elkarte /
Elkarte
| Total Complexity | 64 |
| Total Lines | 444 |
| Duplicated Lines | 0 % |
| Changes | 1 | ||
| Bugs | 0 | Features | 0 |
Complex classes like AbstractDomParser 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.
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 AbstractDomParser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 22 | abstract class AbstractDomParser |
||
| 23 | { |
||
| 24 | /** @var object The object that holds the dom */ |
||
| 25 | public $document; |
||
| 26 | |||
| 27 | /** @var bool If we are using the internal or external parser */ |
||
| 28 | public $internalParser; |
||
| 29 | |||
| 30 | /** @var string Line end character */ |
||
| 31 | public $line_end = "\n"; |
||
| 32 | |||
| 33 | /** @var string Line break character */ |
||
| 34 | public $line_break = " \n\n"; |
||
| 35 | |||
| 36 | /** @var int Wordwrap output, set to 0 to skip wrapping */ |
||
| 37 | public $body_width = 76; |
||
| 38 | |||
| 39 | /** |
||
| 40 | * For a given node, checks if it is anywhere nested inside a code block |
||
| 41 | * |
||
| 42 | * - Prevents converting anything that's inside a code block |
||
| 43 | * |
||
| 44 | * @param object $node |
||
| 45 | * |
||
| 46 | * @return bool |
||
| 47 | */ |
||
| 48 | public static function hasParentCode($node, $internalParser) |
||
| 49 | { |
||
| 50 | $parent = $internalParser ? $node->parentNode : $node->parentNode(); |
||
| 51 | while ($parent) |
||
| 52 | { |
||
| 53 | // Anywhere nested inside a code/pre block we don't render tags |
||
| 54 | if (in_array($internalParser ? $parent->nodeName : $parent->nodeName(), ['pre', 'code'])) |
||
| 55 | { |
||
| 56 | return true; |
||
| 57 | } |
||
| 58 | |||
| 59 | // Back out another level, until we are done |
||
| 60 | $parent = $internalParser ? $parent->parentNode : $parent->parentNode(); |
||
| 61 | } |
||
| 62 | |||
| 63 | return false; |
||
| 64 | } |
||
| 65 | |||
| 66 | /** |
||
| 67 | * Set the DOM parser for class, loads the supplied HTML |
||
| 68 | */ |
||
| 69 | public function setParser() |
||
| 78 | } |
||
| 79 | } |
||
| 80 | |||
| 81 | /** |
||
| 82 | * Loads a string of HTML into the parser for processing |
||
| 83 | * |
||
| 84 | * @param string $html |
||
| 85 | */ |
||
| 86 | public function loadHTML($html) |
||
| 110 | } |
||
| 111 | } |
||
| 112 | |||
| 113 | /** |
||
| 114 | * Returns just the body of a html document such that we are not dealing with head |
||
| 115 | * and any above head markup. multipart/mixed may have multiple sections that we concatenate |
||
| 116 | * |
||
| 117 | * @param $text |
||
| 118 | * |
||
| 119 | * @return string |
||
| 120 | */ |
||
| 121 | public function getBodyText($text) |
||
| 122 | { |
||
| 123 | if (preg_match_all('~<body[^>]*?>(.*?)</body>~su', $text, $bodies)) |
||
| 124 | { |
||
| 125 | return implode("\n", $bodies[1]); |
||
| 126 | } |
||
| 127 | |||
| 128 | if (preg_match_all('~<html[^>]*?>(.*)</html>~su', $text, $bodies)) |
||
| 129 | { |
||
| 130 | return implode("\n", $bodies[1]); |
||
| 131 | } |
||
| 132 | |||
| 133 | // Parsers may have clipped the ending body or html tag off with the quote/signature |
||
| 134 | if (preg_match('~<body[^>]*?>(.*)~su', $text, $bodies)) |
||
| 135 | { |
||
| 136 | return $bodies[1]; |
||
| 137 | } |
||
| 138 | |||
| 139 | return $text; |
||
| 140 | } |
||
| 141 | |||
| 142 | /** |
||
| 143 | * Returns just the body of a dom object such that we are not dealing with head |
||
| 144 | * and any above head markup |
||
| 145 | * |
||
| 146 | * @return object |
||
| 147 | */ |
||
| 148 | public function getDOMBodyNode() |
||
| 167 | } |
||
| 168 | |||
| 169 | /** |
||
| 170 | * Remove any <head node from the DOM |
||
| 171 | * |
||
| 172 | * This is done due to poor structure of some received HTML via email ect |
||
| 173 | */ |
||
| 174 | private function _removeHeadNode() |
||
| 187 | } |
||
| 188 | } |
||
| 189 | } |
||
| 190 | |||
| 191 | /** |
||
| 192 | * Breaks a string up so its no more than width characters long |
||
| 193 | * |
||
| 194 | * - Will break at word boundaries |
||
| 195 | * - If no natural space is found will break mid-word |
||
| 196 | * |
||
| 197 | * @param string $string |
||
| 198 | * @param int $width |
||
| 199 | * @param string $break |
||
| 200 | * @return string |
||
| 201 | */ |
||
| 202 | public function utf8Wordwrap($string, $width = 76, $break = "\n") |
||
| 203 | { |
||
| 204 | if ($width < 76) |
||
| 205 | { |
||
| 206 | return $string; |
||
| 207 | } |
||
| 208 | |||
| 209 | $strings = explode($break, $string); |
||
| 210 | $lines = []; |
||
| 211 | |||
| 212 | foreach ($strings as $string) |
||
| 213 | { |
||
| 214 | $in_quote = isset($string[0]) && $string[0] === '>'; |
||
| 215 | if (empty($string)) |
||
| 216 | { |
||
| 217 | $lines[] = ''; |
||
| 218 | } |
||
| 219 | |||
| 220 | while (!empty($string)) |
||
| 221 | { |
||
| 222 | // Get the next #width characters before a break (space, punctuation tab etc) |
||
| 223 | if (preg_match('~^(.{1,' . $width . '})(?:\s|$|,|\.)~u', $string, $matches)) |
||
| 224 | { |
||
| 225 | // Add the #width to the output and set up for the next pass |
||
| 226 | $lines[] = ($in_quote && $matches[1][0] !== '>' ? '> ' : '') . $matches[1]; |
||
| 227 | $string = Util::substr($string, Util::strlen($matches[1])); |
||
| 228 | } |
||
| 229 | // Humm just a long word with no place to break, so we simply cut it after width characters |
||
| 230 | else |
||
| 231 | { |
||
| 232 | $lines[] = ($in_quote && $string[0] !== '>' ? '> ' : '') . Util::substr($string, 0, $width); |
||
| 233 | $string = Util::substr($string, $width); |
||
| 234 | } |
||
| 235 | } |
||
| 236 | } |
||
| 237 | |||
| 238 | // Join it all the shortened sections up on our break characters |
||
| 239 | return implode($break, $lines); |
||
| 240 | } |
||
| 241 | |||
| 242 | /** |
||
| 243 | * Get the nesting level when inside a list |
||
| 244 | * |
||
| 245 | * @param object $node |
||
| 246 | * |
||
| 247 | * @return int |
||
| 248 | */ |
||
| 249 | public function hasParentList($node) |
||
| 250 | { |
||
| 251 | $depth = 0; |
||
| 252 | |||
| 253 | $parent = $this->getParent($node); |
||
| 254 | while ($parent) |
||
| 255 | { |
||
| 256 | // Anywhere nested inside a list we need to get the depth |
||
| 257 | $tag = $this->getName($parent); |
||
| 258 | if (in_array($tag, ['ul', 'ol'])) |
||
| 259 | { |
||
| 260 | $depth++; |
||
| 261 | } |
||
| 262 | |||
| 263 | // Back out another level |
||
| 264 | $parent = $this->getParent($parent); |
||
| 265 | } |
||
| 266 | |||
| 267 | return $depth; |
||
| 268 | } |
||
| 269 | |||
| 270 | /** |
||
| 271 | * Returns the parent node of another node |
||
| 272 | * |
||
| 273 | * @param $node |
||
| 274 | * @return object |
||
| 275 | */ |
||
| 276 | public function getParent($node) |
||
| 277 | { |
||
| 278 | if ($node === null) |
||
| 279 | { |
||
| 280 | return null; |
||
| 281 | } |
||
| 282 | |||
| 283 | return $this->internalParser ? $node->parentNode : $node->parentNode(); |
||
| 284 | } |
||
| 285 | |||
| 286 | /** |
||
| 287 | * Returns the node Name of a node |
||
| 288 | * |
||
| 289 | * @param $node |
||
| 290 | * @return string |
||
| 291 | */ |
||
| 292 | public function getName($node) |
||
| 300 | } |
||
| 301 | |||
| 302 | /** |
||
| 303 | * Returns the HTML of the document |
||
| 304 | * |
||
| 305 | * @return string |
||
| 306 | */ |
||
| 307 | public function getHTML() |
||
| 315 | } |
||
| 316 | |||
| 317 | /** |
||
| 318 | * Gets a node object |
||
| 319 | * |
||
| 320 | * @param object $node |
||
| 321 | * @param int $item |
||
| 322 | * @return object |
||
| 323 | */ |
||
| 324 | public function getItem($node, $item) |
||
| 325 | { |
||
| 326 | return $this->internalParser ? $node->item($item) : $node[$item]; |
||
| 327 | } |
||
| 328 | |||
| 329 | /** |
||
| 330 | * gets a node length |
||
| 331 | * |
||
| 332 | * @param object|array $node |
||
| 333 | * @return int |
||
| 334 | */ |
||
| 335 | public function getLength($node) |
||
| 336 | { |
||
| 337 | return $this->internalParser ? $node->length : count($node); |
||
| 338 | } |
||
| 339 | |||
| 340 | /** |
||
| 341 | * gets all children of a parent node |
||
| 342 | * |
||
| 343 | * @param object|array $node |
||
| 344 | * @return object |
||
| 345 | */ |
||
| 346 | public function getChildren($node) |
||
| 347 | { |
||
| 348 | return $this->internalParser ? $node->childNodes : $node->childNodes(); |
||
| 349 | } |
||
| 350 | |||
| 351 | /** |
||
| 352 | * gets a specific child of a parent node |
||
| 353 | * |
||
| 354 | * @param object|array $node |
||
| 355 | * @param int child number to return |
||
| 356 | * @return object |
||
| 357 | */ |
||
| 358 | public function getChild($node, $child) |
||
| 359 | { |
||
| 360 | return $this->internalParser ? $node->childNodes->item($child) : $node->childNodes($child); |
||
| 361 | } |
||
| 362 | |||
| 363 | /** |
||
| 364 | * gets the next sibling of a node |
||
| 365 | * |
||
| 366 | * @param object|array $node |
||
| 367 | * @return object |
||
| 368 | */ |
||
| 369 | public function getSibling($node) |
||
| 370 | { |
||
| 371 | return $this->internalParser ? $node->nextSibling : $node->next_sibling(); |
||
| 372 | } |
||
| 373 | |||
| 374 | /** |
||
| 375 | * gets a node value |
||
| 376 | * |
||
| 377 | * @param object $node |
||
| 378 | * @return string |
||
| 379 | */ |
||
| 380 | public function getValue($node) |
||
| 381 | { |
||
| 382 | if ($node === null) |
||
| 383 | { |
||
| 384 | return ''; |
||
| 385 | } |
||
| 386 | |||
| 387 | if ($this->internalParser) |
||
| 388 | { |
||
| 389 | return $node->nodeValue; |
||
| 390 | } |
||
| 391 | |||
| 392 | return html_entity_decode(htmlspecialchars_decode($node->innertext, ENT_QUOTES), ENT_QUOTES, 'UTF-8'); |
||
| 393 | } |
||
| 394 | |||
| 395 | /** |
||
| 396 | * Sets a node to a text value, replacing what was there |
||
| 397 | * |
||
| 398 | * @param $node |
||
| 399 | * @param $text |
||
| 400 | */ |
||
| 401 | public function setTextNode($node, $text) |
||
| 402 | { |
||
| 403 | if ($this->internalParser) |
||
| 404 | { |
||
| 405 | $text_node = $this->document->createTextNode($text); |
||
| 406 | $node->parentNode->replaceChild($text_node, $node); |
||
| 407 | } |
||
| 408 | else |
||
| 409 | { |
||
| 410 | $node->outertext = $text; |
||
| 411 | } |
||
| 412 | } |
||
| 413 | |||
| 414 | /** |
||
| 415 | * Gets the inner html of a node |
||
| 416 | * |
||
| 417 | * @param \DOMNode|object $node |
||
| 418 | * @return string |
||
| 419 | */ |
||
| 420 | public function getInnerHTML($node) |
||
| 421 | { |
||
| 422 | if ($this->internalParser) |
||
| 423 | { |
||
| 424 | $doc = new \DOMDocument(); |
||
| 425 | $doc->preserveWhiteSpace = true; |
||
| 426 | $doc->appendChild($doc->importNode($node, true)); |
||
| 427 | $html = trim($doc->saveHTML()); |
||
| 428 | $tag = $node->nodeName; |
||
| 429 | |||
| 430 | return preg_replace('@^<' . $tag . '[^>]*>|</' . $tag . '>$@', '', $html); |
||
| 431 | } |
||
| 432 | |||
| 433 | return $node->innertext; |
||
| 434 | } |
||
| 435 | |||
| 436 | /** |
||
| 437 | * Gets the outer html of a node |
||
| 438 | * |
||
| 439 | * @param \DOMNode|object $node |
||
| 440 | * @return string |
||
| 441 | */ |
||
| 442 | public function getOuterHTML($node) |
||
| 443 | { |
||
| 444 | return $this->internalParser ? htmlspecialchars_decode($this->document->saveHTML($node)) : $node->outertext; |
||
| 445 | } |
||
| 446 | |||
| 447 | /** |
||
| 448 | * Gets the inner html of a node |
||
| 449 | * |
||
| 450 | * @param \DOMNode|object $node |
||
| 451 | * @return string |
||
| 452 | */ |
||
| 453 | public function setInnerHTML($node) |
||
| 466 | } |
||
| 467 | } |
Loading history...