chillerlan /
php-prototype-dom
Complex classes like Document 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 Document, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 23 | /** |
||
| 24 | * @property string $title |
||
| 25 | */ |
||
| 26 | class Document extends DOMDocument{ |
||
| 27 | use Magic; |
||
| 28 | |||
| 29 | protected const NODE_CLASSES = [ |
||
| 30 | 'DOMAttr' => Attr::class, |
||
| 31 | 'DOMCdataSection' => CdataSection::class, |
||
| 32 | 'DOMCharacterData' => CharacterData::class, |
||
| 33 | 'DOMComment' => Comment::class, |
||
| 34 | 'DOMDocumentFragment' => DocumentFragment::class, |
||
| 35 | 'DOMDocumentType' => DocumentType::class, |
||
| 36 | 'DOMElement' => Element::class, |
||
| 37 | 'DOMEntity' => Entity::class, |
||
| 38 | 'DOMEntityReference' => EntityReference::class, |
||
| 39 | 'DOMNode' => Node::class, |
||
| 40 | 'DOMNotation' => Notation::class, |
||
| 41 | 'DOMProcessingInstruction' => ProcessingInstruction::class, |
||
| 42 | 'DOMText' => Text::class, |
||
| 43 | ]; |
||
| 44 | 42 | ||
| 45 | 42 | protected const LOAD_OPTIONS = \LIBXML_COMPACT|\LIBXML_NONET|\LIBXML_HTML_NODEFDTD|\LIBXML_HTML_NOIMPLIED|\LIBXML_NOERROR; |
|
| 46 | |||
| 47 | 42 | /** |
|
| 48 | 42 | * @var \Symfony\Component\CssSelector\CssSelectorConverter |
|
| 49 | */ |
||
| 50 | protected $cssSelectorConverter; |
||
| 51 | 42 | ||
| 52 | 2 | /** |
|
| 53 | * Document constructor. |
||
| 54 | * |
||
| 55 | 42 | * @param \chillerlan\PrototypeDOM\NodeList|\DOMNodeList|string|null $content |
|
| 56 | * @param bool|null $xml |
||
| 57 | * @param string|null $version |
||
| 58 | * @param string|null $encoding |
||
| 59 | */ |
||
| 60 | public function __construct($content = null, bool $xml = null, string $version = null, string $encoding = null){ |
||
| 61 | parent::__construct($version ?? '1.0', $encoding ?? 'UTF-8'); |
||
| 62 | 1 | ||
| 63 | 1 | foreach($this::NODE_CLASSES as $baseClass => $extendedClass){ |
|
| 64 | $this->registerNodeClass($baseClass, $extendedClass); |
||
| 65 | } |
||
| 66 | 1 | ||
| 67 | 1 | if($content !== null){ |
|
| 68 | $this->loadDocument($content, $xml); |
||
| 69 | 1 | } |
|
| 70 | 1 | ||
| 71 | $this->cssSelectorConverter = new CssSelectorConverter; |
||
| 72 | } |
||
| 73 | 1 | ||
| 74 | 1 | ||
| 75 | /********* |
||
| 76 | 1 | * magic * |
|
| 77 | *********/ |
||
| 78 | |||
| 79 | public function magic_get_title():?string{ |
||
| 80 | 1 | return $this->select(['head > title'])->item(0)->nodeValue ?? null; |
|
| 81 | } |
||
| 82 | 1 | ||
| 83 | /** |
||
| 84 | * @param string $title |
||
| 85 | * |
||
| 86 | * @throws \DOMException |
||
| 87 | */ |
||
| 88 | public function magic_set_title(string $title):void{ |
||
| 89 | $currentTitle = $this->select(['head > title'])->item(0); |
||
| 90 | 2 | ||
| 91 | if($currentTitle instanceof Element){ |
||
| 92 | $currentTitle->update($title); |
||
| 93 | 2 | return; |
|
| 94 | 1 | } |
|
| 95 | 1 | ||
| 96 | $head = $this->select(['head'])->item(0); |
||
| 97 | $currentTitle = $this->newElement('title')->update($title); |
||
| 98 | |||
| 99 | if(!$head){ |
||
| 100 | 1 | $html = $this->select(['html'])->first(); |
|
| 101 | 1 | ||
| 102 | if(!$html instanceof PrototypeHTMLElement){ |
||
| 103 | 1 | throw new DOMException('<html> header missing'); |
|
| 104 | 1 | } |
|
| 105 | 1 | ||
| 106 | $head = $this->newElement('head'); |
||
| 107 | 1 | $html->insert_top($head); |
|
| 108 | } |
||
| 109 | |||
| 110 | $head->insert($currentTitle); |
||
| 111 | } |
||
| 112 | |||
| 113 | /** |
||
| 114 | * @param \chillerlan\PrototypeDOM\NodeList|\DOMNodeList|string $content |
||
| 115 | * @param bool $xml |
||
| 116 | 8 | * |
|
| 117 | * @return \chillerlan\PrototypeDOM\Document |
||
| 118 | * @throws \DOMException |
||
| 119 | 8 | */ |
|
| 120 | 8 | ||
| 121 | 7 | public function loadDocument($content, bool $xml = null):Document{ |
|
| 122 | 7 | ||
| 123 | 7 | if($content instanceof NodeList){ |
|
| 124 | return $this->insertNodeList($content); |
||
| 125 | } |
||
| 126 | |||
| 127 | if($content instanceof DOMNodeList){ |
||
| 128 | return $this->insertNodeList(new NodeList($content)); |
||
| 129 | } |
||
| 130 | |||
| 131 | if(!\is_string($content)){ |
||
| 132 | throw new DOMException('invalid document content'); |
||
| 133 | } |
||
| 134 | |||
| 135 | 8 | if(\is_file($content) && \is_readable($content)){ |
|
| 136 | 8 | return $this->loadDocumentFile($content, $xml); |
|
| 137 | 8 | } |
|
| 138 | |||
| 139 | 8 | return $this->loadDocumentString($content, $xml); |
|
| 140 | } |
||
| 141 | |||
| 142 | /** |
||
| 143 | * @param string $file |
||
| 144 | * @param bool|null $xml |
||
| 145 | * @param int|null $options |
||
| 146 | * |
||
| 147 | 3 | * @return \chillerlan\PrototypeDOM\Document |
|
| 148 | 3 | * @throws \DOMException |
|
| 149 | */ |
||
| 150 | 3 | public function loadDocumentFile(string $file, bool $xml = null, int $options = null):Document{ |
|
| 151 | 3 | $options = $options ?? $this::LOAD_OPTIONS; |
|
| 152 | |||
| 153 | $result = $xml === true |
||
| 154 | 3 | ? $this->load($file, $options) |
|
| 155 | : $this->loadHTMLFile($file, $options); |
||
| 156 | |||
| 157 | if($result === false){ |
||
| 158 | throw new DOMException('failed to load document from file: '.$file); // @codeCoverageIgnore |
||
| 159 | } |
||
| 160 | |||
| 161 | return $this; |
||
| 162 | } |
||
| 163 | |||
| 164 | /** |
||
| 165 | * @param string $documentSource |
||
| 166 | * @param bool $xml |
||
| 167 | * @param int|null $options |
||
| 168 | 41 | * |
|
| 169 | 41 | * @return \chillerlan\PrototypeDOM\Document |
|
| 170 | * @throws \DOMException |
||
| 171 | */ |
||
| 172 | public function loadDocumentString(string $documentSource, bool $xml = null, int $options = null):Document{ |
||
| 173 | $options = $options ?? $this::LOAD_OPTIONS; |
||
| 174 | |||
| 175 | $result = $xml === true |
||
| 176 | ? $this->loadXML($documentSource, $options) |
||
| 177 | : $this->loadHTML($documentSource, $options); |
||
| 178 | 41 | ||
| 179 | 41 | if($result === false){ |
|
| 180 | throw new DOMException('failed to load document from string'); // @codeCoverageIgnore |
||
| 181 | } |
||
| 182 | |||
| 183 | return $this; |
||
| 184 | } |
||
| 185 | |||
| 186 | /** |
||
| 187 | * @param mixed $content |
||
| 188 | * |
||
| 189 | 41 | * @return \chillerlan\PrototypeDOM\NodeList |
|
| 190 | 41 | * @throws \Exception |
|
| 191 | */ |
||
| 192 | public function toNodeList($content):NodeList{ |
||
| 193 | |||
| 194 | if($content instanceof NodeList){ |
||
| 195 | return $content; |
||
| 196 | } |
||
| 197 | |||
| 198 | if($content instanceof DOMNode || $content instanceof PrototypeNode){ |
||
| 199 | return new NodeList([$content]); |
||
| 200 | 1 | } |
|
| 201 | 1 | ||
| 202 | if($content instanceof DOMNodeList || \is_iterable($content)){ |
||
| 203 | 1 | return new NodeList($content); |
|
| 204 | } |
||
| 205 | 1 | ||
| 206 | 1 | if(\is_string($content)){ |
|
| 207 | $document = new self; |
||
| 208 | $document->loadHTML('<html><body id="-import-content">'.$content.'</body></html>'); |
||
| 209 | |||
| 210 | return $document->toNodeList($document->getElementById('-import-content')->childNodes); |
||
| 211 | 1 | } |
|
| 212 | |||
| 213 | throw new DOMException('invalid content'); |
||
| 214 | } |
||
| 215 | |||
| 216 | /*********** |
||
| 217 | * generic * |
||
| 218 | ***********/ |
||
| 219 | 2 | ||
| 220 | /** |
||
| 221 | * @param string $selector |
||
| 222 | 2 | * @param string $axis |
|
| 223 | 2 | * |
|
| 224 | * @return string |
||
| 225 | */ |
||
| 226 | 2 | public function selector2xpath(string $selector, string $axis = null):string{ |
|
| 227 | return $this->cssSelectorConverter->toXPath($selector, $axis ?? '//'); |
||
| 228 | } |
||
| 229 | |||
| 230 | /** |
||
| 231 | * @param string $xpath |
||
| 232 | * @param \DOMNode|null $contextNode |
||
| 233 | * |
||
| 234 | * @return \chillerlan\PrototypeDOM\NodeList|null |
||
| 235 | */ |
||
| 236 | public function query(string $xpath, DOMNode $contextNode = null):?NodeList{ |
||
| 237 | $q = (new DOMXPath($this))->query($xpath, $contextNode); |
||
| 238 | |||
| 239 | return $q !== false ? new NodeList($q) : null; |
||
| 240 | } |
||
| 241 | 8 | ||
| 242 | 8 | /** |
|
| 243 | 2 | * @param string $selector |
|
| 244 | 8 | * @param \DOMNode|null $contextNode |
|
| 245 | * @param string $axis |
||
| 246 | * |
||
| 247 | * @return \chillerlan\PrototypeDOM\NodeList|null |
||
| 248 | */ |
||
| 249 | public function querySelectorAll(string $selector, DOMNode $contextNode = null, string $axis = null):?NodeList{ |
||
| 250 | return $this->query($this->cssSelectorConverter->toXPath($selector, $axis ?? 'descendant-or-self::'), $contextNode); |
||
| 251 | } |
||
| 252 | |||
| 253 | /** |
||
| 254 | * @param string|array $selectors |
||
| 255 | * @param \DOMNode|null $contextNode |
||
| 256 | * @param string $axis |
||
| 257 | 41 | * |
|
| 258 | * @return \chillerlan\PrototypeDOM\Document |
||
| 259 | 41 | */ |
|
| 260 | 41 | public function removeElementsBySelector($selectors, DOMNode $contextNode = null, string $axis = null):Document{ |
|
| 261 | /** @var \chillerlan\PrototypeDOM\NodeList $nodes */ |
||
| 262 | $nodes = $this->select($selectors, $contextNode, $axis ?? 'descendant-or-self::'); |
||
| 263 | 41 | ||
| 264 | 2 | if(\count($nodes) > 0){ |
|
| 265 | |||
| 266 | foreach($nodes as $node){ |
||
| 267 | 41 | $node->remove(); |
|
| 268 | } |
||
| 269 | 41 | ||
| 270 | } |
||
| 271 | 41 | ||
| 272 | return $this; |
||
| 273 | 41 | } |
|
| 274 | 41 | ||
| 275 | /** |
||
| 276 | * @param \chillerlan\PrototypeDOM\NodeList $nodeList |
||
| 277 | * |
||
| 278 | * @return \chillerlan\PrototypeDOM\Document |
||
| 279 | */ |
||
| 280 | public function insertNodeList(NodeList $nodeList):Document{ |
||
| 281 | 41 | ||
| 282 | /** @var \DOMNode $node */ |
||
| 283 | foreach($nodeList as $node){ |
||
| 284 | $this->appendChild($this->importNode($node->cloneNode(true), true)); |
||
| 285 | } |
||
| 286 | |||
| 287 | return $this; |
||
| 288 | } |
||
| 289 | |||
| 290 | /************* |
||
| 291 | * prototype * |
||
| 292 | *************/ |
||
| 293 | |||
| 294 | 3 | /** |
|
| 295 | 3 | * @link http://api.prototypejs.org/dom/Element/inspect/ |
|
| 296 | * |
||
| 297 | 3 | * @param \DOMNode|null $context |
|
| 298 | * @param bool $xml |
||
| 299 | 3 | * |
|
| 300 | * @return string |
||
| 301 | 3 | */ |
|
| 302 | 3 | public function inspect(DOMNode $context = null, bool $xml = null):string{ |
|
| 303 | |||
| 304 | if($xml === true){ |
||
| 305 | 3 | return $this->saveXML($context); |
|
| 306 | 2 | } |
|
| 307 | |||
| 308 | return $this->saveHTML($context); |
||
| 309 | } |
||
| 310 | |||
| 311 | /** |
||
| 312 | * @link http://api.prototypejs.org/dom/Element/select/ |
||
| 313 | 3 | * |
|
| 314 | * @param string|array $selectors |
||
| 315 | * @param \DOMNode|null $contextNode |
||
| 316 | * @param string $axis |
||
| 317 | * @param int $nodeType https://secure.php.net/manual/dom.constants.php |
||
| 318 | * |
||
| 319 | * @return \chillerlan\PrototypeDOM\NodeList |
||
| 320 | */ |
||
| 321 | public function select(array $selectors = null, DOMNode $contextNode = null, string $axis = null, int $nodeType = \XML_ELEMENT_NODE):NodeList{ |
||
| 322 | $elements = new NodeList; |
||
| 323 | |||
| 324 | foreach($selectors ?? ['*'] as $selector){ |
||
| 325 | 4 | ||
| 326 | if(!\is_string($selector)){ |
||
| 327 | 4 | continue; |
|
| 328 | } |
||
| 329 | |||
| 330 | 4 | foreach($this->querySelectorAll($selector, $contextNode, $axis ?? 'descendant-or-self::') as $element){ |
|
| 331 | |||
| 332 | 4 | if($element->nodeType === $nodeType){ |
|
| 333 | 4 | $elements[] = $element; |
|
| 334 | } |
||
| 335 | |||
| 336 | 4 | } |
|
| 337 | |||
| 338 | } |
||
| 339 | |||
| 340 | return $elements; |
||
| 341 | 4 | } |
|
| 342 | |||
| 343 | /** |
||
| 344 | * @link http://api.prototypejs.org/dom/Element/recursivelyCollect/ |
||
| 345 | * |
||
| 346 | * @param \chillerlan\PrototypeDOM\Node\PrototypeNode $element |
||
| 347 | * @param string $property |
||
| 348 | * @param int $maxLength |
||
| 349 | * @param int $nodeType https://secure.php.net/manual/dom.constants.php |
||
| 350 | * |
||
| 351 | * @return \chillerlan\PrototypeDOM\NodeList |
||
| 352 | 4 | */ |
|
| 353 | public function recursivelyCollect(PrototypeNode $element, string $property, int $maxLength = -1, int $nodeType = \XML_ELEMENT_NODE):NodeList{ |
||
| 354 | 4 | $nodes = new NodeList; |
|
| 355 | |||
| 356 | 4 | if(\in_array($property, ['parentNode', 'previousSibling', 'nextSibling'])){ |
|
| 357 | 4 | ||
| 358 | while($element = $element->{$property}){ |
||
| 359 | |||
| 360 | if($element->nodeType === $nodeType){ |
||
| 361 | $nodes[] = $element; |
||
| 362 | 4 | } |
|
| 363 | |||
| 364 | if(\count($nodes) === $maxLength){ |
||
| 365 | break; |
||
| 366 | } |
||
| 367 | |||
| 368 | } |
||
| 369 | |||
| 370 | } |
||
| 371 | |||
| 372 | return $nodes; |
||
| 373 | 6 | } |
|
| 374 | |||
| 375 | 6 | /** |
|
| 376 | * @param \chillerlan\PrototypeDOM\Node\PrototypeNode $element |
||
| 377 | 6 | * @param string $property |
|
| 378 | 4 | * @param string|null $selector |
|
| 379 | * @param int $index |
||
| 380 | * @param int $nodeType https://secure.php.net/manual/dom.constants.php |
||
| 381 | 6 | * |
|
| 382 | * @return \chillerlan\PrototypeDOM\Node\PrototypeNode|null |
||
| 383 | */ |
||
| 384 | public function recursivelyFind(PrototypeNode $element, string $property = null, string $selector = null, int $index = 0, int $nodeType = \XML_ELEMENT_NODE):?PrototypeNode{ |
||
| 385 | |||
| 460 |
Loading history...