Complex classes like AbstractDiff often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use AbstractDiff, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 8 | abstract class AbstractDiff |
||
| 9 | { |
||
| 10 | /** |
||
| 11 | * @var array |
||
| 12 | * |
||
| 13 | * @deprecated since 0.1.0 |
||
| 14 | */ |
||
| 15 | public static $defaultSpecialCaseTags = array('strong', 'b', 'i', 'big', 'small', 'u', 'sub', 'sup', 'strike', 's', 'p'); |
||
|
|
|||
| 16 | |||
| 17 | /** |
||
| 18 | * @var array |
||
| 19 | * |
||
| 20 | * @deprecated since 0.1.0 |
||
| 21 | */ |
||
| 22 | public static $defaultSpecialCaseChars = array('.', ',', '(', ')', '\''); |
||
| 23 | |||
| 24 | /** |
||
| 25 | * @var bool |
||
| 26 | * |
||
| 27 | * @deprecated since 0.1.0 |
||
| 28 | */ |
||
| 29 | public static $defaultGroupDiffs = true; |
||
| 30 | |||
| 31 | /** |
||
| 32 | * @var HtmlDiffConfig |
||
| 33 | */ |
||
| 34 | protected $config; |
||
| 35 | |||
| 36 | /** |
||
| 37 | * @var string |
||
| 38 | */ |
||
| 39 | protected $content; |
||
| 40 | |||
| 41 | /** |
||
| 42 | * @var string |
||
| 43 | */ |
||
| 44 | protected $oldText; |
||
| 45 | |||
| 46 | /** |
||
| 47 | * @var string |
||
| 48 | */ |
||
| 49 | protected $newText; |
||
| 50 | |||
| 51 | /** |
||
| 52 | * @var array |
||
| 53 | */ |
||
| 54 | protected $oldWords = array(); |
||
| 55 | |||
| 56 | /** |
||
| 57 | * @var array |
||
| 58 | */ |
||
| 59 | protected $newWords = array(); |
||
| 60 | |||
| 61 | /** |
||
| 62 | * @var DiffCache[] |
||
| 63 | */ |
||
| 64 | protected $diffCaches = array(); |
||
| 65 | |||
| 66 | /** |
||
| 67 | * @var \HTMLPurifier |
||
| 68 | */ |
||
| 69 | protected $purifier; |
||
| 70 | |||
| 71 | /** |
||
| 72 | * @var \HTMLPurifier_Config|null |
||
| 73 | */ |
||
| 74 | protected $purifierConfig = null; |
||
| 75 | |||
| 76 | /** |
||
| 77 | * @see array_slice_cached(); |
||
| 78 | * @var bool |
||
| 79 | */ |
||
| 80 | protected $resetCache = false; |
||
| 81 | |||
| 82 | /** |
||
| 83 | * AbstractDiff constructor. |
||
| 84 | * |
||
| 85 | * @param string $oldText |
||
| 86 | * @param string $newText |
||
| 87 | * @param string $encoding |
||
| 88 | * @param null|array $specialCaseTags |
||
| 89 | * @param null|bool $groupDiffs |
||
| 90 | */ |
||
| 91 | 15 | public function __construct($oldText, $newText, $encoding = 'UTF-8', $specialCaseTags = null, $groupDiffs = null) |
|
| 92 | { |
||
| 93 | 15 | mb_substitute_character(0x20); |
|
| 94 | |||
| 95 | 15 | $this->setConfig(HtmlDiffConfig::create()->setEncoding($encoding)); |
|
| 96 | |||
| 97 | 15 | if ($specialCaseTags !== null) { |
|
| 98 | 14 | $this->config->setSpecialCaseTags($specialCaseTags); |
|
| 99 | } |
||
| 100 | |||
| 101 | 15 | if ($groupDiffs !== null) { |
|
| 102 | $this->config->setGroupDiffs($groupDiffs); |
||
| 103 | } |
||
| 104 | |||
| 105 | 15 | $this->oldText = $oldText; |
|
| 106 | 15 | $this->newText = $newText; |
|
| 107 | 15 | $this->content = ''; |
|
| 108 | 15 | } |
|
| 109 | |||
| 110 | /** |
||
| 111 | * @return bool|string |
||
| 112 | */ |
||
| 113 | abstract public function build(); |
||
| 114 | |||
| 115 | /** |
||
| 116 | * Initializes HTMLPurifier with cache location. |
||
| 117 | * |
||
| 118 | * @param null|string $defaultPurifierSerializerCache |
||
| 119 | */ |
||
| 120 | 15 | public function initPurifier($defaultPurifierSerializerCache = null) |
|
| 121 | { |
||
| 122 | 15 | if (null !== $this->purifierConfig) { |
|
| 123 | 2 | $HTMLPurifierConfig = $this->purifierConfig; |
|
| 124 | } else { |
||
| 125 | 15 | $HTMLPurifierConfig = \HTMLPurifier_Config::createDefault(); |
|
| 126 | } |
||
| 127 | |||
| 128 | // Cache.SerializerPath defaults to Null and sets |
||
| 129 | // the location to inside the vendor HTMLPurifier library |
||
| 130 | // under the DefinitionCache/Serializer folder. |
||
| 131 | 15 | if (!is_null($defaultPurifierSerializerCache)) { |
|
| 132 | 2 | $HTMLPurifierConfig->set('Cache.SerializerPath', $defaultPurifierSerializerCache); |
|
| 133 | } |
||
| 134 | |||
| 135 | 15 | $this->purifier = new \HTMLPurifier($HTMLPurifierConfig); |
|
| 136 | 15 | } |
|
| 137 | |||
| 138 | /** |
||
| 139 | * Prepare (purify) the HTML |
||
| 140 | * |
||
| 141 | * @return void |
||
| 142 | */ |
||
| 143 | 15 | protected function prepare() |
|
| 150 | |||
| 151 | /** |
||
| 152 | * @return DiffCache|null |
||
| 153 | */ |
||
| 154 | protected function getDiffCache() |
||
| 155 | { |
||
| 156 | if (!$this->hasDiffCache()) { |
||
| 157 | return null; |
||
| 158 | } |
||
| 159 | |||
| 160 | $hash = spl_object_hash($this->getConfig()->getCacheProvider()); |
||
| 161 | |||
| 162 | if (!array_key_exists($hash, $this->diffCaches)) { |
||
| 163 | $this->diffCaches[$hash] = new DiffCache($this->getConfig()->getCacheProvider()); |
||
| 164 | } |
||
| 165 | |||
| 166 | return $this->diffCaches[$hash]; |
||
| 167 | } |
||
| 168 | |||
| 169 | /** |
||
| 170 | * @return bool |
||
| 171 | */ |
||
| 172 | 15 | protected function hasDiffCache() |
|
| 176 | |||
| 177 | /** |
||
| 178 | * @return HtmlDiffConfig |
||
| 179 | */ |
||
| 180 | 15 | public function getConfig() |
|
| 184 | |||
| 185 | /** |
||
| 186 | * @param HtmlDiffConfig $config |
||
| 187 | * |
||
| 188 | * @return AbstractDiff |
||
| 189 | */ |
||
| 190 | 15 | public function setConfig(HtmlDiffConfig $config) |
|
| 196 | |||
| 197 | /** |
||
| 198 | * @return int |
||
| 199 | * |
||
| 200 | * @deprecated since 0.1.0 |
||
| 201 | */ |
||
| 202 | public function getMatchThreshold() |
||
| 203 | { |
||
| 204 | return $this->config->getMatchThreshold(); |
||
| 205 | } |
||
| 206 | |||
| 207 | /** |
||
| 208 | * @param int $matchThreshold |
||
| 209 | * |
||
| 210 | * @return AbstractDiff |
||
| 211 | * |
||
| 212 | * @deprecated since 0.1.0 |
||
| 213 | */ |
||
| 214 | public function setMatchThreshold($matchThreshold) |
||
| 215 | { |
||
| 216 | $this->config->setMatchThreshold($matchThreshold); |
||
| 217 | |||
| 218 | return $this; |
||
| 219 | } |
||
| 220 | |||
| 221 | /** |
||
| 222 | * @param array $chars |
||
| 223 | * |
||
| 224 | * @deprecated since 0.1.0 |
||
| 225 | */ |
||
| 226 | public function setSpecialCaseChars(array $chars) |
||
| 227 | { |
||
| 228 | $this->config->setSpecialCaseChars($chars); |
||
| 229 | } |
||
| 230 | |||
| 231 | /** |
||
| 232 | * @return array|null |
||
| 233 | * |
||
| 234 | * @deprecated since 0.1.0 |
||
| 235 | */ |
||
| 236 | public function getSpecialCaseChars() |
||
| 237 | { |
||
| 238 | return $this->config->getSpecialCaseChars(); |
||
| 239 | } |
||
| 240 | |||
| 241 | /** |
||
| 242 | * @param string $char |
||
| 243 | * |
||
| 244 | * @deprecated since 0.1.0 |
||
| 245 | */ |
||
| 246 | public function addSpecialCaseChar($char) |
||
| 247 | { |
||
| 248 | $this->config->addSpecialCaseChar($char); |
||
| 249 | } |
||
| 250 | |||
| 251 | /** |
||
| 252 | * @param string $char |
||
| 253 | * |
||
| 254 | * @deprecated since 0.1.0 |
||
| 255 | */ |
||
| 256 | public function removeSpecialCaseChar($char) |
||
| 257 | { |
||
| 258 | $this->config->removeSpecialCaseChar($char); |
||
| 259 | } |
||
| 260 | |||
| 261 | /** |
||
| 262 | * @param array $tags |
||
| 263 | * |
||
| 264 | * @deprecated since 0.1.0 |
||
| 265 | */ |
||
| 266 | public function setSpecialCaseTags(array $tags = array()) |
||
| 267 | { |
||
| 268 | $this->config->setSpecialCaseChars($tags); |
||
| 269 | } |
||
| 270 | |||
| 271 | /** |
||
| 272 | * @param string $tag |
||
| 273 | * |
||
| 274 | * @deprecated since 0.1.0 |
||
| 275 | */ |
||
| 276 | public function addSpecialCaseTag($tag) |
||
| 277 | { |
||
| 278 | $this->config->addSpecialCaseTag($tag); |
||
| 279 | } |
||
| 280 | |||
| 281 | /** |
||
| 282 | * @param string $tag |
||
| 283 | * |
||
| 284 | * @deprecated since 0.1.0 |
||
| 285 | */ |
||
| 286 | public function removeSpecialCaseTag($tag) |
||
| 287 | { |
||
| 288 | $this->config->removeSpecialCaseTag($tag); |
||
| 289 | } |
||
| 290 | |||
| 291 | /** |
||
| 292 | * @return array|null |
||
| 293 | * |
||
| 294 | * @deprecated since 0.1.0 |
||
| 295 | */ |
||
| 296 | public function getSpecialCaseTags() |
||
| 297 | { |
||
| 298 | return $this->config->getSpecialCaseTags(); |
||
| 299 | } |
||
| 300 | |||
| 301 | /** |
||
| 302 | * @return string |
||
| 303 | */ |
||
| 304 | public function getOldHtml() |
||
| 308 | |||
| 309 | /** |
||
| 310 | * @return string |
||
| 311 | */ |
||
| 312 | public function getNewHtml() |
||
| 316 | |||
| 317 | /** |
||
| 318 | * @return string |
||
| 319 | */ |
||
| 320 | public function getDifference() |
||
| 324 | |||
| 325 | /** |
||
| 326 | * Clears the diff content. |
||
| 327 | * |
||
| 328 | * @return void |
||
| 329 | */ |
||
| 330 | public function clearContent() |
||
| 334 | |||
| 335 | /** |
||
| 336 | * @param bool $boolean |
||
| 337 | * |
||
| 338 | * @return $this |
||
| 339 | * |
||
| 340 | * @deprecated since 0.1.0 |
||
| 341 | */ |
||
| 342 | public function setGroupDiffs($boolean) |
||
| 343 | { |
||
| 344 | $this->config->setGroupDiffs($boolean); |
||
| 345 | |||
| 346 | return $this; |
||
| 347 | } |
||
| 348 | |||
| 349 | /** |
||
| 350 | * @return bool |
||
| 351 | * |
||
| 352 | * @deprecated since 0.1.0 |
||
| 353 | */ |
||
| 354 | 15 | public function isGroupDiffs() |
|
| 355 | { |
||
| 356 | 15 | return $this->config->isGroupDiffs(); |
|
| 357 | } |
||
| 358 | |||
| 359 | /** |
||
| 360 | * @param \HTMLPurifier_Config $config |
||
| 361 | */ |
||
| 362 | 2 | public function setHTMLPurifierConfig(\HTMLPurifier_Config $config) |
|
| 366 | |||
| 367 | /** |
||
| 368 | * @param string $tag |
||
| 369 | * |
||
| 370 | * @return string |
||
| 371 | */ |
||
| 372 | protected function getOpeningTag($tag) |
||
| 376 | |||
| 377 | /** |
||
| 378 | * @param string $tag |
||
| 379 | * |
||
| 380 | * @return string |
||
| 381 | */ |
||
| 382 | protected function getClosingTag($tag) |
||
| 386 | |||
| 387 | /** |
||
| 388 | * @param string $str |
||
| 389 | * @param string $start |
||
| 390 | * @param string $end |
||
| 391 | * |
||
| 392 | * @return string |
||
| 393 | */ |
||
| 394 | protected function getStringBetween($str, $start, $end) |
||
| 395 | { |
||
| 396 | $expStr = explode($start, $str, 2); |
||
| 397 | if (count($expStr) > 1) { |
||
| 398 | $expStr = explode($end, $expStr[ 1 ]); |
||
| 399 | if (count($expStr) > 1) { |
||
| 400 | array_pop($expStr); |
||
| 401 | |||
| 402 | return implode($end, $expStr); |
||
| 403 | } |
||
| 404 | } |
||
| 405 | |||
| 406 | return ''; |
||
| 407 | } |
||
| 408 | |||
| 409 | /** |
||
| 410 | * @param string $html |
||
| 411 | * |
||
| 412 | * @return string |
||
| 413 | */ |
||
| 414 | 15 | protected function purifyHtml($html) |
|
| 427 | |||
| 428 | 15 | protected function splitInputsToWords() |
|
| 433 | |||
| 434 | /** |
||
| 435 | * @param array $oldWords |
||
| 436 | */ |
||
| 437 | 15 | protected function setOldWords(array $oldWords) |
|
| 442 | |||
| 443 | /** |
||
| 444 | * @param array $newWords |
||
| 445 | */ |
||
| 446 | 15 | protected function setNewWords(array $newWords) |
|
| 451 | |||
| 452 | /** |
||
| 453 | * @param string $text |
||
| 454 | * |
||
| 455 | * @return bool |
||
| 456 | */ |
||
| 457 | 15 | protected function isPartOfWord($text) |
|
| 461 | |||
| 462 | /** |
||
| 463 | * @param array $characterString |
||
| 464 | * |
||
| 465 | * @return array |
||
| 466 | */ |
||
| 467 | 15 | protected function convertHtmlToListOfWords($characterString) |
|
| 468 | { |
||
| 469 | 15 | $mode = 'character'; |
|
| 470 | 15 | $current_word = ''; |
|
| 471 | 15 | $words = array(); |
|
| 472 | 15 | foreach ($characterString as $i => $character) { |
|
| 473 | switch ($mode) { |
||
| 474 | 15 | case 'character': |
|
| 475 | 15 | if ($this->isStartOfTag($character)) { |
|
| 476 | 14 | if ($current_word != '') { |
|
| 477 | 13 | $words[] = $current_word; |
|
| 478 | } |
||
| 479 | |||
| 480 | 14 | $current_word = '<'; |
|
| 481 | 14 | $mode = 'tag'; |
|
| 482 | 15 | } elseif (preg_match("/\s/", $character)) { |
|
| 483 | 13 | if ($current_word !== '') { |
|
| 484 | 13 | $words[] = $current_word; |
|
| 485 | } |
||
| 486 | 13 | $current_word = preg_replace('/\s+/S', ' ', $character); |
|
| 487 | 13 | $mode = 'whitespace'; |
|
| 488 | } else { |
||
| 489 | if ( |
||
| 490 | 15 | (ctype_alnum($character) && (strlen($current_word) == 0 || $this->isPartOfWord($current_word))) || |
|
| 491 | 15 | (in_array($character, $this->config->getSpecialCaseChars()) && isset($characterString[$i + 1]) && $this->isPartOfWord($characterString[$i + 1])) |
|
| 492 | ) { |
||
| 493 | 15 | $current_word .= $character; |
|
| 494 | } else { |
||
| 495 | 15 | $words[] = $current_word; |
|
| 496 | 15 | $current_word = $character; |
|
| 497 | } |
||
| 498 | } |
||
| 499 | 15 | break; |
|
| 500 | 15 | case 'tag' : |
|
| 501 | 15 | if ($this->isEndOfTag($character)) { |
|
| 502 | 15 | $current_word .= '>'; |
|
| 503 | 15 | $words[] = $current_word; |
|
| 504 | 15 | $current_word = ''; |
|
| 505 | |||
| 506 | 15 | if (!preg_match('[^\s]', $character)) { |
|
| 507 | 15 | $mode = 'whitespace'; |
|
| 508 | } else { |
||
| 509 | 15 | $mode = 'character'; |
|
| 510 | } |
||
| 511 | } else { |
||
| 512 | 15 | $current_word .= $character; |
|
| 513 | } |
||
| 514 | 15 | break; |
|
| 515 | 15 | case 'whitespace': |
|
| 516 | 15 | if ($this->isStartOfTag($character)) { |
|
| 517 | 13 | if ($current_word !== '') { |
|
| 518 | 13 | $words[] = $current_word; |
|
| 519 | } |
||
| 520 | 13 | $current_word = '<'; |
|
| 521 | 13 | $mode = 'tag'; |
|
| 522 | 15 | } elseif (preg_match("/\s/", $character)) { |
|
| 523 | 11 | $current_word .= $character; |
|
| 524 | 11 | $current_word = preg_replace('/\s+/S', ' ', $current_word); |
|
| 525 | } else { |
||
| 526 | 15 | if ($current_word != '') { |
|
| 527 | 13 | $words[] = $current_word; |
|
| 528 | } |
||
| 529 | 15 | $current_word = $character; |
|
| 530 | 15 | $mode = 'character'; |
|
| 531 | } |
||
| 532 | 15 | break; |
|
| 533 | default: |
||
| 534 | 15 | break; |
|
| 535 | } |
||
| 536 | } |
||
| 537 | 15 | if ($current_word != '') { |
|
| 538 | $words[] = $current_word; |
||
| 539 | } |
||
| 540 | |||
| 541 | 15 | return $words; |
|
| 542 | } |
||
| 543 | |||
| 544 | /** |
||
| 545 | * @param string $val |
||
| 546 | * |
||
| 547 | * @return bool |
||
| 548 | */ |
||
| 549 | 15 | protected function isStartOfTag($val) |
|
| 553 | |||
| 554 | /** |
||
| 555 | * @param string $val |
||
| 556 | * |
||
| 557 | * @return bool |
||
| 558 | */ |
||
| 559 | 15 | protected function isEndOfTag($val) |
|
| 563 | |||
| 564 | /** |
||
| 565 | * @param string $value |
||
| 566 | * |
||
| 567 | * @return bool |
||
| 568 | */ |
||
| 569 | protected function isWhiteSpace($value) |
||
| 573 | |||
| 574 | /** |
||
| 575 | * @param string $value |
||
| 576 | * |
||
| 577 | * @return array |
||
| 578 | */ |
||
| 579 | 15 | protected function explode($value) |
|
| 584 | } |
||
| 585 |
Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line.