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 |
||
| 18 | abstract class AbstractNode |
||
| 19 | { |
||
| 20 | |||
| 21 | /** |
||
| 22 | * Contains the tag name/type |
||
| 23 | * |
||
| 24 | * @var \PHPHtmlParser\Dom\Tag |
||
| 25 | */ |
||
| 26 | protected $tag; |
||
| 27 | |||
| 28 | /** |
||
| 29 | * Contains a list of attributes on this tag. |
||
| 30 | * |
||
| 31 | * @var array |
||
| 32 | */ |
||
| 33 | protected $attr = []; |
||
| 34 | |||
| 35 | /** |
||
| 36 | * Contains the parent Node. |
||
| 37 | * |
||
| 38 | * @var InnerNode |
||
| 39 | */ |
||
| 40 | protected $parent = null; |
||
| 41 | |||
| 42 | /** |
||
| 43 | * The unique id of the class. Given by PHP. |
||
| 44 | * |
||
| 45 | * @var string |
||
| 46 | */ |
||
| 47 | protected $id; |
||
| 48 | |||
| 49 | /** |
||
| 50 | * The encoding class used to encode strings. |
||
| 51 | * |
||
| 52 | * @var mixed |
||
| 53 | */ |
||
| 54 | protected $encode; |
||
| 55 | |||
| 56 | /** |
||
| 57 | * Creates a unique spl hash for this node. |
||
| 58 | */ |
||
| 59 | public function __construct() |
||
| 63 | |||
| 64 | /** |
||
| 65 | * Magic get method for attributes and certain methods. |
||
| 66 | * |
||
| 67 | * @param string $key |
||
| 68 | * @return mixed |
||
| 69 | */ |
||
| 70 | public function __get($key) |
||
| 90 | |||
| 91 | /** |
||
| 92 | * Attempts to clear out any object references. |
||
| 93 | */ |
||
| 94 | public function __destruct() |
||
| 101 | |||
| 102 | /** |
||
| 103 | * Simply calls the outer text method. |
||
| 104 | * |
||
| 105 | * @return string |
||
| 106 | */ |
||
| 107 | public function __toString() |
||
| 111 | |||
| 112 | /** |
||
| 113 | * Returns the id of this object. |
||
| 114 | */ |
||
| 115 | public function id() |
||
| 119 | |||
| 120 | /** |
||
| 121 | * Returns the parent of node. |
||
| 122 | * |
||
| 123 | * @return AbstractNode |
||
| 124 | */ |
||
| 125 | public function getParent() |
||
| 129 | |||
| 130 | /** |
||
| 131 | * Sets the parent node. |
||
| 132 | * |
||
| 133 | * @param InnerNode $parent |
||
| 134 | * @return $this |
||
| 135 | * @throws CircularException |
||
| 136 | */ |
||
| 137 | public function setParent(InnerNode $parent) |
||
| 159 | |||
| 160 | /** |
||
| 161 | * Removes this node and all its children from the |
||
| 162 | * DOM tree. |
||
| 163 | * |
||
| 164 | * @return void |
||
| 165 | */ |
||
| 166 | public function delete() |
||
| 174 | |||
| 175 | /** |
||
| 176 | * Sets the encoding class to this node. |
||
| 177 | * |
||
| 178 | * @param Encode $encode |
||
| 179 | * @return void |
||
| 180 | */ |
||
| 181 | public function propagateEncoding(Encode $encode) |
||
| 186 | |||
| 187 | /** |
||
| 188 | * Checks if the given node id is an ancestor of |
||
| 189 | * the current node. |
||
| 190 | * |
||
| 191 | * @param int $id |
||
| 192 | * @return bool |
||
| 193 | */ |
||
| 194 | public function isAncestor($id) |
||
| 202 | |||
| 203 | /** |
||
| 204 | * Attempts to get an ancestor node by the given id. |
||
| 205 | * |
||
| 206 | * @param int $id |
||
| 207 | * @return null|AbstractNode |
||
| 208 | */ |
||
| 209 | public function getAncestor($id) |
||
| 221 | |||
| 222 | /** |
||
| 223 | * Attempts to get the next sibling. |
||
| 224 | * |
||
| 225 | * @return AbstractNode |
||
| 226 | * @throws ParentNotFoundException |
||
| 227 | */ |
||
| 228 | public function nextSibling() |
||
| 236 | |||
| 237 | /** |
||
| 238 | * Attempts to get the previous sibling |
||
| 239 | * |
||
| 240 | * @return AbstractNode |
||
| 241 | * @throws ParentNotFoundException |
||
| 242 | */ |
||
| 243 | public function previousSibling() |
||
| 251 | |||
| 252 | /** |
||
| 253 | * Gets the tag object of this node. |
||
| 254 | * |
||
| 255 | * @return Tag |
||
| 256 | */ |
||
| 257 | public function getTag() |
||
| 261 | |||
| 262 | /** |
||
| 263 | * A wrapper method that simply calls the getAttribute method |
||
| 264 | * on the tag of this node. |
||
| 265 | * |
||
| 266 | * @return array |
||
| 267 | */ |
||
| 268 | public function getAttributes() |
||
| 277 | |||
| 278 | /** |
||
| 279 | * A wrapper method that simply calls the getAttribute method |
||
| 280 | * on the tag of this node. |
||
| 281 | * |
||
| 282 | * @param string $key |
||
| 283 | * @return mixed |
||
| 284 | */ |
||
| 285 | public function getAttribute($key) |
||
| 294 | |||
| 295 | /** |
||
| 296 | * A wrapper method that simply calls the setAttribute method |
||
| 297 | * on the tag of this node. |
||
| 298 | * |
||
| 299 | * @param string $key |
||
| 300 | * @param string $value |
||
| 301 | * @return $this |
||
| 302 | */ |
||
| 303 | public function setAttribute($key, $value) |
||
| 309 | |||
| 310 | /** |
||
| 311 | * A wrapper method that simply calls the removeAttribute method |
||
| 312 | * on the tag of this node. |
||
| 313 | * |
||
| 314 | * @param string $key |
||
| 315 | * @return void |
||
| 316 | */ |
||
| 317 | public function removeAttribute($key) |
||
| 321 | |||
| 322 | /** |
||
| 323 | * A wrapper method that simply calls the removeAllAttributes |
||
| 324 | * method on the tag of this node. |
||
| 325 | * |
||
| 326 | * @return void |
||
| 327 | */ |
||
| 328 | public function removeAllAttributes() |
||
| 332 | |||
| 333 | /** |
||
| 334 | * Function to locate a specific ancestor tag in the path to the root. |
||
| 335 | * |
||
| 336 | * @param string $tag |
||
| 337 | * @return AbstractNode |
||
| 338 | * @throws ParentNotFoundException |
||
| 339 | */ |
||
| 340 | public function ancestorByTag($tag) |
||
| 355 | |||
| 356 | /** |
||
| 357 | * Find elements by css selector |
||
| 358 | * |
||
| 359 | * @param string $selector |
||
| 360 | * @param int $nth |
||
| 361 | * @return array|AbstractNode |
||
| 362 | */ |
||
| 363 | public function find($selector, $nth = null) |
||
| 379 | |||
| 380 | /** |
||
| 381 | * Function to try a few tricks to determine the displayed size of an img on the page. |
||
| 382 | * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. |
||
| 383 | * |
||
| 384 | * Future enhancement: |
||
| 385 | * Look in the tag to see if there is a class or id specified that has a height or width attribute to it. |
||
| 386 | * |
||
| 387 | * Far future enhancement |
||
| 388 | * 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 |
||
| 389 | * Note that in this case, the class or id will have the img sub-selector for it to apply to the image. |
||
| 390 | * |
||
| 391 | * ridiculously far future development |
||
| 392 | * 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. |
||
| 393 | * |
||
| 394 | * @author John Schlick |
||
| 395 | * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. |
||
| 396 | */ |
||
| 397 | public function get_display_size() |
||
| 436 | |||
| 437 | /** |
||
| 438 | * If there is a length in the style attributes use it. |
||
| 439 | * |
||
| 440 | * @param array $attributes |
||
| 441 | * @param int $length |
||
| 442 | * @param string $key |
||
| 443 | * @return int |
||
| 444 | */ |
||
| 445 | protected function getLength(array $attributes, $length, $key) |
||
| 460 | |||
| 461 | /** |
||
| 462 | * Gets the inner html of this node. |
||
| 463 | * |
||
| 464 | * @return string |
||
| 465 | */ |
||
| 466 | abstract public function innerHtml(); |
||
| 467 | |||
| 468 | /** |
||
| 469 | * Gets the html of this node, including it's own |
||
| 470 | * tag. |
||
| 471 | * |
||
| 472 | * @return string |
||
| 473 | */ |
||
| 474 | abstract public function outerHtml(); |
||
| 475 | |||
| 476 | /** |
||
| 477 | * Gets the text of this node (if there is any text). |
||
| 478 | * |
||
| 479 | * @return string |
||
| 480 | */ |
||
| 481 | abstract public function text(); |
||
| 482 | |||
| 483 | /** |
||
| 484 | * Call this when something in the node tree has changed. Like a child has been added |
||
| 485 | * or a parent has been changed. |
||
| 486 | * |
||
| 487 | * @return void |
||
| 488 | */ |
||
| 489 | abstract protected function clear(); |
||
| 490 | } |
||
| 491 |
PHP Analyzer performs a side-effects analysis of your code. A side-effect is basically anything that might be visible after the scope of the method is left.
Let’s take a look at an example:
If we look at the
getEmail()method, we can see that it has no side-effect. Whether you call this method or not, no future calls to other methods are affected by this. As such code as the following is useless:On the hand, if we look at the
setEmail(), this method _has_ side-effects. In the following case, we could not remove the method call: