UnicodeTest.php 17 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
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::setStatus() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. In Drupal 9 there will be no way to set the status and in Drupal 8 this ability has been removed because mb_*() functions are supplied using Symfony's polyfill. See https://www.drupal.org/node/2850048.
20
   */
21 22
  public function testSetStatus() {
    Unicode::setStatus(Unicode::STATUS_SINGLEBYTE);
23 24 25
  }

  /**
26
   * Tests multibyte encoding and decoding.
27 28
   *
   * @dataProvider providerTestMimeHeader
29 30
   * @covers ::mimeHeaderEncode
   * @covers ::mimeHeaderDecode
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45
   */
  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() {
46 47
    return [
      ['tést.txt', '=?UTF-8?B?dMOpc3QudHh0?='],
48
      // Simple ASCII characters.
49 50
      ['ASCII', 'ASCII'],
    ];
51 52 53
  }

  /**
54
   * Tests multibyte strtolower.
55 56
   *
   * @dataProvider providerStrtolower
57
   * @covers ::strtolower
58 59
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::strtolower() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. Use mb_strtolower() instead. See https://www.drupal.org/node/2850048.
60
   */
61
  public function testStrtolower($text, $expected) {
62 63 64 65 66 67 68 69 70
    $this->assertEquals($expected, Unicode::strtolower($text));
  }

  /**
   * Data provider for testStrtolower().
   *
   * @see testStrtolower()
   *
   * @return array
71
   *   An array containing a string and its lowercase version.
72 73
   */
  public function providerStrtolower() {
74
    return [
75 76
      ['tHe QUIcK bRoWn', 'the quick brown'],
      ['FrançAIS is ÜBER-åwesome', 'français is über-åwesome'],
77
      ['ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αβγδεζηθικλμνξοσὠ'],
78
    ];
79 80 81
  }

  /**
82
   * Tests multibyte strtoupper.
83 84
   *
   * @dataProvider providerStrtoupper
85
   * @covers ::strtoupper
86 87
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::strtoupper() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. Use mb_strtoupper() instead. See https://www.drupal.org/node/2850048.
88
   */
89
  public function testStrtoupper($text, $expected) {
90 91 92 93 94 95 96 97 98
    $this->assertEquals($expected, Unicode::strtoupper($text));
  }

  /**
   * Data provider for testStrtoupper().
   *
   * @see testStrtoupper()
   *
   * @return array
99
   *   An array containing a string and its uppercase version.
100 101
   */
  public function providerStrtoupper() {
102
    return [
103 104
      ['tHe QUIcK bRoWn', 'THE QUICK BROWN'],
      ['FrançAIS is ÜBER-åwesome', 'FRANÇAIS IS ÜBER-ÅWESOME'],
105
      ['αβγδεζηθικλμνξοσὠ', 'ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ'],
106
    ];
107 108 109
  }

  /**
110
   * Tests multibyte ucfirst.
111 112
   *
   * @dataProvider providerUcfirst
113
   * @covers ::ucfirst
114 115 116 117 118 119 120 121 122 123 124 125 126 127
   */
  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() {
128 129 130 131 132
    return [
      ['tHe QUIcK bRoWn', 'THe QUIcK bRoWn'],
      ['françAIS', 'FrançAIS'],
      ['über', 'Über'],
      ['åwesome', 'Åwesome'],
133
      // A multibyte string.
134 135
      ['σion', 'Σion'],
    ];
136 137
  }

138
  /**
139
   * Tests multibyte lcfirst.
140 141
   *
   * @dataProvider providerLcfirst
142
   * @covers ::lcfirst
143
   */
144
  public function testLcfirst($text, $expected) {
145 146 147 148 149 150 151 152 153
    $this->assertEquals($expected, Unicode::lcfirst($text));
  }

  /**
   * Data provider for testLcfirst().
   *
   * @see testLcfirst()
   *
   * @return array
154
   *   An array containing a string and its lowercase version.
155 156
   */
  public function providerLcfirst() {
157 158 159 160 161
    return [
      ['tHe QUIcK bRoWn', 'tHe QUIcK bRoWn'],
      ['FrançAIS is ÜBER-åwesome', 'françAIS is ÜBER-åwesome'],
      ['Über', 'über'],
      ['Åwesome', 'åwesome'],
162
      // Add a multibyte string.
163
      ['ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ', 'αΒΓΔΕΖΗΘΙΚΛΜΝΞΟΣὨ'],
164
    ];
165 166 167
  }

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

  /**
   * Data provider for testUcwords().
   *
   * @see testUcwords()
   *
   * @return array
183
   *   An array containing a string and its capitalized version.
184 185
   */
  public function providerUcwords() {
186 187 188 189 190
    return [
      ['tHe QUIcK bRoWn', 'THe QUIcK BRoWn'],
      ['françAIS', 'FrançAIS'],
      ['über', 'Über'],
      ['åwesome', 'Åwesome'],
191
      // Make sure we don't mangle extra spaces.
192
      ['frànçAIS is  über-åwesome', 'FrànçAIS Is  Über-Åwesome'],
193
      // Add a multibyte string.
194
      ['σion', 'Σion'],
195
    ];
196 197
  }

198
  /**
199
   * Tests multibyte strlen.
200 201
   *
   * @dataProvider providerStrlen
202
   * @covers ::strlen
203 204
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::strlen() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. Use mb_strlen() instead. See https://www.drupal.org/node/2850048.
205 206 207 208 209 210 211 212 213 214 215 216 217 218
   */
  public function testStrlen($text, $expected) {
    $this->assertEquals($expected, Unicode::strlen($text));
  }

  /**
   * Data provider for testStrlen().
   *
   * @see testStrlen()
   *
   * @return array
   *   An array containing a string and its length.
   */
  public function providerStrlen() {
219 220 221 222 223
    return [
      ['tHe QUIcK bRoWn', 15],
      ['ÜBER-åwesome', 12],
      ['以呂波耳・ほへとち。リヌルヲ。', 15],
    ];
224 225 226
  }

  /**
227
   * Tests multibyte substr.
228 229
   *
   * @dataProvider providerSubstr
230
   * @covers ::substr
231 232
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::substr() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. Use mb_substr() instead. See https://www.drupal.org/node/2850048.
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
   */
  public function testSubstr($text, $start, $length, $expected) {
    $this->assertEquals($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() {
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
    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'],
    ];
278 279 280
  }

  /**
281
   * Tests multibyte truncate.
282 283
   *
   * @dataProvider providerTruncate
284
   * @covers ::truncate
285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303
   */
  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() {
304
    $tests = [
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
      ['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],
    ];
350

351
    // Test truncate on text with multiple lines.
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
    $multi_line = <<<EOF
This is a text that spans multiple lines.
Line 2 goes here.
EOF;
    $multi_line_wordsafe = <<<EOF
This is a text that spans multiple lines.
Line 2
EOF;
    $multi_line_non_wordsafe = <<<EOF
This is a text that spans multiple lines.
Line 2 go
EOF;
    $tests[] = [$multi_line, 51, $multi_line_wordsafe, TRUE];
    $tests[] = [$multi_line, 51, $multi_line_non_wordsafe, FALSE];

    return $tests;
368 369
  }

370
  /**
371 372 373 374
   * Tests multibyte truncate bytes.
   *
   * @dataProvider providerTestTruncateBytes
   * @covers ::truncateBytes
375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394
   *
   * @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() {
395
    return [
396
      // String shorter than max length.
397
      ['Short string', 42, 'Short string'],
398
      // Simple string longer than max length.
399
      ['Longer string than previous.', 10, 'Longer str'],
400
      // Unicode.
401 402
      ['以呂波耳・ほへとち。リヌルヲ。', 10, '以呂波'],
    ];
403 404 405
  }

  /**
406 407 408 409
   * Tests UTF-8 validation.
   *
   * @dataProvider providerTestValidateUtf8
   * @covers ::validateUtf8
410 411 412
   *
   * @param string $text
   *   The text to validate.
413
   * @param bool $expected
414 415 416 417 418 419 420 421 422 423 424
   *   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().
   *
425 426
   * Invalid UTF-8 examples sourced from http://stackoverflow.com/a/11709412/109119.
   *
427 428 429 430 431
   * @return array
   *   An array of arrays, each containing the parameters for
   *   self::testValidateUtf8().
   */
  public function providerTestValidateUtf8() {
432
    return [
433
      // Empty string.
434
      ['', TRUE, 'An empty string did not validate.'],
435
      // Simple text string.
436
      ['Simple text.', TRUE, 'A simple ASCII text string did not validate.'],
437
      // Invalid UTF-8, overlong 5 byte encoding.
438
      [chr(0xF8) . chr(0x80) . chr(0x80) . chr(0x80) . chr(0x80), FALSE, 'Invalid UTF-8 was validated.'],
439
      // High code-point without trailing characters.
440 441
      [chr(0xD0) . chr(0x01), FALSE, 'Invalid UTF-8 was validated.'],
    ];
442 443 444
  }

  /**
445 446 447 448
   * Tests UTF-8 conversion.
   *
   * @dataProvider providerTestConvertToUtf8
   * @covers ::convertToUtf8
449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
   *
   * @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
465
   *   An array of arrays, each containing the parameters to
466 467 468
   *   self::testConvertUtf8().  }
   */
  public function providerTestConvertToUtf8() {
469 470 471 472 473
    return [
      [chr(0x97), 'Windows-1252', '—'],
      [chr(0x99), 'Windows-1252', '™'],
      [chr(0x80), 'Windows-1252', '€'],
    ];
474 475
  }

476 477 478 479 480
  /**
   * Tests multibyte strpos.
   *
   * @dataProvider providerStrpos
   * @covers ::strpos
481 482
   * @group legacy
   * @expectedDeprecation \Drupal\Component\Utility\Unicode::strpos() is deprecated in Drupal 8.6.0 and will be removed before Drupal 9.0.0. Use mb_strpos() instead. See https://www.drupal.org/node/2850048.
483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500
   */
  public function testStrpos($haystack, $needle, $offset, $expected) {
    $this->assertEquals($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() {
501 502 503 504 505 506 507 508 509 510 511 512
    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],
    ];
513 514
  }

515
}