Complex classes like Element 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 Element, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 5 | class Element implements ElementInterface |
||
| 6 | { |
||
| 7 | /** |
||
| 8 | * @var \DOMNode |
||
| 9 | */ |
||
| 10 | protected $node; |
||
| 11 | |||
| 12 | /** |
||
| 13 | * @var ElementInterface|null |
||
| 14 | */ |
||
| 15 | private $nextCached; |
||
| 16 | |||
| 17 | 75 | public function __construct(\DOMNode $node) |
|
| 18 | { |
||
| 19 | 75 | $this->node = $node; |
|
| 20 | 75 | } |
|
| 21 | |||
| 22 | /** |
||
| 23 | * @return bool |
||
| 24 | */ |
||
| 25 | 9 | public function isBlock() |
|
| 26 | { |
||
| 27 | 9 | switch ($this->getTagName()) { |
|
| 28 | 9 | case 'blockquote': |
|
| 29 | 9 | case 'body': |
|
| 30 | 9 | case 'code': |
|
| 31 | 9 | case 'div': |
|
| 32 | 9 | case 'h1': |
|
| 33 | 9 | case 'h2': |
|
| 34 | 9 | case 'h3': |
|
| 35 | 9 | case 'h4': |
|
| 36 | 9 | case 'h5': |
|
| 37 | 9 | case 'h6': |
|
| 38 | 9 | case 'hr': |
|
| 39 | 9 | case 'html': |
|
| 40 | 9 | case 'li': |
|
| 41 | 9 | case 'p': |
|
| 42 | 9 | case 'ol': |
|
| 43 | 9 | case 'ul': |
|
| 44 | 3 | return true; |
|
| 45 | 6 | default: |
|
| 46 | 6 | return false; |
|
| 47 | 6 | } |
|
| 48 | } |
||
| 49 | |||
| 50 | /** |
||
| 51 | * @return bool |
||
| 52 | */ |
||
| 53 | public function isText() |
||
| 54 | { |
||
| 55 | return $this->getTagName() === '#text'; |
||
| 56 | } |
||
| 57 | |||
| 58 | /** |
||
| 59 | * @return bool |
||
| 60 | */ |
||
| 61 | 6 | public function isWhitespace() |
|
| 62 | { |
||
| 63 | 6 | return $this->getTagName() === '#text' && trim($this->getValue()) === ''; |
|
| 64 | } |
||
| 65 | |||
| 66 | /** |
||
| 67 | * @return string |
||
| 68 | */ |
||
| 69 | 75 | public function getTagName() |
|
| 70 | { |
||
| 71 | 75 | return $this->node->nodeName; |
|
| 72 | } |
||
| 73 | |||
| 74 | /** |
||
| 75 | * @return string |
||
| 76 | */ |
||
| 77 | 63 | public function getValue() |
|
| 78 | { |
||
| 79 | 63 | return $this->node->nodeValue; |
|
| 80 | } |
||
| 81 | |||
| 82 | /** |
||
| 83 | * @return ElementInterface|null |
||
| 84 | */ |
||
| 85 | 6 | public function getParent() |
|
| 86 | { |
||
| 87 | 6 | return new static($this->node->parentNode) ?: null; |
|
| 88 | } |
||
| 89 | |||
| 90 | /** |
||
| 91 | * @return bool |
||
| 92 | */ |
||
| 93 | 75 | public function hasChildren() |
|
| 94 | { |
||
| 95 | 75 | return $this->node->hasChildNodes(); |
|
| 96 | } |
||
| 97 | |||
| 98 | /** |
||
| 99 | * @return ElementInterface[] |
||
| 100 | */ |
||
| 101 | 75 | public function getChildren() |
|
| 102 | { |
||
| 103 | 75 | $ret = array(); |
|
| 104 | /** @var \DOMNode $node */ |
||
| 105 | 75 | foreach ($this->node->childNodes as $node) { |
|
| 106 | 75 | $ret[] = new static($node); |
|
| 107 | 75 | } |
|
| 108 | |||
| 109 | 75 | return $ret; |
|
| 110 | } |
||
| 111 | |||
| 112 | /** |
||
| 113 | * @return ElementInterface|null |
||
| 114 | */ |
||
| 115 | 9 | public function getNext() |
|
| 116 | { |
||
| 117 | 9 | if ($this->nextCached === null) { |
|
| 118 | 9 | $nextNode = $this->getNextNode($this->node); |
|
| 119 | 9 | if ($nextNode !== null) { |
|
| 120 | 9 | $this->nextCached = new static($nextNode); |
|
| 121 | 9 | } |
|
| 122 | 9 | } |
|
| 123 | |||
| 124 | 9 | return $this->nextCached; |
|
| 125 | } |
||
| 126 | |||
| 127 | /** |
||
| 128 | * @param \DomNode $node |
||
| 129 | * |
||
| 130 | * @return \DomNode|null |
||
| 131 | */ |
||
| 132 | 9 | private function getNextNode($node, $checkChildren = true) |
|
| 133 | { |
||
| 134 | 9 | if ($checkChildren && $node->firstChild) { |
|
| 135 | return $node->firstChild; |
||
| 136 | 9 | } elseif ($node->nextSibling) { |
|
| 137 | 9 | return $node->nextSibling; |
|
| 138 | } elseif ($node->parentNode) { |
||
| 139 | return $this->getNextNode($node->parentNode, false); |
||
| 140 | } |
||
| 141 | } |
||
| 142 | |||
| 143 | /** |
||
| 144 | * @param string[]|string $tagNames |
||
| 145 | * |
||
| 146 | * @return bool |
||
| 147 | */ |
||
| 148 | 75 | public function isDescendantOf($tagNames) |
|
| 149 | { |
||
| 150 | 75 | if (!is_array($tagNames)) { |
|
| 151 | 3 | $tagNames = array($tagNames); |
|
| 152 | 3 | } |
|
| 153 | |||
| 154 | 75 | for ($p = $this->node->parentNode; $p !== false; $p = $p->parentNode) { |
|
| 155 | 75 | if (is_null($p)) { |
|
| 156 | 75 | return false; |
|
| 157 | } |
||
| 158 | |||
| 159 | 75 | if (in_array($p->nodeName, $tagNames)) { |
|
| 160 | 18 | return true; |
|
| 161 | } |
||
| 162 | 75 | } |
|
| 163 | |||
| 164 | return false; |
||
| 165 | } |
||
| 166 | |||
| 167 | /** |
||
| 168 | * @param string $markdown |
||
| 169 | */ |
||
| 170 | 75 | public function setFinalMarkdown($markdown) |
|
| 171 | { |
||
| 172 | 75 | $markdown_node = $this->node->ownerDocument->createTextNode($markdown); |
|
| 173 | 75 | $this->node->parentNode->replaceChild($markdown_node, $this->node); |
|
| 174 | 75 | } |
|
| 175 | |||
| 176 | /** |
||
| 177 | * @return string |
||
| 178 | */ |
||
| 179 | 66 | public function getChildrenAsString() |
|
| 180 | { |
||
| 181 | 66 | return $this->node->C14N(); |
|
| 182 | } |
||
| 183 | |||
| 184 | /** |
||
| 185 | * @return int |
||
| 186 | */ |
||
| 187 | 6 | public function getSiblingPosition() |
|
| 188 | { |
||
| 189 | 6 | $position = 0; |
|
| 190 | |||
| 191 | // Loop through all nodes and find the given $node |
||
| 192 | 6 | foreach ($this->getParent()->getChildren() as $current_node) { |
|
| 193 | 6 | if (!$current_node->isWhitespace()) { |
|
| 194 | 6 | $position++; |
|
| 195 | 6 | } |
|
| 196 | |||
| 197 | // TODO: Need a less-buggy way of comparing these |
||
| 198 | // Perhaps we can somehow ensure that we always have the exact same object and use === instead? |
||
| 199 | 6 | if ($this->equals($current_node)) { |
|
| 200 | 6 | break; |
|
| 201 | } |
||
| 202 | 6 | } |
|
| 203 | |||
| 204 | 6 | return $position; |
|
| 205 | } |
||
| 206 | |||
| 207 | /** |
||
| 208 | * @return int |
||
| 209 | */ |
||
| 210 | 6 | public function getListItemLevel() |
|
| 224 | |||
| 225 | /** |
||
| 226 | * @param string $name |
||
| 227 | * |
||
| 228 | * @return string |
||
| 229 | */ |
||
| 230 | 18 | public function getAttribute($name) |
|
| 231 | { |
||
| 232 | 18 | if ($this->node instanceof \DOMElement) { |
|
| 233 | 18 | return $this->node->getAttribute($name); |
|
| 234 | } |
||
| 235 | |||
| 236 | return ''; |
||
| 237 | } |
||
| 238 | |||
| 239 | /** |
||
| 240 | * @param ElementInterface $element |
||
| 241 | * |
||
| 242 | * @return bool |
||
| 243 | */ |
||
| 244 | 6 | public function equals(ElementInterface $element) |
|
| 252 | } |
||
| 253 |