Complex classes like AbstractNode 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 AbstractNode, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
16 | abstract class AbstractNode |
||
17 | { |
||
18 | |||
19 | /** |
||
20 | * Contains the tag name/type |
||
21 | * |
||
22 | * @var \PHPHtmlParser\Dom\Tag |
||
23 | */ |
||
24 | protected $tag; |
||
25 | |||
26 | /** |
||
27 | * Contains a list of attributes on this tag. |
||
28 | * |
||
29 | * @var array |
||
30 | */ |
||
31 | protected $attr = []; |
||
32 | |||
33 | /** |
||
34 | * Contains the parent Node. |
||
35 | * |
||
36 | * @var InnerNode |
||
37 | */ |
||
38 | protected $parent = null; |
||
39 | |||
40 | /** |
||
41 | * The unique id of the class. Given by PHP. |
||
42 | * |
||
43 | * @var string |
||
44 | */ |
||
45 | protected $id; |
||
46 | |||
47 | /** |
||
48 | * The encoding class used to encode strings. |
||
49 | * |
||
50 | * @var mixed |
||
51 | */ |
||
52 | protected $encode; |
||
53 | |||
54 | /** |
||
55 | * Creates a unique spl hash for this node. |
||
56 | */ |
||
57 | public function __construct() |
||
61 | |||
62 | /** |
||
63 | * Magic get method for attributes and certain methods. |
||
64 | * |
||
65 | * @param string $key |
||
66 | * @return mixed |
||
67 | */ |
||
68 | public function __get($key) |
||
85 | |||
86 | /** |
||
87 | * Attempts to clear out any object references. |
||
88 | */ |
||
89 | public function __destruct() |
||
96 | |||
97 | /** |
||
98 | * Simply calls the outer text method. |
||
99 | * |
||
100 | * @return string |
||
101 | */ |
||
102 | public function __toString() |
||
106 | |||
107 | /** |
||
108 | * Returns the id of this object. |
||
109 | */ |
||
110 | public function id() |
||
114 | |||
115 | /** |
||
116 | * Returns the parent of node. |
||
117 | * |
||
118 | * @return AbstractNode |
||
119 | */ |
||
120 | public function getParent() |
||
124 | |||
125 | /** |
||
126 | * Sets the parent node. |
||
127 | * |
||
128 | * @param InnerNode $parent |
||
129 | * @return $this |
||
130 | * @throws CircularException |
||
131 | */ |
||
132 | public function setParent(InnerNode $parent) |
||
154 | |||
155 | /** |
||
156 | * Sets the encoding class to this node. |
||
157 | * |
||
158 | * @param Encode $encode |
||
159 | * @return void |
||
160 | */ |
||
161 | public function propagateEncoding(Encode $encode) |
||
166 | |||
167 | /** |
||
168 | * Checks if the given node id is an ancestor of |
||
169 | * the current node. |
||
170 | * |
||
171 | * @param int $id |
||
172 | * @return bool |
||
173 | */ |
||
174 | public function isAncestor($id) |
||
182 | |||
183 | /** |
||
184 | * Attempts to get an ancestor node by the given id. |
||
185 | * |
||
186 | * @param int $id |
||
187 | * @return null|AbstractNode |
||
188 | */ |
||
189 | public function getAncestor($id) |
||
201 | |||
202 | /** |
||
203 | * Shortcut to return the first child. |
||
204 | * |
||
205 | * @return AbstractNode |
||
206 | * @uses $this->getChild() |
||
207 | */ |
||
208 | public function firstChild() |
||
215 | |||
216 | /** |
||
217 | * Attempts to get the last child. |
||
218 | * |
||
219 | * @return AbstractNode |
||
220 | */ |
||
221 | public function lastChild() |
||
228 | |||
229 | /** |
||
230 | * Attempts to get the next sibling. |
||
231 | * |
||
232 | * @return AbstractNode |
||
233 | * @throws ParentNotFoundException |
||
234 | */ |
||
235 | public function nextSibling() |
||
243 | |||
244 | /** |
||
245 | * Attempts to get the previous sibling |
||
246 | * |
||
247 | * @return AbstractNode |
||
248 | * @throws ParentNotFoundException |
||
249 | */ |
||
250 | public function previousSibling() |
||
258 | |||
259 | /** |
||
260 | * Gets the tag object of this node. |
||
261 | * |
||
262 | * @return Tag |
||
263 | */ |
||
264 | public function getTag() |
||
268 | |||
269 | /** |
||
270 | * A wrapper method that simply calls the getAttribute method |
||
271 | * on the tag of this node. |
||
272 | * |
||
273 | * @return array |
||
274 | */ |
||
275 | public function getAttributes() |
||
284 | |||
285 | /** |
||
286 | * A wrapper method that simply calls the getAttribute method |
||
287 | * on the tag of this node. |
||
288 | * |
||
289 | * @param string $key |
||
290 | * @return mixed |
||
291 | */ |
||
292 | public function getAttribute($key) |
||
301 | |||
302 | /** |
||
303 | * A wrapper method that simply calls the setAttribute method |
||
304 | * on the tag of this node. |
||
305 | * |
||
306 | * @param string $key |
||
307 | * @param string $value |
||
308 | * @return $this |
||
309 | */ |
||
310 | public function setAttribute($key, $value) |
||
316 | |||
317 | /** |
||
318 | * Function to locate a specific ancestor tag in the path to the root. |
||
319 | * |
||
320 | * @param string $tag |
||
321 | * @return AbstractNode |
||
322 | * @throws ParentNotFoundException |
||
323 | */ |
||
324 | public function ancestorByTag($tag) |
||
339 | |||
340 | /** |
||
341 | * Find elements by css selector |
||
342 | * |
||
343 | * @param string $selector |
||
344 | * @param int $nth |
||
345 | * @return array|AbstractNode |
||
346 | */ |
||
347 | public function find($selector, $nth = null) |
||
363 | |||
364 | /** |
||
365 | * Function to try a few tricks to determine the displayed size of an img on the page. |
||
366 | * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. |
||
367 | * |
||
368 | * Future enhancement: |
||
369 | * Look in the tag to see if there is a class or id specified that has a height or width attribute to it. |
||
370 | * |
||
371 | * Far future enhancement |
||
372 | * Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width |
||
373 | * Note that in this case, the class or id will have the img sub-selector for it to apply to the image. |
||
374 | * |
||
375 | * ridiculously far future development |
||
376 | * If the class or id is specified in a SEPARATE css file that's not on the page, go get it and do what we were just doing for the ones on the page. |
||
377 | * |
||
378 | * @author John Schlick |
||
379 | * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. |
||
380 | */ |
||
381 | public function get_display_size() |
||
420 | |||
421 | /** |
||
422 | * If there is a length in the style attributes use it. |
||
423 | * |
||
424 | * @param array $attributes |
||
425 | * @param int $length |
||
426 | * @param string $key |
||
427 | * @return int |
||
428 | */ |
||
429 | protected function getLength(array $attributes, $length, $key) |
||
444 | |||
445 | /** |
||
446 | * Gets the inner html of this node. |
||
447 | * |
||
448 | * @return string |
||
449 | */ |
||
450 | abstract public function innerHtml(); |
||
451 | |||
452 | /** |
||
453 | * Gets the html of this node, including it's own |
||
454 | * tag. |
||
455 | * |
||
456 | * @return string |
||
457 | */ |
||
458 | abstract public function outerHtml(); |
||
459 | |||
460 | /** |
||
461 | * Gets the text of this node (if there is any text). |
||
462 | * |
||
463 | * @return string |
||
464 | */ |
||
465 | abstract public function text(); |
||
466 | |||
467 | /** |
||
468 | * Call this when something in the node tree has changed. Like a child has been added |
||
469 | * or a parent has been changed. |
||
470 | * |
||
471 | * @return void |
||
472 | */ |
||
473 | abstract protected function clear(); |
||
474 | } |
||
475 |
In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code:
Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: