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 |
| 212 | |||
| 213 | /** |
||
| 214 | * Replace this node. |
||
| 215 | * |
||
| 216 | * @param string $string |
||
| 217 | * |
||
| 218 | * @return SimpleHtmlDomInterface |
||
| 219 | */ |
||
| 220 | 8 | protected function replaceNodeWithString(string $string): SimpleHtmlDomInterface |
|
| 286 | |||
| 287 | /** |
||
| 288 | * Replace this node with text |
||
| 289 | * |
||
| 290 | * @param string $string |
||
| 291 | * |
||
| 292 | * @return SimpleHtmlDomInterface |
||
| 293 | */ |
||
| 294 | 1 | View Code Duplication | protected function replaceTextWithString($string): SimpleHtmlDomInterface |
| 315 | |||
| 316 | /** |
||
| 317 | * Set attribute value. |
||
| 318 | * |
||
| 319 | * @param string $name <p>The name of the html-attribute.</p> |
||
| 320 | * @param string|null $value <p>Set to NULL or empty string, to remove the attribute.</p> |
||
| 321 | * @param bool $strictEmptyValueCheck <p> |
||
| 322 | * $value must be NULL, to remove the attribute, |
||
| 323 | * so that you can set an empty string as attribute-value e.g. autofocus="" |
||
| 324 | * </p> |
||
| 325 | * |
||
| 326 | * @return SimpleHtmlDomInterface |
||
| 327 | */ |
||
| 328 | 16 | View Code Duplication | public function setAttribute(string $name, $value = null, bool $strictEmptyValueCheck = false): SimpleHtmlDomInterface |
| 344 | |||
| 345 | /** |
||
| 346 | * Get dom node's plain text. |
||
| 347 | * |
||
| 348 | * @return string |
||
| 349 | */ |
||
| 350 | 32 | public function text(): string |
|
| 354 | |||
| 355 | /** |
||
| 356 | * Change the name of a tag in a "DOMNode". |
||
| 357 | * |
||
| 358 | * @param \DOMNode $node |
||
| 359 | * @param string $name |
||
| 360 | * |
||
| 361 | * @return \DOMElement|false |
||
| 362 | * <p>DOMElement a new instance of class DOMElement or false |
||
| 363 | * if an error occured.</p> |
||
| 364 | */ |
||
| 365 | 11 | View Code Duplication | protected function changeElementName(\DOMNode $node, string $name) |
| 391 | |||
| 392 | /** |
||
| 393 | * Returns children of node. |
||
| 394 | * |
||
| 395 | * @param int $idx |
||
| 396 | * |
||
| 397 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface|null |
||
| 398 | */ |
||
| 399 | 2 | View Code Duplication | public function childNodes(int $idx = -1) |
| 409 | |||
| 410 | /** |
||
| 411 | * Find nodes with a CSS selector. |
||
| 412 | * |
||
| 413 | * @param string $selector |
||
| 414 | * |
||
| 415 | * @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 416 | */ |
||
| 417 | 1 | public function findMulti(string $selector): SimpleHtmlDomNodeInterface |
|
| 421 | |||
| 422 | /** |
||
| 423 | * Find nodes with a CSS selector or false, if no element is found. |
||
| 424 | * |
||
| 425 | * @param string $selector |
||
| 426 | * |
||
| 427 | * @return false|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 428 | */ |
||
| 429 | 1 | public function findMultiOrFalse(string $selector) |
|
| 433 | |||
| 434 | /** |
||
| 435 | * Find one node with a CSS selector. |
||
| 436 | * |
||
| 437 | * @param string $selector |
||
| 438 | * |
||
| 439 | * @return SimpleHtmlDomInterface |
||
| 440 | */ |
||
| 441 | 3 | public function findOne(string $selector): SimpleHtmlDomInterface |
|
| 445 | |||
| 446 | /** |
||
| 447 | * Find one node with a CSS selector or false, if no element is found. |
||
| 448 | * |
||
| 449 | * @param string $selector |
||
| 450 | * |
||
| 451 | * @return false|SimpleHtmlDomInterface |
||
| 452 | */ |
||
| 453 | 1 | public function findOneOrFalse(string $selector) |
|
| 457 | |||
| 458 | /** |
||
| 459 | * Returns the first child of node. |
||
| 460 | * |
||
| 461 | * @return SimpleHtmlDomInterface|null |
||
| 462 | */ |
||
| 463 | 4 | View Code Duplication | public function firstChild() |
| 474 | |||
| 475 | /** |
||
| 476 | * Return elements by ".class". |
||
| 477 | * |
||
| 478 | * @param string $class |
||
| 479 | * |
||
| 480 | * @return SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 481 | */ |
||
| 482 | public function getElementByClass(string $class): SimpleHtmlDomNodeInterface |
||
| 486 | |||
| 487 | /** |
||
| 488 | * Return element by #id. |
||
| 489 | * |
||
| 490 | * @param string $id |
||
| 491 | * |
||
| 492 | * @return SimpleHtmlDomInterface |
||
| 493 | */ |
||
| 494 | 1 | public function getElementById(string $id): SimpleHtmlDomInterface |
|
| 498 | |||
| 499 | /** |
||
| 500 | * Return element by tag name. |
||
| 501 | * |
||
| 502 | * @param string $name |
||
| 503 | * |
||
| 504 | * @return SimpleHtmlDomInterface |
||
| 505 | */ |
||
| 506 | 1 | View Code Duplication | public function getElementByTagName(string $name): SimpleHtmlDomInterface |
| 520 | |||
| 521 | /** |
||
| 522 | * Returns elements by "#id". |
||
| 523 | * |
||
| 524 | * @param string $id |
||
| 525 | * @param int|null $idx |
||
| 526 | * |
||
| 527 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 528 | */ |
||
| 529 | public function getElementsById(string $id, $idx = null) |
||
| 533 | |||
| 534 | /** |
||
| 535 | * Returns elements by tag name. |
||
| 536 | * |
||
| 537 | * @param string $name |
||
| 538 | * @param int|null $idx |
||
| 539 | * |
||
| 540 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
| 541 | */ |
||
| 542 | 1 | View Code Duplication | public function getElementsByTagName(string $name, $idx = null) |
| 573 | |||
| 574 | /** |
||
| 575 | * Create a new "HtmlDomParser"-object from the current context. |
||
| 576 | * |
||
| 577 | * @return HtmlDomParser |
||
| 578 | */ |
||
| 579 | 105 | public function getHtmlDomParser(): HtmlDomParser |
|
| 583 | |||
| 584 | /** |
||
| 585 | * @return \DOMNode |
||
| 586 | */ |
||
| 587 | 106 | public function getNode(): \DOMNode |
|
| 591 | |||
| 592 | /** |
||
| 593 | * Nodes can get partially destroyed in which they're still an |
||
| 594 | * actual DOM node (such as \DOMElement) but almost their entire |
||
| 595 | * body is gone, including the `nodeType` attribute. |
||
| 596 | * |
||
| 597 | * @return bool true if node has been destroyed |
||
| 598 | */ |
||
| 599 | public function isRemoved(): bool |
||
| 603 | |||
| 604 | /** |
||
| 605 | * Returns the last child of node. |
||
| 606 | * |
||
| 607 | * @return SimpleHtmlDomInterface|null |
||
| 608 | */ |
||
| 609 | 4 | View Code Duplication | public function lastChild() |
| 620 | |||
| 621 | /** |
||
| 622 | * Returns the next sibling of node. |
||
| 623 | * |
||
| 624 | * @return SimpleHtmlDomInterface|null |
||
| 625 | */ |
||
| 626 | 1 | View Code Duplication | public function nextSibling() |
| 637 | |||
| 638 | /** |
||
| 639 | * Returns the next sibling of node. |
||
| 640 | * |
||
| 641 | * @return SimpleHtmlDomInterface|null |
||
| 642 | */ |
||
| 643 | 1 | View Code Duplication | public function nextNonWhitespaceSibling() |
| 659 | |||
| 660 | /** |
||
| 661 | * Returns the parent of node. |
||
| 662 | * |
||
| 663 | * @return SimpleHtmlDomInterface |
||
| 664 | */ |
||
| 665 | 2 | public function parentNode(): SimpleHtmlDomInterface |
|
| 669 | |||
| 670 | /** |
||
| 671 | * Returns the previous sibling of node. |
||
| 672 | * |
||
| 673 | * @return SimpleHtmlDomInterface|null |
||
| 674 | */ |
||
| 675 | 1 | View Code Duplication | public function previousSibling() |
| 686 | |||
| 687 | |||
| 688 | /** |
||
| 689 | * Returns the previous sibling of node. |
||
| 690 | * |
||
| 691 | * @return SimpleHtmlDomInterface|null |
||
| 692 | */ |
||
| 693 | View Code Duplication | public function previousNonWhitespaceSibling() |
|
| 709 | 1 | ||
| 710 | /** |
||
| 711 | * @param string|string[]|null $value <p> |
||
| 712 | * null === get the current input value |
||
| 713 | 1 | * text === set a new input value |
|
| 714 | * </p> |
||
| 715 | 1 | * |
|
| 716 | * @return string|string[]|null |
||
| 717 | 1 | */ |
|
| 718 | View Code Duplication | public function val($value = null) |
|
| 795 | |||
| 796 | 14 | /** |
|
| 797 | 14 | * @param HtmlDomParser $newDocument |
|
| 798 | * @param bool $removeExtraHeadTag |
||
| 799 | 11 | * |
|
| 800 | * @return HtmlDomParser |
||
| 801 | */ |
||
| 802 | 14 | protected function cleanHtmlWrapper( |
|
| 896 | |||
| 897 | /** |
||
| 898 | * Retrieve an external iterator. |
||
| 899 | * |
||
| 900 | * @see http://php.net/manual/en/iteratoraggregate.getiterator.php |
||
| 901 | * |
||
| 902 | * @return SimpleHtmlDomNode |
||
| 903 | * <p> |
||
| 904 | * An instance of an object implementing <b>Iterator</b> or |
||
| 905 | * <b>Traversable</b> |
||
| 906 | * </p> |
||
| 907 | */ |
||
| 908 | View Code Duplication | public function getIterator(): SimpleHtmlDomNodeInterface |
|
| 919 | 14 | ||
| 920 | /** |
||
| 921 | 14 | * Get dom node's inner html. |
|
| 922 | * |
||
| 923 | 14 | * @param bool $multiDecodeNewHtmlEntity |
|
| 924 | * |
||
| 925 | * @return string |
||
| 926 | 14 | */ |
|
| 927 | public function innerXml(bool $multiDecodeNewHtmlEntity = false): string |
||
| 931 | 14 | ||
| 932 | 14 | /** |
|
| 933 | 14 | * Normalize the given input for comparision. |
|
| 934 | * |
||
| 935 | 14 | * @param HtmlDomParser|string $input |
|
| 936 | * |
||
| 937 | * @return string |
||
| 938 | */ |
||
| 939 | private function normalizeStringForComparision($input): string |
||
| 975 | } |
||
| 976 |
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.