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 |
||
33 | class SimpleHtmlDom implements \IteratorAggregate |
||
34 | { |
||
35 | /** |
||
36 | * @var array |
||
37 | */ |
||
38 | protected static $functionAliases = [ |
||
39 | 'children' => 'childNodes', |
||
40 | 'first_child' => 'firstChild', |
||
41 | 'last_child' => 'lastChild', |
||
42 | 'next_sibling' => 'nextSibling', |
||
43 | 'prev_sibling' => 'previousSibling', |
||
44 | 'parent' => 'parentNode', |
||
45 | 'outertext' => 'html', |
||
46 | 'outerhtml' => 'html', |
||
47 | 'innertext' => 'innerHtml', |
||
48 | 'innerhtml' => 'innerHtml', |
||
49 | ]; |
||
50 | |||
51 | /** |
||
52 | * @var DOMElement |
||
53 | */ |
||
54 | protected $node; |
||
55 | |||
56 | /** |
||
57 | * SimpleHtmlDom constructor. |
||
58 | * |
||
59 | * @param DOMNode $node |
||
60 | */ |
||
61 | 102 | public function __construct(DOMNode $node) |
|
65 | |||
66 | /** |
||
67 | * @param string $name |
||
68 | * @param array $arguments |
||
69 | * |
||
70 | * @throws \BadMethodCallException |
||
71 | * |
||
72 | * @return SimpleHtmlDom|string|null |
||
73 | */ |
||
74 | 9 | View Code Duplication | public function __call($name, $arguments) |
84 | |||
85 | /** |
||
86 | * @param string $name |
||
87 | * |
||
88 | * @return array|string|null |
||
89 | */ |
||
90 | 46 | public function __get($name) |
|
118 | |||
119 | /** |
||
120 | * @param string $selector |
||
121 | * @param int $idx |
||
122 | * |
||
123 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
124 | */ |
||
125 | 12 | public function __invoke($selector, $idx = null) |
|
129 | |||
130 | /** |
||
131 | * @param $name |
||
132 | * |
||
133 | * @return bool |
||
134 | */ |
||
135 | 1 | public function __isset($name) |
|
157 | |||
158 | /** |
||
159 | * @param $name |
||
160 | * @param $value |
||
161 | * |
||
162 | * @return SimpleHtmlDom |
||
163 | */ |
||
164 | 16 | public function __set($name, $value) |
|
186 | |||
187 | /** |
||
188 | * @return string |
||
189 | */ |
||
190 | 2 | public function __toString() |
|
194 | |||
195 | /** |
||
196 | * @param $name |
||
197 | * |
||
198 | * @return SimpleHtmlDom |
||
199 | */ |
||
200 | public function __unset($name) |
||
204 | |||
205 | /** |
||
206 | * Returns children of node. |
||
207 | * |
||
208 | * @param int $idx |
||
209 | * |
||
210 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNode|null |
||
211 | */ |
||
212 | 2 | public function childNodes(int $idx = -1) |
|
222 | |||
223 | /** |
||
224 | * Find list of nodes with a CSS selector. |
||
225 | * |
||
226 | * @param string $selector |
||
227 | * @param int|null $idx |
||
228 | * |
||
229 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
230 | */ |
||
231 | 26 | public function find(string $selector, $idx = null) |
|
235 | |||
236 | /** |
||
237 | * Find one node with a CSS selector. |
||
238 | * |
||
239 | * @param string $selector |
||
240 | * |
||
241 | * @return SimpleHtmlDom|SimpleHtmlDomNodeInterface |
||
242 | */ |
||
243 | public function findOne(string $selector) |
||
247 | |||
248 | /** |
||
249 | * Returns the first child of node. |
||
250 | * |
||
251 | * @return SimpleHtmlDom|null |
||
252 | */ |
||
253 | 4 | public function firstChild() |
|
263 | |||
264 | /** |
||
265 | * Returns an array of attributes. |
||
266 | * |
||
267 | * @return array|null |
||
268 | */ |
||
269 | 2 | public function getAllAttributes() |
|
282 | |||
283 | /** |
||
284 | * Return attribute value. |
||
285 | * |
||
286 | * @param string $name |
||
287 | * |
||
288 | * @return string |
||
289 | */ |
||
290 | 14 | public function getAttribute(string $name): string |
|
296 | |||
297 | /** |
||
298 | * Return element by #id. |
||
299 | * |
||
300 | * @param string $id |
||
301 | * |
||
302 | * @return SimpleHtmlDom|SimpleHtmlDomNodeInterface |
||
303 | */ |
||
304 | 1 | public function getElementById(string $id) |
|
308 | |||
309 | /** |
||
310 | * Return element by tag name. |
||
311 | * |
||
312 | * @param string $name |
||
313 | * |
||
314 | * @return SimpleHtmlDom|SimpleHtmlDomNodeBlank |
||
315 | */ |
||
316 | public function getElementByTagName(string $name) |
||
326 | |||
327 | /** |
||
328 | * Returns elements by #id. |
||
329 | * |
||
330 | * @param string $id |
||
331 | * @param int|null $idx |
||
332 | * |
||
333 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
334 | */ |
||
335 | public function getElementsById(string $id, $idx = null) |
||
339 | |||
340 | /** |
||
341 | * Returns elements by tag name. |
||
342 | * |
||
343 | * @param string $name |
||
344 | * @param int|null $idx |
||
345 | * |
||
346 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNode|SimpleHtmlDomNodeBlank |
||
347 | */ |
||
348 | View Code Duplication | public function getElementsByTagName(string $name, $idx = null) |
|
371 | |||
372 | /** |
||
373 | * Create a new "HtmlDomParser"-object from the current context. |
||
374 | * |
||
375 | * @return HtmlDomParser |
||
376 | */ |
||
377 | public function getHtmlDomParser(): HtmlDomParser |
||
381 | |||
382 | /** |
||
383 | * Retrieve an external iterator. |
||
384 | * |
||
385 | * @see http://php.net/manual/en/iteratoraggregate.getiterator.php |
||
386 | * |
||
387 | * @return SimpleHtmlDomNode An instance of an object implementing <b>Iterator</b> or |
||
388 | * <b>Traversable</b> |
||
389 | */ |
||
390 | public function getIterator(): SimpleHtmlDomNode |
||
401 | |||
402 | /** |
||
403 | * @return DOMNode |
||
404 | */ |
||
405 | public function getNode(): \DOMNode |
||
409 | |||
410 | /** |
||
411 | * Determine if an attribute exists on the element. |
||
412 | * |
||
413 | * @param string $name |
||
414 | * |
||
415 | * @return bool |
||
416 | */ |
||
417 | public function hasAttribute(string $name): bool |
||
421 | |||
422 | /** |
||
423 | * Get dom node's outer html. |
||
424 | * |
||
425 | * @param bool $multiDecodeNewHtmlEntity |
||
426 | * |
||
427 | * @return string |
||
428 | */ |
||
429 | public function html(bool $multiDecodeNewHtmlEntity = false): string |
||
433 | |||
434 | /** |
||
435 | * Get dom node's inner html. |
||
436 | * |
||
437 | * @param bool $multiDecodeNewHtmlEntity |
||
438 | * |
||
439 | * @return string |
||
440 | */ |
||
441 | public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string |
||
445 | |||
446 | /** |
||
447 | * Returns the last child of node. |
||
448 | * |
||
449 | * @return SimpleHtmlDom|null |
||
450 | */ |
||
451 | public function lastChild() |
||
461 | |||
462 | /** |
||
463 | * Returns the next sibling of node. |
||
464 | * |
||
465 | * @return SimpleHtmlDom|null |
||
466 | */ |
||
467 | public function nextSibling() |
||
477 | |||
478 | /** |
||
479 | * Returns the parent of node. |
||
480 | * |
||
481 | * @return SimpleHtmlDom |
||
482 | */ |
||
483 | public function parentNode(): self |
||
487 | |||
488 | /** |
||
489 | * Returns the previous sibling of node. |
||
490 | * |
||
491 | * @return SimpleHtmlDom|null |
||
492 | */ |
||
493 | public function previousSibling() |
||
503 | |||
504 | /** |
||
505 | * Replace child node. |
||
506 | * |
||
507 | * @param string $string |
||
508 | * |
||
509 | * @throws \RuntimeException |
||
510 | * |
||
511 | * @return $this |
||
512 | */ |
||
513 | protected function replaceChildWithString(string $string): self |
||
545 | |||
546 | /** |
||
547 | * Replace this node with text |
||
548 | * |
||
549 | * @param string $string |
||
550 | * |
||
551 | * @return $this|null |
||
552 | */ |
||
553 | protected function replaceTextWithString($string) |
||
568 | |||
569 | /** |
||
570 | * Replace this node. |
||
571 | * |
||
572 | * @param string $string |
||
573 | * |
||
574 | * @throws \RuntimeException |
||
575 | * |
||
576 | * @return $this|null |
||
577 | */ |
||
578 | protected function replaceNodeWithString(string $string) |
||
624 | |||
625 | /** |
||
626 | * Normalize the given input for comparision. |
||
627 | * |
||
628 | * @param HtmlDomParser|string $input |
||
629 | * |
||
630 | * @return string |
||
631 | */ |
||
632 | private function normalizeStringForComparision($input): string |
||
668 | |||
669 | /** |
||
670 | * @param HtmlDomParser $newDocument |
||
671 | * @param bool $removeExtraHeadTag |
||
672 | * |
||
673 | * @return HtmlDomParser |
||
674 | */ |
||
675 | protected function cleanHtmlWrapper(HtmlDomParser $newDocument, $removeExtraHeadTag = false): HtmlDomParser |
||
745 | |||
746 | /** |
||
747 | * Change the name of a tag in a "DOMNode". |
||
748 | * |
||
749 | * @param DOMNode $node |
||
750 | * @param string $name |
||
751 | * |
||
752 | * @return DOMElement |
||
753 | */ |
||
754 | protected function changeElementName(\DOMNode $node, string $name): \DOMElement |
||
774 | |||
775 | /** |
||
776 | * Set attribute value. |
||
777 | * |
||
778 | * @param string $name <p>The name of the html-attribute.</p> |
||
779 | * @param string|null $value <p>Set to NULL or empty string, to remove the attribute.</p> |
||
780 | * @param bool $strict </p> |
||
781 | * $value must be NULL, to remove the attribute, |
||
782 | * so that you can set an empty string as attribute-value e.g. autofocus="" |
||
783 | * </p> |
||
784 | * |
||
785 | * @return $this |
||
786 | */ |
||
787 | public function setAttribute(string $name, $value = null, bool $strict = false): self |
||
802 | |||
803 | /** |
||
804 | * @param string|string[]|null $value <p> |
||
805 | * null === get the current input value |
||
806 | * text === set a new input value |
||
807 | * </p> |
||
808 | * |
||
809 | * @return string|string[]|null |
||
810 | */ |
||
811 | public function val($value = null) |
||
881 | |||
882 | /** |
||
883 | * Remove attribute. |
||
884 | * |
||
885 | * @param string $name <p>The name of the html-attribute.</p> |
||
886 | * |
||
887 | * @return mixed |
||
888 | */ |
||
889 | public function removeAttribute(string $name) |
||
895 | |||
896 | /** |
||
897 | * Get dom node's plain text. |
||
898 | * |
||
899 | * @return string |
||
900 | */ |
||
901 | public function text(): string |
||
905 | } |
||
906 |
Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a given class or a super-class is assigned to a property that is type hinted more strictly.
Either this assignment is in error or an instanceof check should be added for that assignment.