UnicodeTest.php 18.3 KB
Newer Older
1
2
3
4
5
<?php

namespace Drupal\Tests\Component\Utility;

use Drupal\Component\Utility\Unicode;
6
use PHPUnit\Framework\TestCase;
7
8

/**
9
10
 * Test unicode handling features implemented in Unicode component.
 *
11
 * @group Utility
12
13
 *
 * @coversDefaultClass \Drupal\Component\Utility\Unicode
14
 */
15
class UnicodeTest extends TestCase {
16

17
18
19
20
21
  /**
   * {@inheritdoc}
   *
   * @covers ::check
   */
22
  protected function setUp() {
23
24
25
26
27
    // Initialize unicode component.
    Unicode::check();
  }

  /**
28
   * Getting and settings the multibyte environment status.
29
30
   *
   * @dataProvider providerTestStatus
31
32
   * @covers ::getStatus
   * @covers ::setStatus
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
   */
  public function testStatus($value, $expected, $invalid = FALSE) {
    if ($invalid) {
      $this->setExpectedException('InvalidArgumentException');
    }
    Unicode::setStatus($value);
    $this->assertEquals($expected, Unicode::getStatus());
  }

  /**
   * Data provider for testStatus().
   *
   * @see testStatus()
   *
   * @return array
   *   An array containing:
   *     - The status value to set.
   *     - The status value to expect after setting the new value.
   *     - (optional) Boolean indicating invalid status. Defaults to FALSE.
   */
  public function providerTestStatus() {
54
55
56
57
58
59
60
61
62
    return [
      [Unicode::STATUS_SINGLEBYTE, Unicode::STATUS_SINGLEBYTE],
      [rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE],
      [rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE],
      [Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE],
      [rand(10, 100), Unicode::STATUS_MULTIBYTE, TRUE],
      [Unicode::STATUS_ERROR, Unicode::STATUS_ERROR],
      [Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE],
    ];
63
64
65
  }

  /**
66
   * Tests multibyte encoding and decoding.
67
68
   *
   * @dataProvider providerTestMimeHeader
69
70
   * @covers ::mimeHeaderEncode
   * @covers ::mimeHeaderDecode
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
   */
  public function testMimeHeader($value, $encoded) {
    $this->assertEquals($encoded, Unicode::mimeHeaderEncode($value));
    $this->assertEquals($value, Unicode::mimeHeaderDecode($encoded));
  }

  /**
   * Data provider for testMimeHeader().
   *
   * @see testMimeHeader()
   *
   * @return array
   *   An array containing a string and its encoded value.
   */
  public function providerTestMimeHeader() {
86
87
    return [
      ['tést.txt', '=?UTF-8?B?dMOpc3QudHh0?='],
88
      // Simple ASCII characters.
89
90
      ['ASCII', 'ASCII'],
    ];
91
92
93
  }

  /**
94
   * Tests multibyte strtolower.
95
96
   *
   * @dataProvider providerStrtolower
97
98
   * @covers ::strtolower
   * @covers ::caseFlip
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
   */
  public function testStrtolower($text, $expected, $multibyte = FALSE) {
    $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
    Unicode::setStatus($status);
    $this->assertEquals($expected, Unicode::strtolower($text));
  }

  /**
   * Data provider for testStrtolower().
   *
   * @see testStrtolower()
   *
   * @return array
   *   An array containing a string, its lowercase version and whether it should
   *   be processed as multibyte.
   */
  public function providerStrtolower() {
116
117
118
119
    $cases = [
      ['tHe QUIcK bRoWn', 'the quick brown'],
      ['FrançAIS is ÜBER-åwesome', 'français is über-åwesome'],
    ];
120
121
122
123
124
125
    foreach ($cases as $case) {
      // Test the same string both in multibyte and singlebyte conditions.
      array_push($case, TRUE);
      $cases[] = $case;
    }
    // Add a multibyte string.
126
    $cases[] = ['ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αβγδεζηθικλμνξοσὠ', TRUE];
127
128
129
130
    return $cases;
  }

  /**
131
   * Tests multibyte strtoupper.
132
133
   *
   * @dataProvider providerStrtoupper
134
135
   * @covers ::strtoupper
   * @covers ::caseFlip
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
   */
  public function testStrtoupper($text, $expected, $multibyte = FALSE) {
    $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
    Unicode::setStatus($status);
    $this->assertEquals($expected, Unicode::strtoupper($text));
  }

  /**
   * Data provider for testStrtoupper().
   *
   * @see testStrtoupper()
   *
   * @return array
   *   An array containing a string, its uppercase version and whether it should
   *   be processed as multibyte.
   */
  public function providerStrtoupper() {
153
154
155
156
    $cases = [
      ['tHe QUIcK bRoWn', 'THE QUICK BROWN'],
      ['FrançAIS is ÜBER-åwesome', 'FRANÇAIS IS ÜBER-ÅWESOME'],
    ];
157
158
159
160
161
162
    foreach ($cases as $case) {
      // Test the same string both in multibyte and singlebyte conditions.
      array_push($case, TRUE);
      $cases[] = $case;
    }
    // Add a multibyte string.
163
    $cases[] = ['αβγδεζηθικλμνξοσὠ', 'ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', TRUE];
164
165
166
167
    return $cases;
  }

  /**
168
   * Tests multibyte ucfirst.
169
170
   *
   * @dataProvider providerUcfirst
171
   * @covers ::ucfirst
172
173
174
175
176
177
178
179
180
181
182
183
184
185
   */
  public function testUcfirst($text, $expected) {
    $this->assertEquals($expected, Unicode::ucfirst($text));
  }

  /**
   * Data provider for testUcfirst().
   *
   * @see testUcfirst()
   *
   * @return array
   *   An array containing a string and its uppercase first version.
   */
  public function providerUcfirst() {
186
187
188
189
190
    return [
      ['tHe QUIcK bRoWn', 'THe QUIcK bRoWn'],
      ['françAIS', 'FrançAIS'],
      ['über', 'Über'],
      ['åwesome', 'Åwesome'],
191
      // A multibyte string.
192
193
      ['σion', 'Σion'],
    ];
194
195
  }

196
  /**
197
   * Tests multibyte lcfirst.
198
199
   *
   * @dataProvider providerLcfirst
200
   * @covers ::lcfirst
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
   */
  public function testLcfirst($text, $expected, $multibyte = FALSE) {
    $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
    Unicode::setStatus($status);
    $this->assertEquals($expected, Unicode::lcfirst($text));
  }

  /**
   * Data provider for testLcfirst().
   *
   * @see testLcfirst()
   *
   * @return array
   *   An array containing a string, its lowercase version and whether it should
   *   be processed as multibyte.
   */
  public function providerLcfirst() {
218
219
220
221
222
    return [
      ['tHe QUIcK bRoWn', 'tHe QUIcK bRoWn'],
      ['FrançAIS is ÜBER-åwesome', 'françAIS is ÜBER-åwesome'],
      ['Über', 'über'],
      ['Åwesome', 'åwesome'],
223
      // Add a multibyte string.
224
225
      ['ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', TRUE],
    ];
226
227
228
  }

  /**
229
   * Tests multibyte ucwords.
230
231
   *
   * @dataProvider providerUcwords
232
   * @covers ::ucwords
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
   */
  public function testUcwords($text, $expected, $multibyte = FALSE) {
    $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
    Unicode::setStatus($status);
    $this->assertEquals($expected, Unicode::ucwords($text));
  }

  /**
   * Data provider for testUcwords().
   *
   * @see testUcwords()
   *
   * @return array
   *   An array containing a string, its capitalized version and whether it should
   *   be processed as multibyte.
   */
  public function providerUcwords() {
250
251
252
253
254
    return [
      ['tHe QUIcK bRoWn', 'THe QUIcK BRoWn'],
      ['françAIS', 'FrançAIS'],
      ['über', 'Über'],
      ['åwesome', 'Åwesome'],
255
      // Make sure we don't mangle extra spaces.
256
      ['frànçAIS is  über-åwesome', 'FrànçAIS Is  Über-Åwesome'],
257
      // Add a multibyte string.
258
259
      ['σion', 'Σion', TRUE],
    ];
260
261
  }

262
  /**
263
   * Tests multibyte strlen.
264
265
   *
   * @dataProvider providerStrlen
266
   * @covers ::strlen
267
268
   */
  public function testStrlen($text, $expected) {
269
270
271
272
273
    // Run through multibyte code path.
    Unicode::setStatus(Unicode::STATUS_MULTIBYTE);
    $this->assertEquals($expected, Unicode::strlen($text));
    // Run through singlebyte code path.
    Unicode::setStatus(Unicode::STATUS_SINGLEBYTE);
274
275
276
277
278
279
280
281
282
283
284
285
    $this->assertEquals($expected, Unicode::strlen($text));
  }

  /**
   * Data provider for testStrlen().
   *
   * @see testStrlen()
   *
   * @return array
   *   An array containing a string and its length.
   */
  public function providerStrlen() {
286
287
288
289
290
    return [
      ['tHe QUIcK bRoWn', 15],
      ['ÜBER-åwesome', 12],
      ['以呂波耳・ほへとち。リヌルヲ。', 15],
    ];
291
292
293
  }

  /**
294
   * Tests multibyte substr.
295
296
   *
   * @dataProvider providerSubstr
297
   * @covers ::substr
298
299
   */
  public function testSubstr($text, $start, $length, $expected) {
300
301
302
303
304
    // Run through multibyte code path.
    Unicode::setStatus(Unicode::STATUS_MULTIBYTE);
    $this->assertEquals($expected, Unicode::substr($text, $start, $length));
    // Run through singlebyte code path.
    Unicode::setStatus(Unicode::STATUS_SINGLEBYTE);
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
    $this->assertEquals($expected, Unicode::substr($text, $start, $length));
  }

  /**
   * Data provider for testSubstr().
   *
   * @see testSubstr()
   *
   * @return array
   *   An array containing:
   *     - The string to test.
   *     - The start number to be processed by substr.
   *     - The length number to be processed by substr.
   *     - The expected string result.
   */
  public function providerSubstr() {
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
    return [
      ['frànçAIS is über-åwesome', 0, NULL, 'frànçAIS is über-åwesome'],
      ['frànçAIS is über-åwesome', 0, 0, ''],
      ['frànçAIS is über-åwesome', 0, 1, 'f'],
      ['frànçAIS is über-åwesome', 0, 8, 'frànçAIS'],
      ['frànçAIS is über-åwesome', 0, 23, 'frànçAIS is über-åwesom'],
      ['frànçAIS is über-åwesome', 0, 24, 'frànçAIS is über-åwesome'],
      ['frànçAIS is über-åwesome', 0, 25, 'frànçAIS is über-åwesome'],
      ['frànçAIS is über-åwesome', 0, 100, 'frànçAIS is über-åwesome'],
      ['frànçAIS is über-åwesome', 4, 4, 'çAIS'],
      ['frànçAIS is über-åwesome', 1, 0, ''],
      ['frànçAIS is über-åwesome', 100, 0, ''],
      ['frànçAIS is über-åwesome', -4, 2, 'so'],
      ['frànçAIS is über-åwesome', -4, 3, 'som'],
      ['frànçAIS is über-åwesome', -4, 4, 'some'],
      ['frànçAIS is über-åwesome', -4, 5, 'some'],
      ['frànçAIS is über-åwesome', -7, 10, 'åwesome'],
      ['frànçAIS is über-åwesome', 5, -10, 'AIS is üb'],
      ['frànçAIS is über-åwesome', 0, -10, 'frànçAIS is üb'],
      ['frànçAIS is über-åwesome', 0, -1, 'frànçAIS is über-åwesom'],
      ['frànçAIS is über-åwesome', -7, -2, 'åweso'],
      ['frànçAIS is über-åwesome', -7, -6, 'å'],
      ['frànçAIS is über-åwesome', -7, -7, ''],
      ['frànçAIS is über-åwesome', -7, -8, ''],
      ['...', 0, 2, '..'],
      ['以呂波耳・ほへとち。リヌルヲ。', 1, 3, '呂波耳'],
    ];
348
349
350
  }

  /**
351
   * Tests multibyte truncate.
352
353
   *
   * @dataProvider providerTruncate
354
   * @covers ::truncate
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
   */
  public function testTruncate($text, $max_length, $expected, $wordsafe = FALSE, $add_ellipsis = FALSE) {
    $this->assertEquals($expected, Unicode::truncate($text, $max_length, $wordsafe, $add_ellipsis));
  }

  /**
   * Data provider for testTruncate().
   *
   * @see testTruncate()
   *
   * @return array
   *   An array containing:
   *     - The string to test.
   *     - The max length to truncate this string to.
   *     - The expected string result.
   *     - (optional) Boolean for the $wordsafe flag. Defaults to FALSE.
   *     - (optional) Boolean for the $add_ellipsis flag. Defaults to FALSE.
   */
  public function providerTruncate() {
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
    return [
      ['frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome'],
      ['frànçAIS is über-åwesome', 23, 'frànçAIS is über-åwesom'],
      ['frànçAIS is über-åwesome', 17, 'frànçAIS is über-'],
      ['以呂波耳・ほへとち。リヌルヲ。', 6, '以呂波耳・ほ'],
      ['frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome', FALSE, TRUE],
      ['frànçAIS is über-åwesome', 23, 'frànçAIS is über-åweso…', FALSE, TRUE],
      ['frànçAIS is über-åwesome', 17, 'frànçAIS is über…', FALSE, TRUE],
      ['123', 1, '…', TRUE, TRUE],
      ['123', 2, '1…', TRUE, TRUE],
      ['123', 3, '123', TRUE, TRUE],
      ['1234', 3, '12…', TRUE, TRUE],
      ['1234567890', 10, '1234567890', TRUE, TRUE],
      ['12345678901', 10, '123456789…', TRUE, TRUE],
      ['12345678901', 11, '12345678901', TRUE, TRUE],
      ['123456789012', 11, '1234567890…', TRUE, TRUE],
      ['12345 7890', 10, '12345 7890', TRUE, TRUE],
      ['12345 7890', 9, '12345…', TRUE, TRUE],
      ['123 567 90', 10, '123 567 90', TRUE, TRUE],
      ['123 567 901', 10, '123 567…', TRUE, TRUE],
      ['Stop. Hammertime.', 17, 'Stop. Hammertime.', TRUE, TRUE],
      ['Stop. Hammertime.', 16, 'Stop…', TRUE, TRUE],
      ['frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome', TRUE, TRUE],
      ['frànçAIS is über-åwesome', 23, 'frànçAIS is über…', TRUE, TRUE],
      ['frànçAIS is über-åwesome', 17, 'frànçAIS is über…', TRUE, TRUE],
      ['¿Dónde está el niño?', 20, '¿Dónde está el niño?', TRUE, TRUE],
      ['¿Dónde está el niño?', 19, '¿Dónde está el…', TRUE, TRUE],
      ['¿Dónde está el niño?', 13, '¿Dónde está…', TRUE, TRUE],
      ['¿Dónde está el niño?', 10, '¿Dónde…', TRUE, TRUE],
      ['Help! Help! Help!', 17, 'Help! Help! Help!', TRUE, TRUE],
      ['Help! Help! Help!', 16, 'Help! Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 15, 'Help! Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 14, 'Help! Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 13, 'Help! Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 12, 'Help! Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 11, 'Help! Help…', TRUE, TRUE],
      ['Help! Help! Help!', 10, 'Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 9, 'Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 8, 'Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 7, 'Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 6, 'Help!…', TRUE, TRUE],
      ['Help! Help! Help!', 5, 'Help…', TRUE, TRUE],
      ['Help! Help! Help!', 4, 'Hel…', TRUE, TRUE],
      ['Help! Help! Help!', 3, 'He…', TRUE, TRUE],
      ['Help! Help! Help!', 2, 'H…', TRUE, TRUE],
    ];
420
421
  }

422
  /**
423
424
425
426
   * Tests multibyte truncate bytes.
   *
   * @dataProvider providerTestTruncateBytes
   * @covers ::truncateBytes
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
   *
   * @param string $text
   *   The string to truncate.
   * @param int $max_length
   *   The upper limit on the returned string length.
   * @param string $expected
   *   The expected return from Unicode::truncateBytes().
   */
  public function testTruncateBytes($text, $max_length, $expected) {
    $this->assertEquals($expected, Unicode::truncateBytes($text, $max_length), 'The string was not correctly truncated.');
  }

  /**
   * Provides data for self::testTruncateBytes().
   *
   * @return array
   *   An array of arrays, each containing the parameters to
   *   self::testTruncateBytes().
   */
  public function providerTestTruncateBytes() {
447
    return [
448
      // String shorter than max length.
449
      ['Short string', 42, 'Short string'],
450
      // Simple string longer than max length.
451
      ['Longer string than previous.', 10, 'Longer str'],
452
      // Unicode.
453
454
      ['以呂波耳・ほへとち。リヌルヲ。', 10, '以呂波'],
    ];
455
456
457
  }

  /**
458
459
460
461
   * Tests UTF-8 validation.
   *
   * @dataProvider providerTestValidateUtf8
   * @covers ::validateUtf8
462
463
464
   *
   * @param string $text
   *   The text to validate.
465
   * @param bool $expected
466
467
468
469
470
471
472
473
474
475
476
   *   The expected return value from Unicode::validateUtf8().
   * @param string $message
   *   The message to display on failure.
   */
  public function testValidateUtf8($text, $expected, $message) {
    $this->assertEquals($expected, Unicode::validateUtf8($text), $message);
  }

  /**
   * Provides data for self::testValidateUtf8().
   *
477
478
   * Invalid UTF-8 examples sourced from http://stackoverflow.com/a/11709412/109119.
   *
479
480
481
482
483
   * @return array
   *   An array of arrays, each containing the parameters for
   *   self::testValidateUtf8().
   */
  public function providerTestValidateUtf8() {
484
    return [
485
      // Empty string.
486
      ['', TRUE, 'An empty string did not validate.'],
487
      // Simple text string.
488
      ['Simple text.', TRUE, 'A simple ASCII text string did not validate.'],
489
      // Invalid UTF-8, overlong 5 byte encoding.
490
      [chr(0xF8) . chr(0x80) . chr(0x80) . chr(0x80) . chr(0x80), FALSE, 'Invalid UTF-8 was validated.'],
491
      // High code-point without trailing characters.
492
493
      [chr(0xD0) . chr(0x01), FALSE, 'Invalid UTF-8 was validated.'],
    ];
494
495
496
  }

  /**
497
498
499
500
   * Tests UTF-8 conversion.
   *
   * @dataProvider providerTestConvertToUtf8
   * @covers ::convertToUtf8
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
   *
   * @param string $data
   *   The data to be converted.
   * @param string $encoding
   *   The encoding the data is in.
   * @param string|bool $expected
   *   The expected result.
   */
  public function testConvertToUtf8($data, $encoding, $expected) {
    $this->assertEquals($expected, Unicode::convertToUtf8($data, $encoding));
  }

  /**
   * Provides data to self::testConvertToUtf8().
   *
   * @return array
517
   *   An array of arrays, each containing the parameters to
518
519
520
   *   self::testConvertUtf8().  }
   */
  public function providerTestConvertToUtf8() {
521
522
523
524
525
    return [
      [chr(0x97), 'Windows-1252', '—'],
      [chr(0x99), 'Windows-1252', '™'],
      [chr(0x80), 'Windows-1252', '€'],
    ];
526
527
  }

528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
  /**
   * Tests multibyte strpos.
   *
   * @dataProvider providerStrpos
   * @covers ::strpos
   */
  public function testStrpos($haystack, $needle, $offset, $expected) {
    // Run through multibyte code path.
    Unicode::setStatus(Unicode::STATUS_MULTIBYTE);
    $this->assertEquals($expected, Unicode::strpos($haystack, $needle, $offset));
    // Run through singlebyte code path.
    Unicode::setStatus(Unicode::STATUS_SINGLEBYTE);
    $this->assertEquals($expected, Unicode::strpos($haystack, $needle, $offset));
  }

  /**
   * Data provider for testStrpos().
   *
   * @see testStrpos()
   *
   * @return array
   *   An array containing:
   *     - The haystack string to be searched in.
   *     - The needle string to search for.
   *     - The offset integer to start at.
   *     - The expected integer/FALSE result.
   */
  public function providerStrpos() {
556
557
558
559
560
561
562
563
564
565
566
567
    return [
      ['frànçAIS is über-åwesome', 'frànçAIS is über-åwesome', 0, 0],
      ['frànçAIS is über-åwesome', 'rànçAIS is über-åwesome', 0, 1],
      ['frànçAIS is über-åwesome', 'not in string', 0, FALSE],
      ['frànçAIS is über-åwesome', 'r', 0, 1],
      ['frànçAIS is über-åwesome', 'nçAIS', 0, 3],
      ['frànçAIS is über-åwesome', 'nçAIS', 2, 3],
      ['frànçAIS is über-åwesome', 'nçAIS', 3, 3],
      ['以呂波耳・ほへとち。リヌルヲ。', '波耳', 0, 2],
      ['以呂波耳・ほへとち。リヌルヲ。', '波耳', 1, 2],
      ['以呂波耳・ほへとち。リヌルヲ。', '波耳', 2, 2],
    ];
568
569
  }

570
}