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 SimpleHtmlDom 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 SimpleHtmlDom, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 14 | class SimpleHtmlDom extends AbstractSimpleHtmlDom implements \IteratorAggregate, SimpleHtmlDomInterface |
||
| 15 | { |
||
| 16 | /** |
||
| 17 | * @param \DOMElement|\DOMNode $node |
||
| 18 | */ |
||
| 19 | 164 | public function __construct(\DOMNode $node) |
|
| 23 | |||
| 24 | /** |
||
| 25 | * @param string $name |
||
| 26 | * @param array $arguments |
||
| 27 | * |
||
| 28 | * @throws \BadMethodCallException |
||
| 29 | * |
||
| 30 | * @return SimpleHtmlDomInterface|string|null |
||
| 31 | */ |
||
| 32 | 11 | public function __call($name, $arguments) |
|
| 42 | |||
| 43 | /** |
||
| 44 | * Find list of nodes with a CSS selector. |
||
| 45 | * |
||
| 46 | * @param string $selector |
||
| 47 | * @param int|null $idx |
||
| 48 | * |
||
| 49 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
|
|
|||
| 50 | */ |
||
| 51 | 27 | public function find(string $selector, $idx = null) |
|
| 55 | |||
| 56 | /** |
||
| 57 | * Returns an array of attributes. |
||
| 58 | * |
||
| 59 | * @return string[]|null |
||
| 60 | */ |
||
| 61 | 3 | View Code Duplication | public function getAllAttributes() |
| 78 | |||
| 79 | /** |
||
| 80 | * @return bool |
||
| 81 | */ |
||
| 82 | public function hasAttributes(): bool |
||
| 86 | |||
| 87 | /** |
||
| 88 | * Return attribute value. |
||
| 89 | * |
||
| 90 | * @param string $name |
||
| 91 | * |
||
| 92 | * @return string |
||
| 93 | */ |
||
| 94 | 26 | public function getAttribute(string $name): string |
|
| 104 | |||
| 105 | /** |
||
| 106 | * Determine if an attribute exists on the element. |
||
| 107 | * |
||
| 108 | * @param string $name |
||
| 109 | * |
||
| 110 | * @return bool |
||
| 111 | */ |
||
| 112 | 2 | public function hasAttribute(string $name): bool |
|
| 120 | |||
| 121 | /** |
||
| 122 | * Get dom node's outer html. |
||
| 123 | * |
||
| 124 | * @param bool $multiDecodeNewHtmlEntity |
||
| 125 | * |
||
| 126 | * @return string |
||
| 127 | */ |
||
| 128 | 36 | public function html(bool $multiDecodeNewHtmlEntity = false): string |
|
| 132 | |||
| 133 | /** |
||
| 134 | * Get dom node's inner html. |
||
| 135 | * |
||
| 136 | * @param bool $multiDecodeNewHtmlEntity |
||
| 137 | * |
||
| 138 | * @return string |
||
| 139 | */ |
||
| 140 | 24 | public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string |
|
| 144 | |||
| 145 | /** |
||
| 146 | * Remove attribute. |
||
| 147 | * |
||
| 148 | * @param string $name <p>The name of the html-attribute.</p> |
||
| 149 | * |
||
| 150 | * @return SimpleHtmlDomInterface |
||
| 151 | */ |
||
| 152 | 2 | public function removeAttribute(string $name): SimpleHtmlDomInterface |
|
| 160 | |||
| 161 | /** |
||
| 162 | * Replace child node. |
||
| 163 | * |
||
| 164 | * @param string $string |
||
| 165 | * |
||
| 166 | * @return SimpleHtmlDomInterface |
||
| 167 | */ |
||
| 168 | 9 | View Code Duplication | protected function replaceChildWithString(string $string): SimpleHtmlDomInterface |
| 213 | |||
| 214 | /** |
||
| 215 | * Replace this node. |
||
| 216 | * |
||
| 217 | * @param string $string |
||
| 218 | * |
||
| 219 | * @return SimpleHtmlDomInterface |
||
| 220 | */ |
||
| 221 | 8 | protected function replaceNodeWithString(string $string): SimpleHtmlDomInterface |
|
| 288 | |||
| 289 | /** |
||
| 290 | * Replace this node with text |
||
| 291 | * |
||
| 292 | * @param string $string |
||
| 293 | * |
||
| 294 | * @return SimpleHtmlDomInterface |
||
| 295 | */ |
||
| 296 | 1 | View Code Duplication | protected function replaceTextWithString($string): SimpleHtmlDomInterface |
| 317 | |||
| 318 | /** |
||
| 319 | * Set attribute value. |
||
| 320 | * |
||
| 321 | * @param string $name <p>The name of the html-attribute.</p> |
||
| 322 | * @param string|null $value <p>Set to NULL or empty string, to remove the attribute.</p> |
||
| 323 | * @param bool $strictEmptyValueCheck <p> |
||
| 324 | * $value must be NULL, to remove the attribute, |
||
| 325 | * so that you can set an empty string as attribute-value e.g. autofocus="" |
||
| 326 | * </p> |
||
| 327 | * |
||
| 328 | * @return SimpleHtmlDomInterface |
||
| 329 | */ |
||
| 330 | 16 | View Code Duplication | public function setAttribute(string $name, $value = null, bool $strictEmptyValueCheck = false): SimpleHtmlDomInterface |
| 346 | |||
| 347 | /** |
||
| 348 | * Get dom node's plain text. |
||
| 349 | * |
||
| 350 | * @return string |
||
| 351 | */ |
||
| 352 | 32 | public function text(): string |
|
| 356 | |||
| 357 | /** |
||
| 358 | * Change the name of a tag in a "DOMNode". |
||
| 359 | * |
||
| 360 | * @param \DOMNode $node |
||
| 361 | * @param string $name |
||
| 362 | * |
||
| 363 | * @return \DOMElement|false |
||
| 364 | * <p>DOMElement a new instance of class DOMElement or false |
||
| 365 | * if an error occured.</p> |
||
| 366 | */ |
||
| 367 | 11 | View Code Duplication | protected function changeElementName(\DOMNode $node, string $name) |
| 393 | |||
| 394 | /** |
||
| 395 | * Returns children of node. |
||
| 396 | * |
||
| 397 | * @param int $idx |
||
| 398 | * |
||
| 399 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface|null |
||
| 400 | */ |
||
| 401 | 2 | View Code Duplication | public function childNodes(int $idx = -1) |
| 411 | |||
| 412 | /** |
||
| 413 | * Find nodes with a CSS selector. |
||
| 414 | * |
||
| 415 | * @param string $selector |
||
| 416 | * |
||
| 417 | * @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 418 | */ |
||
| 419 | 1 | public function findMulti(string $selector): SimpleHtmlDomNodeInterface |
|
| 423 | |||
| 424 | /** |
||
| 425 | * Find nodes with a CSS selector or false, if no element is found. |
||
| 426 | * |
||
| 427 | * @param string $selector |
||
| 428 | * |
||
| 429 | * @return false|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 430 | */ |
||
| 431 | 1 | public function findMultiOrFalse(string $selector) |
|
| 435 | |||
| 436 | /** |
||
| 437 | * Find one node with a CSS selector. |
||
| 438 | * |
||
| 439 | * @param string $selector |
||
| 440 | * |
||
| 441 | * @return SimpleHtmlDomInterface |
||
| 442 | */ |
||
| 443 | 3 | public function findOne(string $selector): SimpleHtmlDomInterface |
|
| 447 | |||
| 448 | /** |
||
| 449 | * Find one node with a CSS selector or false, if no element is found. |
||
| 450 | * |
||
| 451 | * @param string $selector |
||
| 452 | * |
||
| 453 | * @return false|SimpleHtmlDomInterface |
||
| 454 | */ |
||
| 455 | 1 | public function findOneOrFalse(string $selector) |
|
| 459 | |||
| 460 | /** |
||
| 461 | * Returns the first child of node. |
||
| 462 | * |
||
| 463 | * @return SimpleHtmlDomInterface|null |
||
| 464 | */ |
||
| 465 | 4 | View Code Duplication | public function firstChild() |
| 476 | |||
| 477 | /** |
||
| 478 | * Return elements by ".class". |
||
| 479 | * |
||
| 480 | * @param string $class |
||
| 481 | * |
||
| 482 | * @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 483 | */ |
||
| 484 | public function getElementByClass(string $class): SimpleHtmlDomNodeInterface |
||
| 488 | |||
| 489 | /** |
||
| 490 | * Return element by #id. |
||
| 491 | * |
||
| 492 | * @param string $id |
||
| 493 | * |
||
| 494 | * @return SimpleHtmlDomInterface |
||
| 495 | */ |
||
| 496 | public function getElementById(string $id): SimpleHtmlDomInterface |
||
| 500 | |||
| 501 | /** |
||
| 502 | * Return element by tag name. |
||
| 503 | * |
||
| 504 | * @param string $name |
||
| 505 | * |
||
| 506 | * @return SimpleHtmlDomInterface |
||
| 507 | */ |
||
| 508 | View Code Duplication | public function getElementByTagName(string $name): SimpleHtmlDomInterface |
|
| 522 | |||
| 523 | /** |
||
| 524 | * Returns elements by "#id". |
||
| 525 | * |
||
| 526 | * @param string $id |
||
| 527 | * @param int|null $idx |
||
| 528 | * |
||
| 529 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 530 | */ |
||
| 531 | public function getElementsById(string $id, $idx = null) |
||
| 535 | |||
| 536 | /** |
||
| 537 | * Returns elements by tag name. |
||
| 538 | * |
||
| 539 | * @param string $name |
||
| 540 | * @param int|null $idx |
||
| 541 | * |
||
| 542 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 543 | */ |
||
| 544 | View Code Duplication | public function getElementsByTagName(string $name, $idx = null) |
|
| 575 | |||
| 576 | /** |
||
| 577 | * Create a new "HtmlDomParser"-object from the current context. |
||
| 578 | * |
||
| 579 | * @return HtmlDomParser |
||
| 580 | */ |
||
| 581 | public function getHtmlDomParser(): HtmlDomParser |
||
| 585 | |||
| 586 | /** |
||
| 587 | * @return \DOMNode |
||
| 588 | */ |
||
| 589 | public function getNode(): \DOMNode |
||
| 593 | |||
| 594 | /** |
||
| 595 | * Nodes can get partially destroyed in which they're still an |
||
| 596 | * actual DOM node (such as \DOMElement) but almost their entire |
||
| 597 | * body is gone, including the `nodeType` attribute. |
||
| 598 | * |
||
| 599 | * @return bool true if node has been destroyed |
||
| 600 | */ |
||
| 601 | public function isRemoved(): bool |
||
| 605 | |||
| 606 | /** |
||
| 607 | * Returns the last child of node. |
||
| 608 | * |
||
| 609 | * @return SimpleHtmlDomInterface|null |
||
| 610 | */ |
||
| 611 | View Code Duplication | public function lastChild() |
|
| 622 | |||
| 623 | /** |
||
| 624 | * Returns the next sibling of node. |
||
| 625 | * |
||
| 626 | * @return SimpleHtmlDomInterface|null |
||
| 627 | */ |
||
| 628 | View Code Duplication | public function nextSibling() |
|
| 639 | |||
| 640 | /** |
||
| 641 | * Returns the next sibling of node. |
||
| 642 | * |
||
| 643 | * @return SimpleHtmlDomInterface|null |
||
| 644 | */ |
||
| 645 | View Code Duplication | public function nextNonWhitespaceSibling() |
|
| 661 | |||
| 662 | /** |
||
| 663 | * Returns the parent of node. |
||
| 664 | * |
||
| 665 | * @return SimpleHtmlDomInterface |
||
| 666 | */ |
||
| 667 | public function parentNode(): SimpleHtmlDomInterface |
||
| 671 | |||
| 672 | /** |
||
| 673 | * Returns the previous sibling of node. |
||
| 674 | * |
||
| 675 | * @return SimpleHtmlDomInterface|null |
||
| 676 | */ |
||
| 677 | View Code Duplication | public function previousSibling() |
|
| 688 | |||
| 689 | /** |
||
| 690 | * @param string|string[]|null $value <p> |
||
| 691 | * null === get the current input value |
||
| 692 | * text === set a new input value |
||
| 693 | * </p> |
||
| 694 | * |
||
| 695 | * @return string|string[]|null |
||
| 696 | */ |
||
| 697 | View Code Duplication | public function val($value = null) |
|
| 775 | |||
| 776 | /** |
||
| 777 | * @param HtmlDomParser $newDocument |
||
| 778 | * @param bool $removeExtraHeadTag |
||
| 779 | * |
||
| 780 | * @return HtmlDomParser |
||
| 781 | */ |
||
| 782 | protected function cleanHtmlWrapper( |
||
| 880 | |||
| 881 | /** |
||
| 882 | * Retrieve an external iterator. |
||
| 883 | * |
||
| 884 | * @see http://php.net/manual/en/iteratoraggregate.getiterator.php |
||
| 885 | * |
||
| 886 | * @return SimpleHtmlDomNode |
||
| 887 | * <p> |
||
| 888 | * An instance of an object implementing <b>Iterator</b> or |
||
| 889 | * <b>Traversable</b> |
||
| 890 | * </p> |
||
| 891 | */ |
||
| 892 | View Code Duplication | public function getIterator(): SimpleHtmlDomNodeInterface |
|
| 903 | |||
| 904 | /** |
||
| 905 | * Get dom node's inner html. |
||
| 906 | * |
||
| 907 | * @param bool $multiDecodeNewHtmlEntity |
||
| 908 | * |
||
| 909 | * @return string |
||
| 910 | */ |
||
| 911 | public function innerXml(bool $multiDecodeNewHtmlEntity = false): string |
||
| 915 | |||
| 916 | /** |
||
| 917 | * Normalize the given input for comparision. |
||
| 918 | * |
||
| 919 | * @param HtmlDomParser|string $input |
||
| 920 | * |
||
| 921 | * @return string |
||
| 922 | */ |
||
| 923 | private function normalizeStringForComparision($input): string |
||
| 959 | } |
||
| 960 |
This check marks PHPDoc comments that could not be parsed by our parser. To see which comment annotations we can parse, please refer to our documentation on supported doc-types.