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:
Complex classes like HtmlDiff 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 HtmlDiff, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 11 | class HtmlDiff extends AbstractDiff |
||
| 12 | { |
||
| 13 | /** |
||
| 14 | * @var array |
||
| 15 | */ |
||
| 16 | protected $wordIndices; |
||
| 17 | /** |
||
| 18 | * @var array |
||
| 19 | */ |
||
| 20 | protected $oldTables; |
||
| 21 | /** |
||
| 22 | * @var array |
||
| 23 | */ |
||
| 24 | protected $newTables; |
||
| 25 | /** |
||
| 26 | * @var bool |
||
| 27 | */ |
||
| 28 | protected $insertSpaceInReplace = false; |
||
| 29 | /** |
||
| 30 | * @var array |
||
| 31 | */ |
||
| 32 | protected $newIsolatedDiffTags; |
||
| 33 | /** |
||
| 34 | * @var array |
||
| 35 | */ |
||
| 36 | protected $oldIsolatedDiffTags; |
||
| 37 | /** |
||
| 38 | * @var array |
||
| 39 | */ |
||
| 40 | protected $isolatedDiffTags = array ( |
||
| 41 | 'ol' => '[[REPLACE_ORDERED_LIST]]', |
||
| 42 | 'ul' => '[[REPLACE_UNORDERED_LIST]]', |
||
| 43 | 'sub' => '[[REPLACE_SUB_SCRIPT]]', |
||
| 44 | 'sup' => '[[REPLACE_SUPER_SCRIPT]]', |
||
| 45 | 'dl' => '[[REPLACE_DEFINITION_LIST]]', |
||
| 46 | 'table' => '[[REPLACE_TABLE]]', |
||
| 47 | 'strong' => '[[REPLACE_STRONG]]', |
||
| 48 | 'b' => '[[REPLACE_B]]', |
||
| 49 | 'em' => '[[REPLACE_EM]]', |
||
| 50 | 'i' => '[[REPLACE_I]]', |
||
| 51 | 'a' => '[[REPLACE_A]]', |
||
| 52 | ); |
||
| 53 | /** |
||
| 54 | * @var bool |
||
| 55 | */ |
||
| 56 | protected $useTableDiffing = true; |
||
| 57 | |||
| 58 | /** |
||
| 59 | * @param $bool |
||
| 60 | * |
||
| 61 | * @return $this |
||
| 62 | */ |
||
| 63 | public function setUseTableDiffing($bool) |
||
| 69 | |||
| 70 | /** |
||
| 71 | * @param boolean $boolean |
||
| 72 | * @return HtmlDiff |
||
| 73 | */ |
||
| 74 | public function setInsertSpaceInReplace($boolean) |
||
| 80 | |||
| 81 | /** |
||
| 82 | * @return boolean |
||
| 83 | */ |
||
| 84 | public function getInsertSpaceInReplace() |
||
| 88 | |||
| 89 | /** |
||
| 90 | * @return string |
||
| 91 | */ |
||
| 92 | 11 | public function build() |
|
| 105 | |||
| 106 | 11 | protected function indexNewWords() |
|
| 120 | |||
| 121 | 11 | protected function replaceIsolatedDiffTags() |
|
| 126 | |||
| 127 | /** |
||
| 128 | * @param array $words |
||
| 129 | * |
||
| 130 | * @return array |
||
| 131 | */ |
||
| 132 | 11 | protected function createIsolatedDiffTagPlaceholders(&$words) |
|
| 166 | |||
| 167 | /** |
||
| 168 | * @param string $item |
||
| 169 | * @param null|string $currentIsolatedDiffTag |
||
| 170 | * |
||
| 171 | * @return false|string |
||
| 172 | */ |
||
| 173 | 11 | View Code Duplication | protected function isOpeningIsolatedDiffTag($item, $currentIsolatedDiffTag = null) |
| 186 | |||
| 187 | /** |
||
| 188 | * @param string $item |
||
| 189 | * @param null|string $currentIsolatedDiffTag |
||
| 190 | * |
||
| 191 | * @return false|string |
||
| 192 | */ |
||
| 193 | 11 | View Code Duplication | protected function isClosingIsolatedDiffTag($item, $currentIsolatedDiffTag = null) |
| 206 | |||
| 207 | /** |
||
| 208 | * @param Operation $operation |
||
| 209 | */ |
||
| 210 | 11 | protected function performOperation($operation) |
|
| 229 | |||
| 230 | /** |
||
| 231 | * @param Operation $operation |
||
| 232 | */ |
||
| 233 | 7 | protected function processReplaceOperation($operation) |
|
| 238 | |||
| 239 | /** |
||
| 240 | * @param Operation $operation |
||
| 241 | * @param string $cssClass |
||
| 242 | */ |
||
| 243 | 9 | View Code Duplication | protected function processInsertOperation($operation, $cssClass) |
| 259 | |||
| 260 | /** |
||
| 261 | * @param Operation $operation |
||
| 262 | * @param string $cssClass |
||
| 263 | */ |
||
| 264 | 9 | View Code Duplication | protected function processDeleteOperation($operation, $cssClass) |
| 280 | |||
| 281 | /** |
||
| 282 | * @param Operation $operation |
||
| 283 | * @param int $pos |
||
| 284 | * @param string $placeholder |
||
| 285 | * @param bool $stripWrappingTags |
||
| 286 | * |
||
| 287 | * @return string |
||
| 288 | */ |
||
| 289 | 7 | protected function diffIsolatedPlaceholder($operation, $pos, $placeholder, $stripWrappingTags = true) |
|
| 304 | |||
| 305 | /** |
||
| 306 | * @param string $oldText |
||
| 307 | * @param string $newText |
||
| 308 | * @param bool $stripWrappingTags |
||
| 309 | * |
||
| 310 | * @return string |
||
| 311 | */ |
||
| 312 | 5 | protected function diffElements($oldText, $newText, $stripWrappingTags = true) |
|
| 333 | |||
| 334 | /** |
||
| 335 | * @param string $oldText |
||
| 336 | * @param string $newText |
||
| 337 | * |
||
| 338 | * @return string |
||
| 339 | */ |
||
| 340 | 4 | View Code Duplication | protected function diffList($oldText, $newText) |
| 347 | |||
| 348 | /** |
||
| 349 | * @param string $oldText |
||
| 350 | * @param string $newText |
||
| 351 | * |
||
| 352 | * @return string |
||
| 353 | */ |
||
| 354 | View Code Duplication | protected function diffTables($oldText, $newText) |
|
| 361 | |||
| 362 | /** |
||
| 363 | * @param string $oldText |
||
| 364 | * @param string $newText |
||
| 365 | * |
||
| 366 | * @return string |
||
| 367 | */ |
||
| 368 | 1 | protected function diffLinks($oldText, $newText) |
|
| 383 | |||
| 384 | /** |
||
| 385 | * @param Operation $operation |
||
| 386 | */ |
||
| 387 | 11 | View Code Duplication | protected function processEqualOperation($operation) |
| 403 | |||
| 404 | /** |
||
| 405 | * @param string $text |
||
| 406 | * @param string $attribute |
||
| 407 | * |
||
| 408 | * @return null|string |
||
| 409 | */ |
||
| 410 | 1 | protected function getAttributeFromTag($text, $attribute) |
|
| 419 | |||
| 420 | /** |
||
| 421 | * @param string $text |
||
| 422 | * |
||
| 423 | * @return bool |
||
| 424 | */ |
||
| 425 | 7 | protected function isListPlaceholder($text) |
|
| 429 | |||
| 430 | /** |
||
| 431 | * @param string $text |
||
| 432 | * |
||
| 433 | * @return bool |
||
| 434 | */ |
||
| 435 | 5 | public function isLinkPlaceholder($text) |
|
| 439 | |||
| 440 | /** |
||
| 441 | * @param string $text |
||
| 442 | * @param array|string $types |
||
| 443 | * @param bool $strict |
||
| 444 | * |
||
| 445 | * @return bool |
||
| 446 | */ |
||
| 447 | 7 | protected function isPlaceholderType($text, $types, $strict = true) |
|
| 464 | |||
| 465 | /** |
||
| 466 | * @param string $text |
||
| 467 | * |
||
| 468 | * @return bool |
||
| 469 | */ |
||
| 470 | 5 | protected function isTablePlaceholder($text) |
|
| 476 | |||
| 477 | /** |
||
| 478 | * @param Operation $operation |
||
| 479 | * @param int $posInNew |
||
| 480 | * |
||
| 481 | * @return array |
||
| 482 | */ |
||
| 483 | 7 | protected function findIsolatedDiffTagsInOld($operation, $posInNew) |
|
| 489 | |||
| 490 | /** |
||
| 491 | * @param string $tag |
||
| 492 | * @param string $cssClass |
||
| 493 | * @param array $words |
||
| 494 | */ |
||
| 495 | 9 | protected function insertTag($tag, $cssClass, &$words) |
|
| 550 | |||
| 551 | /** |
||
| 552 | * @param string $word |
||
| 553 | * @param string $condition |
||
| 554 | * |
||
| 555 | * @return bool |
||
| 556 | */ |
||
| 557 | 9 | protected function checkCondition($word, $condition) |
|
| 561 | |||
| 562 | /** |
||
| 563 | * @param string $text |
||
| 564 | * @param string $tagName |
||
| 565 | * @param string $cssClass |
||
| 566 | * |
||
| 567 | * @return string |
||
| 568 | */ |
||
| 569 | 10 | protected function wrapText($text, $tagName, $cssClass) |
|
| 573 | |||
| 574 | /** |
||
| 575 | * @param array $words |
||
| 576 | * @param string $condition |
||
| 577 | * |
||
| 578 | * @return array |
||
| 579 | */ |
||
| 580 | 9 | protected function extractConsecutiveWords(&$words, $condition) |
|
| 614 | |||
| 615 | /** |
||
| 616 | * @param string $item |
||
| 617 | * |
||
| 618 | * @return bool |
||
| 619 | */ |
||
| 620 | 11 | protected function isTag($item) |
|
| 624 | |||
| 625 | /** |
||
| 626 | * @param string $item |
||
| 627 | * |
||
| 628 | * @return bool |
||
| 629 | */ |
||
| 630 | 11 | protected function isOpeningTag($item) |
|
| 634 | |||
| 635 | /** |
||
| 636 | * @param string $item |
||
| 637 | * |
||
| 638 | * @return bool |
||
| 639 | */ |
||
| 640 | 11 | protected function isClosingTag($item) |
|
| 644 | |||
| 645 | /** |
||
| 646 | * @return Operation[] |
||
| 647 | */ |
||
| 648 | 11 | protected function operations() |
|
| 681 | |||
| 682 | /** |
||
| 683 | * @return Match[] |
||
| 684 | */ |
||
| 685 | 11 | protected function matchingBlocks() |
|
| 692 | |||
| 693 | /** |
||
| 694 | * @param int $startInOld |
||
| 695 | * @param int $endInOld |
||
| 696 | * @param int $startInNew |
||
| 697 | * @param int $endInNew |
||
| 698 | * @param array $matchingBlocks |
||
| 699 | */ |
||
| 700 | 11 | protected function findMatchingBlocks($startInOld, $endInOld, $startInNew, $endInNew, &$matchingBlocks) |
|
| 713 | |||
| 714 | /** |
||
| 715 | * @param string $word |
||
| 716 | * |
||
| 717 | * @return string |
||
| 718 | */ |
||
| 719 | 8 | protected function stripTagAttributes($word) |
|
| 725 | |||
| 726 | /** |
||
| 727 | * @param int $startInOld |
||
| 728 | * @param int $endInOld |
||
| 729 | * @param int $startInNew |
||
| 730 | * @param int $endInNew |
||
| 731 | * |
||
| 732 | * @return Match|null |
||
| 733 | */ |
||
| 734 | 11 | protected function findMatch($startInOld, $endInOld, $startInNew, $endInNew) |
|
| 789 | } |
||
| 790 |
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.