UnicodeTest.php 16.8 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
<?php

/**
 * @file
 * Contains \Drupal\Tests\Component\Utility\UnicodeTest.
 */

namespace Drupal\Tests\Component\Utility;

use Drupal\Tests\UnitTestCase;
use Drupal\Component\Utility\Unicode;

/**
14
15
 * @coversDefaultClass \Drupal\Component\Utility\Unicode
 * @group Utility
16
17
18
 */
class UnicodeTest extends UnitTestCase {

19
  protected function setUp() {
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
    // Initialize unicode component.
    Unicode::check();
  }

  /**
   * Tests Unicode::getStatus() and Unicode::setStatus().
   *
   * @dataProvider providerTestStatus
   */
  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() {
    return array(
      array(Unicode::STATUS_SINGLEBYTE, Unicode::STATUS_SINGLEBYTE),
      array(rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE),
      array(rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE),
      array(Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE),
      array(rand(10, 100), Unicode::STATUS_MULTIBYTE, TRUE),
      array(Unicode::STATUS_ERROR, Unicode::STATUS_ERROR),
      array(Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE),
    );
  }

  /**
   * Tests Unicode::mimeHeaderEncode() and Unicode::mimeHeaderDecode().
   *
   * @dataProvider providerTestMimeHeader
   */
  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() {
    return array(
      array('tést.txt', '=?UTF-8?B?dMOpc3QudHh0?='),
81
82
      // Simple ASCII characters.
      array('ASCII', 'ASCII'),
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
    );
  }

  /**
   * Tests Unicode::strtolower().
   *
   * @dataProvider providerStrtolower
   */
  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() {
    $cases = array(
      array('tHe QUIcK bRoWn', 'the quick brown'),
      array('FrançAIS is ÜBER-åwesome', 'français is über-åwesome'),
    );
    foreach ($cases as $case) {
      // Test the same string both in multibyte and singlebyte conditions.
      array_push($case, TRUE);
      $cases[] = $case;
    }
    // Add a multibyte string.
    $cases[] = array('ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αβγδεζηθικλμνξοσὠ', TRUE);
    return $cases;
  }

  /**
   * Tests Unicode::strtoupper().
   *
   * @dataProvider providerStrtoupper
   */
  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() {
    $cases = array(
      array('tHe QUIcK bRoWn', 'THE QUICK BROWN'),
      array('FrançAIS is ÜBER-åwesome', 'FRANÇAIS IS ÜBER-ÅWESOME'),
    );
    foreach ($cases as $case) {
      // Test the same string both in multibyte and singlebyte conditions.
      array_push($case, TRUE);
      $cases[] = $case;
    }
    // Add a multibyte string.
    $cases[] = array('αβγδεζηθικλμνξοσὠ', 'ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', TRUE);
    return $cases;
  }

  /**
   * Tests Unicode::ucfirst().
   *
   * @dataProvider providerUcfirst
   */
  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() {
    return array(
      array('tHe QUIcK bRoWn', 'THe QUIcK bRoWn'),
      array('françAIS', 'FrançAIS'),
      array('über', 'Über'),
      array('åwesome', 'Åwesome'),
      // A multibyte string.
      array('σion', 'Σion'),
    );
  }

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
  /**
   * Tests Unicode::lcfirst().
   *
   * @dataProvider providerLcfirst
   */
  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() {
    return array(
      array('tHe QUIcK bRoWn', 'tHe QUIcK bRoWn'),
      array('FrançAIS is ÜBER-åwesome', 'françAIS is ÜBER-åwesome'),
      array('Über', 'über'),
      array('Åwesome', 'åwesome'),
      // Add a multibyte string.
      array('ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', TRUE),
    );
  }

  /**
   * Tests Unicode::ucwords().
   *
   * @dataProvider providerUcwords
   */
  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() {
    return array(
      array('tHe QUIcK bRoWn', 'THe QUIcK BRoWn'),
      array('françAIS', 'FrançAIS'),
      array('über', 'Über'),
      array('åwesome', 'Åwesome'),
      // Make sure we don't mangle extra spaces.
      array('frànçAIS is  über-åwesome', 'FrànçAIS Is  Über-Åwesome'),
      // Add a multibyte string.
      array('σion', 'Σion', TRUE),
    );
  }

248
249
250
251
252
253
  /**
   * Tests Unicode::strlen().
   *
   * @dataProvider providerStrlen
   */
  public function testStrlen($text, $expected) {
254
255
256
257
258
    // 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);
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
    $this->assertEquals($expected, Unicode::strlen($text));
  }

  /**
   * Data provider for testStrlen().
   *
   * @see testStrlen()
   *
   * @return array
   *   An array containing a string and its length.
   */
  public function providerStrlen() {
    return array(
      array('tHe QUIcK bRoWn', 15),
      array('ÜBER-åwesome', 12),
    );
  }

  /**
   * Tests Unicode::substr().
   *
   * @dataProvider providerSubstr
   */
  public function testSubstr($text, $start, $length, $expected) {
283
284
285
286
287
    // 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);
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
    $this->assertEquals($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() {
    return array(
      array('frànçAIS is über-åwesome', 0, 0, ''),
      array('frànçAIS is über-åwesome', 0, 1, 'f'),
      array('frànçAIS is über-åwesome', 0, 8, 'frànçAIS'),
      array('frànçAIS is über-åwesome', 0, 23, 'frànçAIS is über-åwesom'),
      array('frànçAIS is über-åwesome', 0, 24, 'frànçAIS is über-åwesome'),
      array('frànçAIS is über-åwesome', 0, 25, 'frànçAIS is über-åwesome'),
      array('frànçAIS is über-åwesome', 0, 100, 'frànçAIS is über-åwesome'),
      array('frànçAIS is über-åwesome', 4, 4, 'çAIS'),
      array('frànçAIS is über-åwesome', 1, 0, ''),
      array('frànçAIS is über-åwesome', 100, 0, ''),
      array('frànçAIS is über-åwesome', -4, 2, 'so'),
      array('frànçAIS is über-åwesome', -4, 3, 'som'),
      array('frànçAIS is über-åwesome', -4, 4, 'some'),
      array('frànçAIS is über-åwesome', -4, 5, 'some'),
      array('frànçAIS is über-åwesome', -7, 10, 'åwesome'),
      array('frànçAIS is über-åwesome', 5, -10, 'AIS is üb'),
      array('frànçAIS is über-åwesome', 0, -10, 'frànçAIS is üb'),
      array('frànçAIS is über-åwesome', 0, -1, 'frànçAIS is über-åwesom'),
      array('frànçAIS is über-åwesome', -7, -2, 'åweso'),
      array('frànçAIS is über-åwesome', -7, -6, 'å'),
      array('frànçAIS is über-åwesome', -7, -7, ''),
      array('frànçAIS is über-åwesome', -7, -8, ''),
      array('...', 0, 2, '..'),
      array('以呂波耳・ほへとち。リヌルヲ。', 1, 3, '呂波耳'),
    );
  }

  /**
   * Tests Unicode::truncate().
   *
   * @dataProvider providerTruncate
   */
  public function testTruncate($text, $max_length, $expected, $wordsafe = FALSE, $add_ellipsis = FALSE) {
    Unicode::check();
    $this->assertEquals($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() {
    return array(
      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome'),
      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über-åwesom'),
      array('frànçAIS is über-åwesome', 17, 'frànçAIS is über-'),
      array('以呂波耳・ほへとち。リヌルヲ。', 6, '以呂波耳・ほ'),
      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome', FALSE, TRUE),
      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über-åweso…', FALSE, TRUE),
      array('frànçAIS is über-åwesome', 17, 'frànçAIS is über…', FALSE, TRUE),
      array('123', 1, '…', TRUE, TRUE),
      array('123', 2, '1…', TRUE, TRUE),
      array('123', 3, '123', TRUE, TRUE),
      array('1234', 3, '12…', TRUE, TRUE),
      array('1234567890', 10, '1234567890', TRUE, TRUE),
      array('12345678901', 10, '123456789…', TRUE, TRUE),
      array('12345678901', 11, '12345678901', TRUE, TRUE),
      array('123456789012', 11, '1234567890…', TRUE, TRUE),
      array('12345 7890', 10, '12345 7890', TRUE, TRUE),
      array('12345 7890', 9, '12345…', TRUE, TRUE),
      array('123 567 90', 10, '123 567 90', TRUE, TRUE),
      array('123 567 901', 10, '123 567…', TRUE, TRUE),
      array('Stop. Hammertime.', 17, 'Stop. Hammertime.', TRUE, TRUE),
      array('Stop. Hammertime.', 16, 'Stop…', TRUE, TRUE),
      array('frànçAIS is über-åwesome', 24, 'frànçAIS is über-åwesome', TRUE, TRUE),
      array('frànçAIS is über-åwesome', 23, 'frànçAIS is über…', TRUE, TRUE),
      array('frànçAIS is über-åwesome', 17, 'frànçAIS is über…', TRUE, TRUE),
      array('¿Dónde está el niño?', 20, '¿Dónde está el niño?', TRUE, TRUE),
      array('¿Dónde está el niño?', 19, '¿Dónde está el…', TRUE, TRUE),
      array('¿Dónde está el niño?', 13, '¿Dónde está…', TRUE, TRUE),
      array('¿Dónde está el niño?', 10, '¿Dónde…', TRUE, TRUE),
      array('Help! Help! Help!', 17, 'Help! Help! Help!', TRUE, TRUE),
      array('Help! Help! Help!', 16, 'Help! Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 15, 'Help! Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 14, 'Help! Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 13, 'Help! Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 12, 'Help! Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 11, 'Help! Help…', TRUE, TRUE),
      array('Help! Help! Help!', 10, 'Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 9, 'Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 8, 'Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 7, 'Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 6, 'Help!…', TRUE, TRUE),
      array('Help! Help! Help!', 5, 'Help…', TRUE, TRUE),
      array('Help! Help! Help!', 4, 'Hel…', TRUE, TRUE),
      array('Help! Help! Help!', 3, 'He…', TRUE, TRUE),
      array('Help! Help! Help!', 2, 'H…', TRUE, TRUE),
    );
  }

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
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
  /**
   * Tests Unicode::truncateBytes().
   *
   * @param string $text
   *   The string to truncate.
   * @param int $max_length
   *   The upper limit on the returned string length.
   * @param string $expected
   *   The expected return from Unicode::truncateBytes().
   *
   * @dataProvider providerTestTruncateBytes
   */
  public function testTruncateBytes($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() {
    return array(
      // String shorter than max length.
      array('Short string', 42, 'Short string'),
      // Simple string longer than max length.
      array('Longer string than previous.', 10, 'Longer str'),
      // Unicode.
      array('以呂波耳・ほへとち。リヌルヲ。', 10, '以呂波'),
    );
  }

  /**
   * Tests Unicode::validateUtf8().
   *
   * @param string $text
   *   The text to validate.
   * @param boolean $expected
   *   The expected return value from Unicode::validateUtf8().
   * @param string $message
   *   The message to display on failure.
   *
   * @dataProvider providerTestValidateUtf8
   */
  public function testValidateUtf8($text, $expected, $message) {
    $this->assertEquals($expected, Unicode::validateUtf8($text), $message);
  }

  /**
   * Provides data for self::testValidateUtf8().
   *
   * @return array
   *   An array of arrays, each containing the parameters for
   *   self::testValidateUtf8().
   *
   * Invalid UTF-8 examples sourced from http://stackoverflow.com/a/11709412/109119.
   */
  public function providerTestValidateUtf8() {
    return array(
      // Empty string.
      array('', TRUE, 'An empty string did not validate.'),
      // Simple text string.
      array('Simple text.', TRUE, 'A simple ASCII text string did not validate.'),
      // Invalid UTF-8, overlong 5 byte encoding.
      array(chr(0xF8) . chr(0x80) . chr(0x80) . chr(0x80) . chr(0x80), FALSE, 'Invalid UTF-8 was validated.'),
      // High code-point without trailing characters.
      array(chr(0xD0) . chr(0x01), FALSE, 'Invalid UTF-8 was validated.'),
    );
  }

  /**
   * Tests Unicode::convertToUtf8().
   *
   * @param string $data
   *   The data to be converted.
   * @param string $encoding
   *   The encoding the data is in.
   * @param string|bool $expected
   *   The expected result.
   *
   * @dataProvider providerTestConvertToUtf8
   */
  public function testConvertToUtf8($data, $encoding, $expected) {
    $this->assertEquals($expected, Unicode::convertToUtf8($data, $encoding));
  }

  /**
   * Provides data to self::testConvertToUtf8().
   *
   * @return array
496
   *   An array of arrays, each containing the parameters to
497
498
499
500
   *   self::testConvertUtf8().  }
   */
  public function providerTestConvertToUtf8() {
    return array(
501
502
503
      array(chr(0x97), 'Windows-1252', '—'),
      array(chr(0x99), 'Windows-1252', '™'),
      array(chr(0x80), 'Windows-1252', '€'),
504
505
506
    );
  }

507
}