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 AbstractSimpleHtmlDom 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 AbstractSimpleHtmlDom, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
7 | abstract class AbstractSimpleHtmlDom |
||
8 | { |
||
9 | /** |
||
10 | * @var array |
||
11 | */ |
||
12 | protected static $functionAliases = [ |
||
13 | 'children' => 'childNodes', |
||
14 | 'first_child' => 'firstChild', |
||
15 | 'last_child' => 'lastChild', |
||
16 | 'next_sibling' => 'nextSibling', |
||
17 | 'prev_sibling' => 'previousSibling', |
||
18 | 'parent' => 'parentNode', |
||
19 | 'outertext' => 'html', |
||
20 | 'outerhtml' => 'html', |
||
21 | 'innertext' => 'innerHtml', |
||
22 | 'innerhtml' => 'innerHtml', |
||
23 | ]; |
||
24 | |||
25 | /** |
||
26 | * @var \DOMElement|\DOMNode|null |
||
27 | */ |
||
28 | protected $node; |
||
29 | |||
30 | /** |
||
31 | * @var SimpleHtmlAttributes|null |
||
32 | */ |
||
33 | private $classListCache; |
||
34 | |||
35 | /** |
||
36 | * @param string $name |
||
37 | * @param array $arguments |
||
38 | * |
||
39 | * @throws \BadMethodCallException |
||
40 | * |
||
41 | * @return SimpleHtmlDomInterface|string|null |
||
42 | */ |
||
43 | public function __call($name, $arguments) |
||
53 | |||
54 | /** |
||
55 | * @param string $name |
||
56 | * |
||
57 | * @return SimpleHtmlAttributes|string|string[]|null |
||
58 | */ |
||
59 | 81 | public function __get($name) |
|
60 | { |
||
61 | 81 | $nameOrig = $name; |
|
62 | 81 | $name = \strtolower($name); |
|
63 | |||
64 | 81 | switch ($name) { |
|
65 | 81 | case 'outerhtml': |
|
66 | 73 | case 'outertext': |
|
67 | 63 | case 'html': |
|
68 | 28 | return $this->html(); |
|
69 | 63 | case 'innerhtml': |
|
70 | 51 | case 'innertext': |
|
71 | 20 | return $this->innerHtml(); |
|
72 | 46 | case 'text': |
|
73 | 41 | case 'plaintext': |
|
74 | 21 | return $this->text(); |
|
75 | 29 | case 'tag': |
|
76 | 5 | return $this->node ? $this->node->nodeName : ''; |
|
77 | 27 | case 'attr': |
|
78 | return $this->getAllAttributes(); |
||
79 | 27 | case 'classlist': |
|
80 | 12 | if ($this->classListCache === null) { |
|
81 | 12 | $this->classListCache = new SimpleHtmlAttributes($this->node ?? null, 'class'); |
|
|
|||
82 | } |
||
83 | |||
84 | 12 | return $this->classListCache; |
|
85 | default: |
||
86 | 15 | if ($this->node && \property_exists($this->node, $nameOrig)) { |
|
87 | 2 | if (\is_string($this->node->{$nameOrig})) { |
|
88 | 2 | return HtmlDomParser::putReplacedBackToPreserveHtmlEntities($this->node->{$nameOrig}); |
|
89 | } |
||
90 | |||
91 | return $this->node->{$nameOrig}; |
||
92 | } |
||
93 | |||
94 | 15 | return $this->getAttribute($name); |
|
95 | } |
||
96 | } |
||
97 | |||
98 | /** |
||
99 | * @param string $selector |
||
100 | * @param int $idx |
||
101 | * |
||
102 | * @return SimpleHtmlDomInterface|SimpleHtmlDomInterface[]|SimpleHtmlDomNodeInterface<SimpleHtmlDomInterface> |
||
103 | */ |
||
104 | 12 | public function __invoke($selector, $idx = null) |
|
108 | |||
109 | /** |
||
110 | * @param string $name |
||
111 | * |
||
112 | * @return bool |
||
113 | */ |
||
114 | 1 | View Code Duplication | public function __isset($name) |
136 | |||
137 | /** |
||
138 | * @param string $name |
||
139 | * @param mixed $value |
||
140 | * |
||
141 | * @return SimpleHtmlDomInterface|null |
||
142 | */ |
||
143 | 24 | public function __set($name, $value) |
|
169 | |||
170 | /** |
||
171 | * @return string |
||
172 | */ |
||
173 | 3 | public function __toString() |
|
177 | |||
178 | /** |
||
179 | * @param string $name |
||
180 | * |
||
181 | * @return void |
||
182 | */ |
||
183 | public function __unset($name) |
||
188 | |||
189 | /** |
||
190 | * @param string $selector |
||
191 | * @param int|null $idx |
||
192 | * |
||
193 | * @return mixed |
||
194 | */ |
||
195 | abstract public function find(string $selector, $idx = null); |
||
196 | |||
197 | /** |
||
198 | * @return string[]|null |
||
199 | */ |
||
200 | abstract public function getAllAttributes(); |
||
201 | |||
202 | abstract public function getAttribute(string $name): string; |
||
203 | |||
204 | abstract public function hasAttribute(string $name): bool; |
||
205 | |||
206 | abstract public function html(bool $multiDecodeNewHtmlEntity = false): string; |
||
207 | |||
208 | abstract public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string; |
||
209 | |||
210 | abstract public function removeAttribute(string $name): SimpleHtmlDomInterface; |
||
211 | |||
212 | abstract protected function replaceChildWithString(string $string): SimpleHtmlDomInterface; |
||
213 | |||
214 | abstract protected function replaceNodeWithString(string $string): SimpleHtmlDomInterface; |
||
215 | |||
216 | /** |
||
217 | * @param string $string |
||
218 | * |
||
219 | * @return SimpleHtmlDomInterface |
||
220 | */ |
||
221 | abstract protected function replaceTextWithString($string): SimpleHtmlDomInterface; |
||
222 | |||
223 | /** |
||
224 | * @param string $name |
||
225 | * @param string|null $value |
||
226 | * @param bool $strict |
||
227 | * |
||
228 | * @return SimpleHtmlDomInterface |
||
229 | */ |
||
230 | abstract public function setAttribute(string $name, $value = null, bool $strict = false): SimpleHtmlDomInterface; |
||
231 | |||
232 | abstract public function text(): string; |
||
233 | } |
||
234 |
If a method or function can return multiple different values and unless you are sure that you only can receive a single value in this context, we recommend to add an additional type check:
If this a common case that PHP Analyzer should handle natively, please let us know by opening an issue.