCharactersAreEqual() );
// The Greek capital letter omega "Ω" is the same character as the ohm sign
// "Ω". The lowercase of both characters is the Greek small letter omega "ω".
EXPECT_THAT( repo.GetElements( { NormalizeInput( "Ω" ),
NormalizeInput( "Ω" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "ω" ),
NormalizeInput( "Ω" ),
NormalizeInput( "Ω" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "ω" ),
NormalizeInput( "Ω" ),
NormalizeInput( "Ω" ) } ),
BaseCharactersAreEqual() );
// The Latin capital letter a with ring above "Å" (which can be represented as
// the Latin capital letter "A" plus the combining ring above character) is
// the same character as the angstrom sign "Å". The lowercase of these
// characters is the Latin small letter a with ring above "å" (which can also
// be represented as the Latin small letter "a" plus the combining ring above
// character).
EXPECT_THAT( repo.GetElements( { NormalizeInput( "a" ),
NormalizeInput( "å" ),
NormalizeInput( "A" ),
NormalizeInput( "Å" ) } ),
CharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "å" ),
NormalizeInput( "å" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "Å" ),
NormalizeInput( "Å" ),
NormalizeInput( "Å" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "å" ),
NormalizeInput( "å" ),
NormalizeInput( "Å" ),
NormalizeInput( "Å" ),
NormalizeInput( "Å" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "a" ),
NormalizeInput( "å" ),
NormalizeInput( "å" ),
NormalizeInput( "A" ),
NormalizeInput( "Å" ),
NormalizeInput( "Å" ),
NormalizeInput( "Å" ) } ),
BaseCharactersAreEqual() );
// The uppercase of the Greek small letter sigma "σ" and Greek small letter
// final sigma "ς" is the Greek capital letter sigma "Σ".
EXPECT_THAT( repo.GetElements( { NormalizeInput( "σ" ),
NormalizeInput( "ς" ),
NormalizeInput( "Σ" ) } ),
CharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "σ" ),
NormalizeInput( "ς" ),
NormalizeInput( "Σ" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "σ" ),
NormalizeInput( "ς" ),
NormalizeInput( "Σ" ) } ),
BaseCharactersAreEqual() );
// The lowercase of the Greek capital theta symbol "ϴ" and capital letter
// theta "Θ" is the Greek small letter theta "θ". There is also the Greek
// theta symbol "ϑ" whose uppercase is "Θ".
EXPECT_THAT( repo.GetElements( { NormalizeInput( "θ" ),
NormalizeInput( "ϑ" ),
NormalizeInput( "ϴ" ),
NormalizeInput( "Θ" ) } ),
CharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "θ" ),
NormalizeInput( "ϑ" ),
NormalizeInput( "ϴ" ),
NormalizeInput( "Θ" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "θ" ),
NormalizeInput( "ϑ" ),
NormalizeInput( "ϴ" ),
NormalizeInput( "Θ" ) } ),
BaseCharactersAreEqual() );
// In the Latin alphabet, the uppercase of "i" (with a dot) is "I" (without a
// dot). However, in the Turkish alphabet (a variant of the Latin alphabet),
// there are two distinct versions of the letter "i":
// - "ı" (without a dot) whose uppercase is "I" (without a dot);
// - "i" (with a dot) whose uppercase is "İ" (with a dot), which can also be
// represented as the letter "I" plus the combining dot above character.
// Since our matching is language-independent, the Turkish form is ignored and
// the letter "ı" (without a dot) does not match "I" (without a dot) when the
// case is ignored. Similarly, "ı" plus the combining dot above character does
// not match "İ" (with a dot) or "I" plus the combining dot above character
// but "i" (with a dot) plus the combining dot above does.
EXPECT_THAT( repo.GetElements( { NormalizeInput( "i" ),
NormalizeInput( "I" ),
NormalizeInput( "ı" ),
NormalizeInput( "ı̇" ),
NormalizeInput( "i̇" ),
NormalizeInput( "İ" ) } ),
CharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "İ" ),
NormalizeInput( "İ" ) } ),
CharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "i" ),
NormalizeInput( "I" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "i̇" ),
NormalizeInput( "İ" ),
NormalizeInput( "İ" ) } ),
CharactersAreEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "ı" ),
NormalizeInput( "ı̇" ),
NormalizeInput( "I" ),
NormalizeInput( "İ" ) } ),
CharactersAreNotEqualWhenCaseIsIgnored() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "i" ),
NormalizeInput( "ı" ) } ),
BaseCharactersAreNotEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "i" ),
NormalizeInput( "i̇" ),
NormalizeInput( "I" ),
NormalizeInput( "İ" ),
NormalizeInput( "İ" ) } ),
BaseCharactersAreEqual() );
EXPECT_THAT( repo.GetElements( { NormalizeInput( "ı" ),
NormalizeInput( "ı̇" ) } ),
BaseCharactersAreEqual() );
}
TEST( CharacterTest, SmartMatching ) {
// The letter "é" and "É" appear twice in the tests as they can be represented
// on one code point or two ("e"/"E" plus the combining acute character).
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "e" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "é" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "E" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_TRUE ( Character( NormalizeInput( "É" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "e" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "é" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "E" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
EXPECT_FALSE( Character( NormalizeInput( "è" ) )
.MatchesSmart( Character( NormalizeInput( "É" ) ) ) );
}
} // namespace YouCompleteMe
|
