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 SimpleXmlDom 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 SimpleXmlDom, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
14 | class SimpleXmlDom extends AbstractSimpleXmlDom implements \IteratorAggregate, SimpleXmlDomInterface |
||
15 | { |
||
16 | /** |
||
17 | * @param \DOMElement|\DOMNode $node |
||
18 | */ |
||
19 | 5 | public function __construct(\DOMNode $node) |
|
23 | |||
24 | /** |
||
25 | * @param string $name |
||
26 | * @param array $arguments |
||
27 | * |
||
28 | * @throws \BadMethodCallException |
||
29 | * |
||
30 | * @return SimpleXmlDomInterface|string|null |
||
31 | */ |
||
32 | public function __call($name, $arguments) |
||
42 | |||
43 | /** |
||
44 | * Find list of nodes with a CSS or xPath selector. |
||
45 | * |
||
46 | * @param string $selector |
||
47 | * @param int|null $idx |
||
48 | * |
||
49 | * @return SimpleXmlDomInterface|SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
|
|||
50 | */ |
||
51 | 3 | public function find(string $selector, $idx = null) |
|
52 | { |
||
53 | 3 | return $this->getXmlDomParser()->find($selector, $idx); |
|
54 | } |
||
55 | |||
56 | /** |
||
57 | * Returns an array of attributes. |
||
58 | * |
||
59 | * @return string[]|null |
||
60 | */ |
||
61 | 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 | 1 | public function getAttribute(string $name): string |
|
95 | { |
||
96 | 1 | if ($this->node instanceof \DOMElement) { |
|
97 | 1 | return XmlDomParser::putReplacedBackToPreserveHtmlEntities( |
|
98 | 1 | $this->node->getAttribute($name) |
|
99 | ); |
||
100 | } |
||
101 | |||
102 | return ''; |
||
103 | } |
||
104 | |||
105 | /** |
||
106 | * Determine if an attribute exists on the element. |
||
107 | * |
||
108 | * @param string $name |
||
109 | * |
||
110 | * @return bool |
||
111 | */ |
||
112 | public function hasAttribute(string $name): bool |
||
120 | |||
121 | /** |
||
122 | * Get dom node's inner html. |
||
123 | * |
||
124 | * @param bool $multiDecodeNewHtmlEntity |
||
125 | * |
||
126 | * @return string |
||
127 | */ |
||
128 | public function innerXml(bool $multiDecodeNewHtmlEntity = false): string |
||
132 | |||
133 | /** |
||
134 | * Remove attribute. |
||
135 | * |
||
136 | * @param string $name <p>The name of the html-attribute.</p> |
||
137 | * |
||
138 | * @return SimpleXmlDomInterface |
||
139 | */ |
||
140 | public function removeAttribute(string $name): SimpleXmlDomInterface |
||
148 | |||
149 | /** |
||
150 | * Replace child node. |
||
151 | * |
||
152 | * @param string $string |
||
153 | * |
||
154 | * @return SimpleXmlDomInterface |
||
155 | */ |
||
156 | View Code Duplication | protected function replaceChildWithString(string $string): SimpleXmlDomInterface |
|
200 | |||
201 | /** |
||
202 | * Replace this node. |
||
203 | * |
||
204 | * @param string $string |
||
205 | * |
||
206 | * @return SimpleXmlDomInterface |
||
207 | */ |
||
208 | protected function replaceNodeWithString(string $string): SimpleXmlDomInterface |
||
246 | |||
247 | /** |
||
248 | * Replace this node with text |
||
249 | * |
||
250 | * @param string $string |
||
251 | * |
||
252 | * @return SimpleXmlDomInterface |
||
253 | */ |
||
254 | View Code Duplication | protected function replaceTextWithString($string): SimpleXmlDomInterface |
|
274 | |||
275 | /** |
||
276 | * Set attribute value. |
||
277 | * |
||
278 | * @param string $name <p>The name of the html-attribute.</p> |
||
279 | * @param string|null $value <p>Set to NULL or empty string, to remove the attribute.</p> |
||
280 | * @param bool $strictEmptyValueCheck </p> |
||
281 | * $value must be NULL, to remove the attribute, |
||
282 | * so that you can set an empty string as attribute-value e.g. autofocus="" |
||
283 | * </p> |
||
284 | * |
||
285 | * @return SimpleXmlDomInterface |
||
286 | */ |
||
287 | View Code Duplication | public function setAttribute(string $name, $value = null, bool $strictEmptyValueCheck = false): SimpleXmlDomInterface |
|
303 | |||
304 | /** |
||
305 | * Get dom node's plain text. |
||
306 | * |
||
307 | * @return string |
||
308 | */ |
||
309 | 4 | public function text(): string |
|
310 | { |
||
311 | 4 | return $this->getXmlDomParser()->fixHtmlOutput($this->node->textContent); |
|
312 | } |
||
313 | |||
314 | /** |
||
315 | * Get dom node's outer html. |
||
316 | * |
||
317 | * @param bool $multiDecodeNewHtmlEntity |
||
318 | * |
||
319 | * @return string |
||
320 | */ |
||
321 | public function xml(bool $multiDecodeNewHtmlEntity = false): string |
||
325 | |||
326 | /** |
||
327 | * Change the name of a tag in a "DOMNode". |
||
328 | * |
||
329 | * @param \DOMNode $node |
||
330 | * @param string $name |
||
331 | * |
||
332 | * @return \DOMElement|false |
||
333 | * <p>DOMElement a new instance of class DOMElement or false |
||
334 | * if an error occured.</p> |
||
335 | */ |
||
336 | View Code Duplication | protected function changeElementName(\DOMNode $node, string $name) |
|
362 | |||
363 | /** |
||
364 | * Returns children of node. |
||
365 | * |
||
366 | * @param int $idx |
||
367 | * |
||
368 | * @return SimpleXmlDomInterface|SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface>|null |
||
369 | */ |
||
370 | View Code Duplication | public function childNodes(int $idx = -1) |
|
380 | |||
381 | /** |
||
382 | * Find nodes with a CSS or xPath selector. |
||
383 | * |
||
384 | * @param string $selector |
||
385 | * |
||
386 | * @return SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
387 | */ |
||
388 | public function findMulti(string $selector): SimpleXmlDomNodeInterface |
||
392 | |||
393 | /** |
||
394 | * Find nodes with a CSS or xPath selector. |
||
395 | * |
||
396 | * @param string $selector |
||
397 | * |
||
398 | * @return false|SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
399 | */ |
||
400 | public function findMultiOrFalse(string $selector) |
||
404 | |||
405 | /** |
||
406 | * Find one node with a CSS or xPath selector. |
||
407 | * |
||
408 | * @param string $selector |
||
409 | * |
||
410 | * @return SimpleXmlDomInterface |
||
411 | */ |
||
412 | 1 | public function findOne(string $selector): SimpleXmlDomInterface |
|
413 | { |
||
414 | 1 | return $this->getXmlDomParser()->findOne($selector); |
|
415 | } |
||
416 | |||
417 | /** |
||
418 | * Find one node with a CSS or xPath selector or false, if no element is found. |
||
419 | * |
||
420 | * @param string $selector |
||
421 | * |
||
422 | * @return false|SimpleXmlDomInterface |
||
423 | */ |
||
424 | public function findOneOrFalse(string $selector) |
||
428 | |||
429 | /** |
||
430 | * Returns the first child of node. |
||
431 | * |
||
432 | * @return SimpleXmlDomInterface|null |
||
433 | */ |
||
434 | View Code Duplication | public function firstChild() |
|
445 | |||
446 | /** |
||
447 | * Return elements by ".class". |
||
448 | * |
||
449 | * @param string $class |
||
450 | * |
||
451 | * @return SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
452 | */ |
||
453 | public function getElementByClass(string $class): SimpleXmlDomNodeInterface |
||
457 | |||
458 | /** |
||
459 | * Return element by #id. |
||
460 | * |
||
461 | * @param string $id |
||
462 | * |
||
463 | * @return SimpleXmlDomInterface |
||
464 | */ |
||
465 | public function getElementById(string $id): SimpleXmlDomInterface |
||
469 | |||
470 | /** |
||
471 | * Return element by tag name. |
||
472 | * |
||
473 | * @param string $name |
||
474 | * |
||
475 | * @return SimpleXmlDomInterface |
||
476 | */ |
||
477 | View Code Duplication | public function getElementByTagName(string $name): SimpleXmlDomInterface |
|
491 | |||
492 | /** |
||
493 | * Returns elements by "#id". |
||
494 | * |
||
495 | * @param string $id |
||
496 | * @param int|null $idx |
||
497 | * |
||
498 | * @return SimpleXmlDomInterface|SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
499 | */ |
||
500 | public function getElementsById(string $id, $idx = null) |
||
504 | |||
505 | /** |
||
506 | * Returns elements by tag name. |
||
507 | * |
||
508 | * @param string $name |
||
509 | * @param int|null $idx |
||
510 | * |
||
511 | * @return SimpleXmlDomInterface|SimpleXmlDomInterface[]|SimpleXmlDomNodeInterface<SimpleXmlDomInterface> |
||
512 | */ |
||
513 | View Code Duplication | public function getElementsByTagName(string $name, $idx = null) |
|
544 | |||
545 | /** |
||
546 | * @return \DOMNode |
||
547 | */ |
||
548 | 5 | public function getNode(): \DOMNode |
|
552 | |||
553 | /** |
||
554 | * Create a new "XmlDomParser"-object from the current context. |
||
555 | * |
||
556 | * @return XmlDomParser |
||
557 | */ |
||
558 | 4 | public function getXmlDomParser(): XmlDomParser |
|
559 | { |
||
560 | 4 | return new XmlDomParser($this); |
|
561 | } |
||
562 | |||
563 | /** |
||
564 | * Get dom node's inner html. |
||
565 | * |
||
566 | * @param bool $multiDecodeNewHtmlEntity |
||
567 | * |
||
568 | * @return string |
||
569 | */ |
||
570 | public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string |
||
574 | |||
575 | /** |
||
576 | * Nodes can get partially destroyed in which they're still an |
||
577 | * actual DOM node (such as \DOMElement) but almost their entire |
||
578 | * body is gone, including the `nodeType` attribute. |
||
579 | * |
||
580 | * @return bool true if node has been destroyed |
||
581 | */ |
||
582 | public function isRemoved(): bool |
||
586 | |||
587 | /** |
||
588 | * Returns the last child of node. |
||
589 | * |
||
590 | * @return SimpleXmlDomInterface|null |
||
591 | */ |
||
592 | View Code Duplication | public function lastChild() |
|
603 | |||
604 | /** |
||
605 | * Returns the next sibling of node. |
||
606 | * |
||
607 | * @return SimpleXmlDomInterface|null |
||
608 | */ |
||
609 | View Code Duplication | public function nextSibling() |
|
620 | |||
621 | /** |
||
622 | * Returns the next sibling of node. |
||
623 | * |
||
624 | * @return SimpleXmlDomInterface|null |
||
625 | */ |
||
626 | View Code Duplication | public function nextNonWhitespaceSibling() |
|
642 | |||
643 | /** |
||
644 | * Returns the parent of node. |
||
645 | * |
||
646 | * @return SimpleXmlDomInterface |
||
647 | */ |
||
648 | public function parentNode(): SimpleXmlDomInterface |
||
652 | |||
653 | /** |
||
654 | * Returns the previous sibling of node. |
||
655 | * |
||
656 | * @return SimpleXmlDomInterface|null |
||
657 | */ |
||
658 | View Code Duplication | public function previousSibling() |
|
669 | |||
670 | /** |
||
671 | * @param string|string[]|null $value <p> |
||
672 | * null === get the current input value |
||
673 | * text === set a new input value |
||
674 | * </p> |
||
675 | * |
||
676 | * @return string|string[]|null |
||
677 | */ |
||
678 | View Code Duplication | public function val($value = null) |
|
755 | |||
756 | /** |
||
757 | * Retrieve an external iterator. |
||
758 | * |
||
759 | * @see http://php.net/manual/en/iteratoraggregate.getiterator.php |
||
760 | * |
||
761 | * @return SimpleXmlDomNode |
||
762 | * <p> |
||
763 | * An instance of an object implementing <b>Iterator</b> or |
||
764 | * <b>Traversable</b> |
||
765 | * </p> |
||
766 | */ |
||
767 | View Code Duplication | public function getIterator(): SimpleXmlDomNodeInterface |
|
778 | |||
779 | /** |
||
780 | * Normalize the given input for comparision. |
||
781 | * |
||
782 | * @param string|XmlDomParser $input |
||
783 | * |
||
784 | * @return string |
||
785 | */ |
||
786 | private function normalizeStringForComparision($input): string |
||
817 | } |
||
818 |
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.