mundschenk-at /
php-typography
We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.
Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
| 1 | <?php |
||
| 40 | class Text_Parser_Test extends PHP_Typography_Testcase { |
||
| 41 | /** |
||
| 42 | * The Text_Parser fixture. |
||
| 43 | * |
||
| 44 | * @var Text_Parser |
||
| 45 | */ |
||
| 46 | protected $parser; |
||
| 47 | |||
| 48 | /** |
||
| 49 | * Sets up the fixture, for example, opens a network connection. |
||
| 50 | * This method is called before a test is executed. |
||
| 51 | */ |
||
| 52 | protected function setUp() { |
||
| 53 | $this->parser = new \PHP_Typography\Text_Parser(); |
||
| 54 | } |
||
| 55 | |||
| 56 | /** |
||
| 57 | * Tears down the fixture, for example, closes a network connection. |
||
| 58 | * This method is called after a test is executed. |
||
| 59 | */ |
||
| 60 | protected function tearDown() { |
||
| 61 | } |
||
| 62 | |||
| 63 | /** |
||
| 64 | * Test constructor. |
||
| 65 | * |
||
| 66 | * @covers ::__construct |
||
| 67 | */ |
||
| 68 | public function test_constructor() { |
||
| 69 | $parser = new Text_Parser(); |
||
| 70 | |||
| 71 | $this->assertAttributeCount( 0, 'text', $parser ); |
||
| 72 | $this->assertAttributeEmpty( 'current_strtoupper', $parser ); |
||
| 73 | } |
||
| 74 | |||
| 75 | /** |
||
| 76 | * Test load. |
||
| 77 | * |
||
| 78 | * @covers ::load |
||
| 79 | * @covers ::tokenize |
||
| 80 | * @covers ::parse_ambiguous_token |
||
| 81 | * @covers ::is_preceeded_by |
||
| 82 | * @covers ::is_not_preceeded_by |
||
| 83 | * |
||
| 84 | * @uses ::get_all |
||
| 85 | */ |
||
| 86 | public function test_load() { |
||
| 87 | $too_long = 'A really long string with a word that is wwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwway too long.'; |
||
| 88 | $still_too_long = 'A really long string with a word that is aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaalmost too long.'; |
||
| 89 | $almost_too_long = 'A really long string with a word that is aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaalmost too long.'; |
||
| 90 | |||
| 91 | $parser = $this->parser; |
||
| 92 | |||
| 93 | // Security check. |
||
| 94 | $this->assertFalse( $parser->load( $too_long ) ); |
||
| 95 | $this->assertFalse( $parser->load( $still_too_long ) ); |
||
| 96 | $this->assertTrue( $parser->load( $almost_too_long ) ); |
||
| 97 | |||
| 98 | $interesting = 'Quoth the raven, "nevermore"! Äöüß?'; |
||
| 99 | $this->assertTrue( $parser->load( $interesting ) ); |
||
| 100 | |||
| 101 | $tokens = $parser->get_all(); |
||
| 102 | |||
| 103 | $this->assertCount( 13, $tokens ); |
||
| 104 | $this->assertArraySubset( [ |
||
| 105 | 0 => new Token( 'Quoth', Token::WORD ), |
||
| 106 | ], $tokens ); |
||
| 107 | $this->assertArraySubset( [ |
||
| 108 | 5 => new Token( ',', Token::PUNCTUATION ), |
||
| 109 | ], $tokens ); |
||
| 110 | $this->assertArraySubset( [ |
||
| 111 | 11 => new Token( 'Äöüß', Token::WORD ), |
||
| 112 | ], $tokens ); |
||
| 113 | |||
| 114 | return $parser; |
||
| 115 | } |
||
| 116 | |||
| 117 | /** |
||
| 118 | * Test load with email address. |
||
| 119 | * |
||
| 120 | * @covers ::load |
||
| 121 | * @covers ::tokenize |
||
| 122 | * @covers ::parse_ambiguous_token |
||
| 123 | * @covers ::is_preceeded_by |
||
| 124 | * @covers ::is_not_preceeded_by |
||
| 125 | * |
||
| 126 | * @uses ::get_all |
||
| 127 | */ |
||
| 128 | public function test_load_email() { |
||
| 129 | $parser = $this->parser; |
||
| 130 | |||
| 131 | $string = 'Quoth the raven, "nevermore"! Please mail to [email protected].'; |
||
| 132 | $this->assertTrue( $parser->load( $string ) ); |
||
| 133 | |||
| 134 | $tokens = $parser->get_all(); |
||
| 135 | $this->assertCount( 19, $tokens ); |
||
| 136 | |||
| 137 | $this->assertArraySubset( [ |
||
| 138 | 0 => new Token( 'Quoth', Token::WORD ), |
||
| 139 | ], $tokens ); |
||
| 140 | $this->assertArraySubset( [ |
||
| 141 | 5 => new Token( ',', Token::PUNCTUATION ), |
||
| 142 | ], $tokens ); |
||
| 143 | $this->assertArraySubset( [ |
||
| 144 | 17 => new Token( '[email protected]', Token::OTHER ), |
||
| 145 | ], $tokens ); |
||
| 146 | |||
| 147 | return $parser; |
||
| 148 | } |
||
| 149 | |||
| 150 | /** |
||
| 151 | * Test load with URL. |
||
| 152 | * |
||
| 153 | * @covers ::load |
||
| 154 | * @covers ::tokenize |
||
| 155 | * @covers ::parse_ambiguous_token |
||
| 156 | * @covers ::is_preceeded_by |
||
| 157 | * @covers ::is_not_preceeded_by |
||
| 158 | * |
||
| 159 | * @uses ::get_all |
||
| 160 | */ |
||
| 161 | public function test_load_url() { |
||
| 162 | $parser = $this->parser; |
||
| 163 | |||
| 164 | $string = 'Quoth the raven, "nevermore"! Please open http://example.org or foo:WordPress or foo:W@rdPress or @example or @:@:@:risk.'; |
||
| 165 | $this->assertTrue( $parser->load( $string ) ); |
||
| 166 | |||
| 167 | $tokens = $parser->get_all(); |
||
| 168 | $this->assertCount( 33, $tokens ); |
||
| 169 | |||
| 170 | $this->assertArraySubset( [ |
||
| 171 | 0 => new Token( 'Quoth', Token::WORD ), |
||
| 172 | ], $tokens ); |
||
| 173 | $this->assertArraySubset( [ |
||
| 174 | 5 => new Token( ',', Token::PUNCTUATION ), |
||
| 175 | ], $tokens ); |
||
| 176 | $this->assertArraySubset( [ |
||
| 177 | 15 => new Token( 'http://example.org', Token::OTHER ), |
||
| 178 | ], $tokens ); |
||
| 179 | $this->assertArraySubset( [ |
||
| 180 | 19 => new Token( 'foo:WordPress', Token::OTHER ), |
||
| 181 | ], $tokens ); |
||
| 182 | $this->assertArraySubset( [ |
||
| 183 | 23 => new Token( 'foo:W@rdPress', Token::OTHER ), |
||
| 184 | ], $tokens ); |
||
| 185 | $this->assertArraySubset( [ |
||
| 186 | 27 => new Token( '@example', Token::OTHER ), |
||
| 187 | ], $tokens ); |
||
| 188 | $this->assertArraySubset( [ |
||
| 189 | 31 => new Token( '@:@:@:risk', Token::OTHER ), |
||
| 190 | ], $tokens ); |
||
| 191 | |||
| 192 | return $parser; |
||
| 193 | } |
||
| 194 | |||
| 195 | /** |
||
| 196 | * Test load with a compound word. |
||
| 197 | * |
||
| 198 | * @covers ::load |
||
| 199 | * @covers ::tokenize |
||
| 200 | * @covers ::parse_ambiguous_token |
||
| 201 | * @covers ::is_preceeded_by |
||
| 202 | * @covers ::is_not_preceeded_by |
||
| 203 | * |
||
| 204 | * @uses ::get_all |
||
| 205 | */ |
||
| 206 | public function test_load_compound_word() { |
||
| 207 | $parser = $this->parser; |
||
| 208 | |||
| 209 | $string = 'Some don\'t trust the captain-owner.'; |
||
| 210 | $this->assertTrue( $parser->load( $string ) ); |
||
| 211 | |||
| 212 | $tokens = $parser->get_all(); |
||
| 213 | $this->assertCount( 10, $tokens ); |
||
| 214 | |||
| 215 | $this->assertArraySubset( [ |
||
| 216 | 0 => new Token( 'Some', Token::WORD ), |
||
| 217 | ], $tokens ); |
||
| 218 | $this->assertArraySubset( [ |
||
| 219 | 2 => new Token( "don't", Token::OTHER ), |
||
| 220 | ], $tokens ); |
||
| 221 | $this->assertArraySubset( [ |
||
| 222 | 8 => new Token( 'captain-owner', Token::WORD ), |
||
| 223 | ], $tokens ); |
||
| 224 | |||
| 225 | return $parser; |
||
| 226 | } |
||
| 227 | |||
| 228 | /** |
||
| 229 | * Test load with an invalid encoding. |
||
| 230 | * |
||
| 231 | * @covers ::load |
||
| 232 | */ |
||
| 233 | public function test_load_invalid_encoding() { |
||
| 234 | $string = mb_convert_encoding( 'Ein längerer String im falschen Zeichensatz', 'ISO-8859-2' ); |
||
| 235 | $parser = $this->parser; |
||
| 236 | |||
| 237 | $this->assertFalse( $parser->load( $string ) ); |
||
| 238 | } |
||
| 239 | |||
| 240 | /** |
||
| 241 | * Test load with something that is not a string. |
||
| 242 | * |
||
| 243 | * @covers ::load |
||
| 244 | */ |
||
| 245 | public function test_load_not_a_string() { |
||
| 246 | $parser = $this->parser; |
||
| 247 | |||
| 248 | $this->assertFalse( $parser->load( [] ) ); |
||
| 249 | } |
||
| 250 | |||
| 251 | /** |
||
| 252 | * Test reload. |
||
| 253 | * |
||
| 254 | * @covers ::reload |
||
| 255 | * |
||
| 256 | * @depends test_load |
||
| 257 | * @uses ::clear |
||
| 258 | * @uses ::get_all |
||
| 259 | * @uses ::is_not_preceeded_by |
||
| 260 | * @uses ::is_preceeded_by |
||
| 261 | * @uses ::load |
||
| 262 | * @uses ::parse_ambiguous_token |
||
| 263 | * @uses ::tokenize |
||
| 264 | * @uses ::unload |
||
| 265 | * @uses ::update |
||
| 266 | |||
| 267 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 268 | */ |
||
| 269 | public function test_reload( Text_Parser $parser ) { |
||
| 270 | $tokens = $parser->get_all(); |
||
| 271 | $tokens[12] = $tokens[12]->with_value( '' ); // ?. |
||
| 272 | $tokens[11] = $tokens[11]->with_value( '' ); // Äöüß |
||
| 273 | $tokens[10] = $tokens[10]->with_value( '' ); // |
||
| 274 | $tokens[9] = $tokens[9]->with_value( $tokens[9]->value . '!' ); |
||
| 275 | $parser->update( $tokens ); |
||
| 276 | |||
| 277 | $this->assertTrue( $parser->reload() ); |
||
| 278 | $this->assertSame( 'Quoth the raven, "nevermore"!!', $parser->unload() ); |
||
| 279 | |||
| 280 | return $parser; |
||
| 281 | } |
||
| 282 | |||
| 283 | /** |
||
| 284 | * Test unload. |
||
| 285 | * |
||
| 286 | * @covers ::unload |
||
| 287 | * |
||
| 288 | * @uses ::clear |
||
| 289 | * @uses ::is_not_preceeded_by |
||
| 290 | * @uses ::is_preceeded_by |
||
| 291 | * @uses ::load |
||
| 292 | * @uses ::parse_ambiguous_token |
||
| 293 | * @uses ::tokenize |
||
| 294 | */ |
||
| 295 | public function test_unload() { |
||
| 296 | $interesting = 'Quoth the raven, "nevermore"! Äöüß?'; |
||
| 297 | $parser = $this->parser; |
||
| 298 | |||
| 299 | $this->assertTrue( $parser->load( $interesting ) ); |
||
| 300 | |||
| 301 | $result = $parser->unload(); |
||
| 302 | |||
| 303 | $this->assertSame( $interesting, $result ); |
||
| 304 | $this->assertNotSame( $result, $parser->unload() ); // the parser is empty now. |
||
| 305 | } |
||
| 306 | |||
| 307 | /** |
||
| 308 | * Test clear. |
||
| 309 | * |
||
| 310 | * @covers ::clear |
||
| 311 | * |
||
| 312 | * @uses ::get_all |
||
| 313 | * @uses ::is_not_preceeded_by |
||
| 314 | * @uses ::is_preceeded_by |
||
| 315 | * @uses ::load |
||
| 316 | * @uses ::parse_ambiguous_token |
||
| 317 | * @uses ::tokenize |
||
| 318 | */ |
||
| 319 | public function test_clear() { |
||
| 320 | $parser = $this->parser; |
||
| 321 | $interesting = 'Quoth the raven, "nevermore"!'; |
||
| 322 | |||
| 323 | $this->assertTrue( $parser->load( $interesting ) ); |
||
| 324 | $this->assertGreaterThan( 0, count( $parser->get_all() ) ); |
||
| 325 | |||
| 326 | $parser->clear(); |
||
| 327 | $this->assertCount( 0, $parser->get_all() ); |
||
| 328 | } |
||
| 329 | |||
| 330 | /** |
||
| 331 | * Test update. |
||
| 332 | * |
||
| 333 | * @covers ::update |
||
| 334 | * |
||
| 335 | * @uses ::clear |
||
| 336 | * @uses ::get_all |
||
| 337 | * @uses ::is_not_preceeded_by |
||
| 338 | * @uses ::is_preceeded_by |
||
| 339 | * @uses ::load |
||
| 340 | * @uses ::parse_ambiguous_token |
||
| 341 | * @uses ::tokenize |
||
| 342 | * @uses ::unload |
||
| 343 | */ |
||
| 344 | public function test_update() { |
||
| 345 | $parser = $this->parser; |
||
| 346 | $interesting = 'Quoth the raven, "nevermore"! Äöüß?'; |
||
| 347 | $this->assertTrue( $parser->load( $interesting ) ); |
||
| 348 | |||
| 349 | $tokens = $parser->get_all(); |
||
| 350 | $tokens[12] = $tokens[12]->with_value( '' ); // ?. |
||
| 351 | $tokens[11] = $tokens[11]->with_value( '' ); // Äöüß |
||
| 352 | $tokens[10] = $tokens[10]->with_value( '' ); // |
||
| 353 | $tokens[9] = $tokens[9]->with_value( $tokens[9]->value . '!' ); |
||
| 354 | $parser->update( $tokens ); |
||
| 355 | |||
| 356 | $this->assertSame( 'Quoth the raven, "nevermore"!!', $parser->unload() ); |
||
| 357 | |||
| 358 | return $parser; |
||
| 359 | } |
||
| 360 | |||
| 361 | /** |
||
| 362 | * Test get_all. |
||
| 363 | * |
||
| 364 | * @covers ::get_all |
||
| 365 | * |
||
| 366 | * @uses ::load |
||
| 367 | * @uses ::is_not_preceeded_by |
||
| 368 | * @uses ::is_preceeded_by |
||
| 369 | * @uses ::parse_ambiguous_token |
||
| 370 | * @uses ::tokenize |
||
| 371 | */ |
||
| 372 | public function test_get_all() { |
||
| 373 | $interesting = 'Quoth the raven, "nevermore"!'; |
||
| 374 | $parser = $this->parser; |
||
| 375 | $this->assertTrue( $parser->load( $interesting ) ); |
||
| 376 | |||
| 377 | $tokens = $parser->get_all(); |
||
| 378 | $this->assertCount( 10, $tokens ); |
||
| 379 | |||
| 380 | return $parser; |
||
| 381 | } |
||
| 382 | |||
| 383 | /** |
||
| 384 | * Test get_spaces. |
||
| 385 | * |
||
| 386 | * @covers ::get_spaces |
||
| 387 | * @depends test_get_all |
||
| 388 | * |
||
| 389 | * @uses ::get_type |
||
| 390 | * |
||
| 391 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 392 | */ |
||
| 393 | public function test_get_spaces( Text_Parser $parser ) { |
||
| 394 | $tokens = $parser->get_spaces(); |
||
| 395 | $this->assertCount( 3, $tokens ); |
||
| 396 | |||
| 397 | return $parser; |
||
| 398 | } |
||
| 399 | |||
| 400 | /** |
||
| 401 | * Test get_punctuation. |
||
| 402 | * |
||
| 403 | * @covers ::get_punctuation |
||
| 404 | * @depends test_get_all |
||
| 405 | * |
||
| 406 | * @uses ::get_type |
||
| 407 | * |
||
| 408 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 409 | */ |
||
| 410 | public function test_get_punctuation( Text_Parser $parser ) { |
||
| 411 | $tokens = $parser->get_punctuation(); |
||
| 412 | $this->assertCount( 3, $tokens ); |
||
| 413 | |||
| 414 | return $parser; |
||
| 415 | } |
||
| 416 | |||
| 417 | /** |
||
| 418 | * Test get_words. |
||
| 419 | * |
||
| 420 | * @covers ::get_words |
||
| 421 | * @depends test_get_all |
||
| 422 | * |
||
| 423 | * @uses ::conforms_to_caps_policy |
||
| 424 | * @uses ::conforms_to_compounds_policy |
||
| 425 | * @uses ::conforms_to_letters_policy |
||
| 426 | * @uses ::check_policy |
||
| 427 | * @uses ::get_type |
||
| 428 | * @uses ::is_preceeded_by |
||
| 429 | * @uses ::load |
||
| 430 | * @uses ::parse_ambiguous_token |
||
| 431 | * @uses ::tokenize |
||
| 432 | * |
||
| 433 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 434 | */ |
||
| 435 | public function test_get_words( Text_Parser $parser ) { |
||
| 436 | $tokens = $parser->get_words(); |
||
| 437 | $this->assertCount( 4, $tokens ); |
||
| 438 | |||
| 439 | $parser->load( 'A few m1xed W0RDS.' ); |
||
| 440 | $tokens = $parser->get_words( Text_Parser::REQUIRE_ALL_LETTERS, Text_Parser::NO_ALL_CAPS ); |
||
| 441 | $this->assertCount( 1, $tokens ); |
||
| 442 | $this->assertContains( new Token( 'few', Token::WORD ), $tokens, '', false, false, true ); |
||
| 443 | |||
| 444 | $tokens = $parser->get_words( Text_Parser::ALLOW_ALL_LETTERS, Text_Parser::NO_ALL_CAPS ); |
||
| 445 | $this->assertCount( 2, $tokens ); |
||
| 446 | $this->assertContains( new Token( 'few', Token::WORD ), $tokens, '', false, false, true ); |
||
| 447 | $this->assertContains( new Token( 'm1xed', Token::WORD ), $tokens, '', false, false, true ); |
||
| 448 | |||
| 449 | $tokens = $parser->get_words( Text_Parser::NO_ALL_LETTERS, Text_Parser::NO_ALL_CAPS ); |
||
| 450 | $this->assertCount( 1, $tokens ); |
||
| 451 | $this->assertContains( new Token( 'm1xed', Token::WORD ), $tokens, '', false, false, true ); |
||
| 452 | |||
| 453 | $tokens = $parser->get_words( Text_Parser::REQUIRE_ALL_LETTERS, Text_Parser::ALLOW_ALL_CAPS ); |
||
| 454 | $this->assertCount( 2, $tokens ); |
||
| 455 | $this->assertContains( new Token( 'A', Token::WORD ), $tokens, '', false, false, true ); |
||
| 456 | $this->assertContains( new Token( 'few', Token::WORD ), $tokens, '', false, false, true ); |
||
| 457 | |||
| 458 | $tokens = $parser->get_words( Text_Parser::ALLOW_ALL_LETTERS, Text_Parser::ALLOW_ALL_CAPS ); |
||
| 459 | $this->assertCount( 4, $tokens ); |
||
| 460 | $this->assertContains( new Token( 'A', Token::WORD ), $tokens, '', false, false, true ); |
||
| 461 | $this->assertContains( new Token( 'few', Token::WORD ), $tokens, '', false, false, true ); |
||
| 462 | $this->assertContains( new Token( 'm1xed', Token::WORD ), $tokens, '', false, false, true ); |
||
| 463 | $this->assertContains( new Token( 'W0RDS', Token::WORD ), $tokens, '', false, false, true ); |
||
| 464 | |||
| 465 | $tokens = $parser->get_words( Text_Parser::NO_ALL_LETTERS, Text_Parser::ALLOW_ALL_CAPS ); |
||
| 466 | $this->assertCount( 2, $tokens ); |
||
| 467 | $this->assertContains( new Token( 'm1xed', Token::WORD ), $tokens, '', false, false, true ); |
||
| 468 | $this->assertContains( new Token( 'W0RDS', Token::WORD ), $tokens, '', false, false, true ); |
||
| 469 | |||
| 470 | $tokens = $parser->get_words( Text_Parser::REQUIRE_ALL_LETTERS, Text_Parser::REQUIRE_ALL_CAPS ); |
||
| 471 | $this->assertCount( 1, $tokens ); |
||
| 472 | $this->assertContains( new Token( 'A', Token::WORD ), $tokens, '', false, false, true ); |
||
| 473 | |||
| 474 | $tokens = $parser->get_words( Text_Parser::ALLOW_ALL_LETTERS, Text_Parser::REQUIRE_ALL_CAPS ); |
||
| 475 | $this->assertCount( 2, $tokens ); |
||
| 476 | $this->assertContains( new Token( 'A', Token::WORD ), $tokens, '', false, false, true ); |
||
| 477 | $this->assertContains( new Token( 'W0RDS', Token::WORD ), $tokens, '', false, false, true ); |
||
| 478 | |||
| 479 | $tokens = $parser->get_words( Text_Parser::NO_ALL_LETTERS, Text_Parser::REQUIRE_ALL_CAPS ); |
||
| 480 | $this->assertCount( 1, $tokens ); |
||
| 481 | $this->assertContains( new Token( 'W0RDS', Token::WORD ), $tokens, '', false, false, true ); |
||
| 482 | } |
||
| 483 | |||
| 484 | /** |
||
| 485 | * Providate data for testing conforms_to_letters_policy. |
||
| 486 | * |
||
| 487 | * @return array |
||
| 488 | */ |
||
| 489 | public function provide_conforms_to_letters_policy_data() { |
||
| 490 | return [ |
||
| 491 | [ 'simple', Token::WORD, Text_Parser::ALLOW_ALL_LETTERS, true ], |
||
| 492 | [ 'SIMPLE', Token::WORD, Text_Parser::ALLOW_ALL_LETTERS, true ], |
||
| 493 | [ 'simple', Token::WORD, Text_Parser::NO_ALL_LETTERS, false ], |
||
| 494 | [ 'simple99', Token::WORD, Text_Parser::NO_ALL_LETTERS, true ], |
||
| 495 | [ 'simple', Token::WORD, Text_Parser::REQUIRE_ALL_LETTERS, true ], |
||
| 496 | [ 'SIMPLE', Token::WORD, Text_Parser::REQUIRE_ALL_LETTERS, true ], |
||
| 497 | [ 'SIMPLE99', Token::WORD, Text_Parser::REQUIRE_ALL_LETTERS, false ], |
||
| 498 | [ 'simple99', Token::WORD, Text_Parser::ALLOW_ALL_LETTERS, true ], |
||
| 499 | [ 'SIM-PLE', Token::WORD, Text_Parser::ALLOW_ALL_LETTERS, true ], |
||
| 500 | [ 'sim-ple', Token::WORD, Text_Parser::NO_ALL_LETTERS, true ], |
||
| 501 | [ 'SIM-PLE', Token::WORD, Text_Parser::NO_ALL_LETTERS, true ], |
||
| 502 | [ 'sim-ple', Token::WORD, Text_Parser::REQUIRE_ALL_LETTERS, false ], |
||
| 503 | [ 'SIM-PLE', Token::WORD, Text_Parser::REQUIRE_ALL_LETTERS, false ], |
||
| 504 | ]; |
||
| 505 | } |
||
| 506 | |||
| 507 | /** |
||
| 508 | * Test conforms_to_letters_policy. |
||
| 509 | * |
||
| 510 | * @covers ::conforms_to_letters_policy |
||
| 511 | * @covers ::check_policy |
||
| 512 | * @dataProvider provide_conforms_to_letters_policy_data |
||
| 513 | * |
||
| 514 | * @uses ::load |
||
| 515 | * @uses ::is_preceeded_by |
||
| 516 | * @uses ::parse_ambiguous_token |
||
| 517 | * @uses ::tokenize |
||
| 518 | * |
||
| 519 | * @param string $value Token value. |
||
| 520 | * @param int $type Token type. |
||
| 521 | * @param int $policy Letters policy. |
||
| 522 | * @param bool $result Expected result. |
||
| 523 | */ |
||
| 524 | public function test_conforms_to_letters_policy( $value, $type, $policy, $result ) { |
||
| 525 | $parser = $this->parser; |
||
| 526 | $token = new Token( $value, $type ); |
||
| 527 | |||
| 528 | $this->assertSame( $result, $this->invokeMethod( $parser, 'conforms_to_letters_policy', [ $token, $policy ] ) ); |
||
| 529 | } |
||
| 530 | |||
| 531 | /** |
||
| 532 | * Providate data for testing conforms_to_caps_policy. |
||
| 533 | * |
||
| 534 | * @return array |
||
| 535 | */ |
||
| 536 | public function provide_conforms_to_caps_policy_data() { |
||
| 537 | return [ |
||
| 538 | [ 'simple', Token::WORD, Text_Parser::ALLOW_ALL_CAPS, true ], |
||
| 539 | [ 'SIMPLE', Token::WORD, Text_Parser::ALLOW_ALL_CAPS, true ], |
||
| 540 | [ 'simple', Token::WORD, Text_Parser::NO_ALL_CAPS, true ], |
||
| 541 | [ 'simple99', Token::WORD, Text_Parser::NO_ALL_CAPS, true ], |
||
| 542 | [ 'simple', Token::WORD, Text_Parser::REQUIRE_ALL_CAPS, false ], |
||
| 543 | [ 'SIMPLE', Token::WORD, Text_Parser::REQUIRE_ALL_CAPS, true ], |
||
| 544 | [ 'SIMPLE99', Token::WORD, Text_Parser::REQUIRE_ALL_CAPS, true ], |
||
| 545 | [ 'simple99', Token::WORD, Text_Parser::ALLOW_ALL_CAPS, true ], |
||
| 546 | [ 'SIM-PLE', Token::WORD, Text_Parser::ALLOW_ALL_CAPS, true ], |
||
| 547 | [ 'sim-ple', Token::WORD, Text_Parser::NO_ALL_CAPS, true ], |
||
| 548 | [ 'SIM-PLE', Token::WORD, Text_Parser::NO_ALL_CAPS, false ], |
||
| 549 | [ 'sim-ple', Token::WORD, Text_Parser::REQUIRE_ALL_CAPS, false ], |
||
| 550 | [ 'SIM-PLE', Token::WORD, Text_Parser::REQUIRE_ALL_CAPS, true ], |
||
| 551 | ]; |
||
| 552 | } |
||
| 553 | |||
| 554 | /** |
||
| 555 | * Test conforms_to_caps_policy. |
||
| 556 | * |
||
| 557 | * @covers ::conforms_to_caps_policy |
||
| 558 | * @covers ::check_policy |
||
| 559 | * @dataProvider provide_conforms_to_caps_policy_data |
||
| 560 | * |
||
| 561 | * @uses ::load |
||
| 562 | * @uses ::is_preceeded_by |
||
| 563 | * @uses ::parse_ambiguous_token |
||
| 564 | * @uses ::tokenize |
||
| 565 | * |
||
| 566 | * @param string $value Token value. |
||
| 567 | * @param int $type Token type. |
||
| 568 | * @param int $policy All caps policy. |
||
| 569 | * @param bool $result Expected result. |
||
| 570 | */ |
||
| 571 | public function test_conforms_to_caps_policy( $value, $type, $policy, $result ) { |
||
| 572 | $parser = $this->parser; |
||
| 573 | $parser->load( $value ); // Ensure that encoding can be determined. |
||
| 574 | |||
| 575 | $token = new Token( $value, $type ); |
||
| 576 | |||
| 577 | $this->assertSame( $result, $this->invokeMethod( $parser, 'conforms_to_caps_policy', [ $token, $policy ] ) ); |
||
| 578 | } |
||
| 579 | |||
| 580 | /** |
||
| 581 | * Providate data for testing conforms_to_compounds_policy. |
||
| 582 | * |
||
| 583 | * @return array |
||
| 584 | */ |
||
| 585 | public function provide_conforms_to_compounds_policy() { |
||
| 586 | return [ |
||
| 587 | [ 'simple', Token::WORD, Text_Parser::ALLOW_COMPOUNDS, true ], |
||
| 588 | [ 'SIMPLE', Token::WORD, Text_Parser::ALLOW_COMPOUNDS, true ], |
||
| 589 | [ 'simple', Token::WORD, Text_Parser::NO_COMPOUNDS, true ], |
||
| 590 | [ 'simple99', Token::WORD, Text_Parser::NO_COMPOUNDS, true ], |
||
| 591 | [ 'simple', Token::WORD, Text_Parser::REQUIRE_COMPOUNDS, false ], |
||
| 592 | [ 'SIMPLE', Token::WORD, Text_Parser::REQUIRE_COMPOUNDS, false ], |
||
| 593 | [ 'SIMPLE99', Token::WORD, Text_Parser::REQUIRE_COMPOUNDS, false ], |
||
| 594 | [ 'simple99', Token::WORD, Text_Parser::ALLOW_COMPOUNDS, true ], |
||
| 595 | [ 'SIM-PLE', Token::WORD, Text_Parser::ALLOW_COMPOUNDS, true ], |
||
| 596 | [ 'sim-ple', Token::WORD, Text_Parser::NO_COMPOUNDS, false ], |
||
| 597 | [ 'SIM-PLE', Token::WORD, Text_Parser::NO_COMPOUNDS, false ], |
||
| 598 | [ 'sim-ple', Token::WORD, Text_Parser::REQUIRE_COMPOUNDS, true ], |
||
| 599 | [ 'SIM-PLE', Token::WORD, Text_Parser::REQUIRE_COMPOUNDS, true ], |
||
| 600 | ]; |
||
| 601 | } |
||
| 602 | |||
| 603 | /** |
||
| 604 | * Test conforms_to_compounds_policy. |
||
| 605 | * |
||
| 606 | * @covers ::conforms_to_compounds_policy |
||
| 607 | * @covers ::check_policy |
||
| 608 | * @dataProvider provide_conforms_to_compounds_policy |
||
| 609 | * |
||
| 610 | * @uses ::load |
||
| 611 | * @uses ::is_preceeded_by |
||
| 612 | * @uses ::parse_ambiguous_token |
||
| 613 | * @uses ::tokenize |
||
| 614 | * |
||
| 615 | * @param string $value Token value. |
||
| 616 | * @param int $type Token type. |
||
| 617 | * @param int $policy Compounds policy. |
||
| 618 | * @param bool $result Expected result. |
||
| 619 | */ |
||
| 620 | public function test_conforms_to_compounds_policy( $value, $type, $policy, $result ) { |
||
| 621 | $parser = $this->parser; |
||
| 622 | $parser->load( $value ); // Ensure that encoding can be determined. |
||
| 623 | |||
| 624 | $token = new Token( $value, $type ); |
||
| 625 | |||
| 626 | $this->assertSame( $result, $this->invokeMethod( $parser, 'conforms_to_compounds_policy', [ $token, $policy ] ) ); |
||
| 627 | } |
||
| 628 | |||
| 629 | /** |
||
| 630 | * Test get_words. |
||
| 631 | * |
||
| 632 | * @covers ::get_words |
||
| 633 | * @depends test_get_all |
||
| 634 | * |
||
| 635 | * @uses ::clear |
||
| 636 | * @uses ::is_preceeded_by |
||
| 637 | * @uses ::load |
||
| 638 | * @uses ::parse_ambiguous_token |
||
| 639 | * @uses ::tokenize |
||
| 640 | * @uses ::unload |
||
| 641 | * |
||
| 642 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 643 | */ |
||
| 644 | public function test_get_words_unloaded( Text_Parser $parser ) { |
||
| 645 | $parser->load( 'A few m1xed W0RDS.' ); |
||
| 646 | $parser->unload(); |
||
| 647 | |||
| 648 | $tokens = $parser->get_words( Text_Parser::REQUIRE_ALL_LETTERS, Text_Parser::NO_ALL_CAPS ); |
||
| 649 | $this->assertCount( 0, $tokens ); |
||
| 650 | $this->assertSame( [], $tokens ); |
||
| 651 | |||
| 652 | return $parser; |
||
| 653 | } |
||
| 654 | |||
| 655 | /** |
||
| 656 | * Test get_other. |
||
| 657 | * |
||
| 658 | * @covers ::get_other |
||
| 659 | * @depends test_get_all |
||
| 660 | * |
||
| 661 | * @uses ::get_type |
||
| 662 | * |
||
| 663 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 664 | */ |
||
| 665 | public function test_get_other( Text_Parser $parser ) { |
||
| 666 | $tokens = $parser->get_other(); |
||
| 667 | $this->assertCount( 0, $tokens ); |
||
| 668 | |||
| 669 | return $parser; |
||
| 670 | } |
||
| 671 | |||
| 672 | /** |
||
| 673 | * Test get_type. |
||
| 674 | * |
||
| 675 | * @covers ::get_type |
||
| 676 | * @depends test_get_all |
||
| 677 | * |
||
| 678 | * @uses ::get_all |
||
| 679 | * @uses ::is_preceeded_by |
||
| 680 | * @uses ::load |
||
| 681 | * @uses ::parse_ambiguous_token |
||
| 682 | * @uses ::tokenize |
||
| 683 | * |
||
| 684 | * @param \PHP_Typography\Text_Parser $parser The parser to use. |
||
| 685 | */ |
||
| 686 | public function test_get_type( Text_Parser $parser ) { |
||
| 687 | $parser->load( 'A few m1xed W0RDS.' ); |
||
| 688 | |||
| 689 | $words = []; |
||
| 690 | $tokens = $parser->get_all(); |
||
| 691 | foreach ( $tokens as $index => $token ) { |
||
| 692 | if ( Token::WORD === $token->type ) { |
||
| 693 | $words[ $index ] = $token; |
||
| 694 | } |
||
| 695 | } |
||
| 696 | |||
| 700 |
