| 1 |
<?php |
| 2 |
/** |
| 3 |
* This class provides functions for converting CSS styles into inline style attributes in your HTML code |
| 4 |
* |
| 5 |
* For more information, please see the README.md file. |
| 6 |
* |
| 7 |
* @author Cameron Brooks |
| 8 |
* @author Jaime Prado |
| 9 |
* @author Roman Ožana <ozana@omdesign.cz> |
| 10 |
*/ |
| 11 |
class Emogrifier { |
| 12 |
/** |
| 13 |
* @var string |
| 14 |
*/ |
| 15 |
const ENCODING = 'UTF-8'; |
| 16 |
|
| 17 |
/** |
| 18 |
* @var integer |
| 19 |
*/ |
| 20 |
const CACHE_KEY_CSS = 0; |
| 21 |
|
| 22 |
/** |
| 23 |
* @var integer |
| 24 |
*/ |
| 25 |
const CACHE_KEY_SELECTOR = 1; |
| 26 |
|
| 27 |
/** |
| 28 |
* @var integer |
| 29 |
*/ |
| 30 |
const CACHE_KEY_XPATH = 2; |
| 31 |
|
| 32 |
/** |
| 33 |
* @var integer |
| 34 |
*/ |
| 35 |
const CACHE_KEY_CSS_DECLARATION_BLOCK = 3; |
| 36 |
|
| 37 |
/** |
| 38 |
* for calculating nth-of-type and nth-child selectors. |
| 39 |
* |
| 40 |
* @var integer |
| 41 |
*/ |
| 42 |
const INDEX = 0; |
| 43 |
|
| 44 |
/** |
| 45 |
* for calculating nth-of-type and nth-child selectors. |
| 46 |
* |
| 47 |
* @var integer |
| 48 |
*/ |
| 49 |
const MULTIPLIER = 1; |
| 50 |
|
| 51 |
/** |
| 52 |
* @var string |
| 53 |
*/ |
| 54 |
const ID_ATTRIBUTE_MATCHER = '/(\\w+)?\\#([\\w\\-]+)/'; |
| 55 |
|
| 56 |
/** |
| 57 |
* @var string |
| 58 |
*/ |
| 59 |
const CLASS_ATTRIBUTE_MATCHER = '/(\\w+|[\\*\\]])?((\\.[\\w\\-]+)+)/'; |
| 60 |
|
| 61 |
/** |
| 62 |
* @var string |
| 63 |
*/ |
| 64 |
private $html = ''; |
| 65 |
|
| 66 |
/** |
| 67 |
* @var string |
| 68 |
*/ |
| 69 |
private $css = ''; |
| 70 |
|
| 71 |
/** |
| 72 |
* @var array<string> |
| 73 |
*/ |
| 74 |
private $unprocessableHtmlTags = array('wbr'); |
| 75 |
|
| 76 |
/** |
| 77 |
* @var array<array> |
| 78 |
*/ |
| 79 |
private $caches = array( |
| 80 |
self::CACHE_KEY_CSS => array(), |
| 81 |
self::CACHE_KEY_SELECTOR => array(), |
| 82 |
self::CACHE_KEY_XPATH => array(), |
| 83 |
self::CACHE_KEY_CSS_DECLARATION_BLOCK => array(), |
| 84 |
); |
| 85 |
|
| 86 |
/** |
| 87 |
* the visited nodes with the XPath paths as array keys. |
| 88 |
* |
| 89 |
* @var array<\DOMNode> |
| 90 |
*/ |
| 91 |
private $visitedNodes = array(); |
| 92 |
|
| 93 |
/** |
| 94 |
* the styles to apply to the nodes with the XPath paths as array keys for the outer array and the attribute names/values. |
| 95 |
* as key/value pairs for the inner array. |
| 96 |
* |
| 97 |
* @var array<array><string> |
| 98 |
*/ |
| 99 |
private $styleAttributesForNodes = array(); |
| 100 |
|
| 101 |
/** |
| 102 |
* This attribute applies to the case where you want to preserve your original text encoding. |
| 103 |
* |
| 104 |
* By default, emogrifier translates your text into HTML entities for two reasons: |
| 105 |
* |
| 106 |
* 1. Because of client incompatibilities, it is better practice to send out HTML entities rather than unicode over email. |
| 107 |
* |
| 108 |
* 2. It translates any illegal XML characters that DOMDocument cannot work with. |
| 109 |
* |
| 110 |
* If you would like to preserve your original encoding, set this attribute to TRUE. |
| 111 |
* |
| 112 |
* @var boolean |
| 113 |
*/ |
| 114 |
public $preserveEncoding = false; |
| 115 |
|
| 116 |
public static $_media = ''; |
| 117 |
|
| 118 |
/** |
| 119 |
* The constructor. |
| 120 |
* |
| 121 |
* @param string $html the HTML to emogrify, must be UTF-8-encoded |
| 122 |
* @param string $css the CSS to merge, must be UTF-8-encoded |
| 123 |
*/ |
| 124 |
public function __construct($html = '', $css = '') { |
| 125 |
$this->setHtml($html); |
| 126 |
$this->setCss($css); |
| 127 |
} |
| 128 |
|
| 129 |
/** |
| 130 |
* The destructor. |
| 131 |
*/ |
| 132 |
public function __destruct() { |
| 133 |
$this->purgeVisitedNodes(); |
| 134 |
} |
| 135 |
|
| 136 |
/** |
| 137 |
* Sets the HTML to emogrify. |
| 138 |
* |
| 139 |
* @param string $html the HTML to emogrify, must be UTF-8-encoded |
| 140 |
*/ |
| 141 |
public function setHtml($html = '') { |
| 142 |
$this->html = $html; |
| 143 |
} |
| 144 |
|
| 145 |
/** |
| 146 |
* Sets the CSS to merge with the HTML. |
| 147 |
* |
| 148 |
* @param string $css the CSS to merge, must be UTF-8-encoded |
| 149 |
*/ |
| 150 |
public function setCss($css = '') { |
| 151 |
$this->css = $css; |
| 152 |
} |
| 153 |
|
| 154 |
/** |
| 155 |
* Clears all caches. |
| 156 |
*/ |
| 157 |
private function clearAllCaches() { |
| 158 |
$this->clearCache(self::CACHE_KEY_CSS); |
| 159 |
$this->clearCache(self::CACHE_KEY_SELECTOR); |
| 160 |
$this->clearCache(self::CACHE_KEY_XPATH); |
| 161 |
$this->clearCache(self::CACHE_KEY_CSS_DECLARATION_BLOCK); |
| 162 |
} |
| 163 |
|
| 164 |
/** |
| 165 |
* Clears a single cache by key. |
| 166 |
* |
| 167 |
* @param integer $key the cache key, must be CACHE_KEY_CSS, CACHE_KEY_SELECTOR, CACHE_KEY_XPATH or CACHE_KEY_CSS_DECLARATION_BLOCK |
| 168 |
* |
| 169 |
* @throws InvalidArgumentException |
| 170 |
*/ |
| 171 |
private function clearCache($key) { |
| 172 |
$allowedCacheKeys = array(self::CACHE_KEY_CSS, self::CACHE_KEY_SELECTOR, self::CACHE_KEY_XPATH, self::CACHE_KEY_CSS_DECLARATION_BLOCK); |
| 173 |
if (!in_array($key, $allowedCacheKeys, true)) { |
| 174 |
throw new InvalidArgumentException('Invalid cache key: ' . $key, 1391822035); |
| 175 |
} |
| 176 |
|
| 177 |
$this->caches[$key] = array(); |
| 178 |
} |
| 179 |
|
| 180 |
/** |
| 181 |
* Purges the visited nodes. |
| 182 |
*/ |
| 183 |
private function purgeVisitedNodes() { |
| 184 |
$this->visitedNodes = array(); |
| 185 |
$this->styleAttributesForNodes = array(); |
| 186 |
} |
| 187 |
|
| 188 |
/** |
| 189 |
* Marks a tag for removal. |
| 190 |
* |
| 191 |
* There are some HTML tags that DOMDocument cannot process, and it will throw an error if it encounters them. |
| 192 |
* In particular, DOMDocument will complain if you try to use HTML5 tags in an XHTML document. |
| 193 |
* |
| 194 |
* Note: The tags will not be removed if they have any content. |
| 195 |
* |
| 196 |
* @param string $tagName the tag name, e.g., "p" |
| 197 |
*/ |
| 198 |
public function addUnprocessableHtmlTag($tagName) { |
| 199 |
$this->unprocessableHtmlTags[] = $tagName; |
| 200 |
} |
| 201 |
|
| 202 |
/** |
| 203 |
* Drops a tag from the removal list. |
| 204 |
* |
| 205 |
* @param string $tagName the tag name, e.g., "p" |
| 206 |
*/ |
| 207 |
public function removeUnprocessableHtmlTag($tagName) { |
| 208 |
$key = array_search($tagName, $this->unprocessableHtmlTags, true); |
| 209 |
if ($key !== false) { |
| 210 |
unset($this->unprocessableHtmlTags[$key]); |
| 211 |
} |
| 212 |
} |
| 213 |
|
| 214 |
/** |
| 215 |
* Applies the CSS you submit to the HTML you submit. |
| 216 |
* |
| 217 |
* This method places the CSS inline. |
| 218 |
* |
| 219 |
* @return string |
| 220 |
* |
| 221 |
* @throws BadMethodCallException |
| 222 |
*/ |
| 223 |
public function emogrify() { |
| 224 |
if ($this->html === '') { |
| 225 |
throw new BadMethodCallException('Please set some HTML first before calling emogrify.', 1390393096); |
| 226 |
} |
| 227 |
|
| 228 |
$xmlDocument = $this->createXmlDocument(); |
| 229 |
$xpath = new DOMXPath($xmlDocument); |
| 230 |
$this->clearAllCaches(); |
| 231 |
|
| 232 |
// before be begin processing the CSS file, parse the document and normalize all existing CSS attributes (changes 'DISPLAY: none' to 'display: none'); |
| 233 |
// we wouldn't have to do this if DOMXPath supported XPath 2.0. |
| 234 |
// also store a reference of nodes with existing inline styles so we don't overwrite them |
| 235 |
$this->purgeVisitedNodes(); |
| 236 |
|
| 237 |
$nodesWithStyleAttributes = $xpath->query('//*[@style]'); |
| 238 |
if ($nodesWithStyleAttributes !== false) { |
| 239 |
/** @var $nodeWithStyleAttribute DOMNode */ |
| 240 |
foreach ($nodesWithStyleAttributes as $node) { |
| 241 |
$normalizedOriginalStyle = preg_replace_callback( '/[A-z\\-]+(?=\\:)/S', array( $this, 'strtolower' ), $node->getAttribute('style') ); |
| 242 |
|
| 243 |
// in order to not overwrite existing style attributes in the HTML, we have to save the original HTML styles |
| 244 |
$nodePath = $node->getNodePath(); |
| 245 |
if (!isset($this->styleAttributesForNodes[$nodePath])) { |
| 246 |
$this->styleAttributesForNodes[$nodePath] = $this->parseCssDeclarationBlock($normalizedOriginalStyle); |
| 247 |
$this->visitedNodes[$nodePath] = $node; |
| 248 |
} |
| 249 |
|
| 250 |
$node->setAttribute('style', $normalizedOriginalStyle); |
| 251 |
} |
| 252 |
} |
| 253 |
|
| 254 |
// grab any existing style blocks from the html and append them to the existing CSS |
| 255 |
// (these blocks should be appended so as to have precedence over conflicting styles in the existing CSS) |
| 256 |
$allCss = $this->css; |
| 257 |
|
| 258 |
$allCss .= $this->getCssFromAllStyleNodes($xpath); |
| 259 |
|
| 260 |
$cssParts = $this->splitCssAndMediaQuery($allCss); |
| 261 |
self::$_media = ''; // reset |
| 262 |
|
| 263 |
$cssKey = md5($cssParts['css']); |
| 264 |
if (!isset($this->caches[self::CACHE_KEY_CSS][$cssKey])) { |
| 265 |
// process the CSS file for selectors and definitions |
| 266 |
preg_match_all('/(?:^|[\\s^{}]*)([^{]+){([^}]*)}/mis', $cssParts['css'], $matches, PREG_SET_ORDER); |
| 267 |
|
| 268 |
$allSelectors = array(); |
| 269 |
foreach ($matches as $key => $selectorString) { |
| 270 |
// if there is a blank definition, skip |
| 271 |
if (!strlen(trim($selectorString[2]))) { |
| 272 |
continue; |
| 273 |
} |
| 274 |
|
| 275 |
// else split by commas and duplicate attributes so we can sort by selector precedence |
| 276 |
$selectors = explode(',', $selectorString[1]); |
| 277 |
foreach ($selectors as $selector) { |
| 278 |
// don't process pseudo-elements and behavioral (dynamic) pseudo-classes; ONLY allow structural pseudo-classes |
| 279 |
if (strpos($selector, ':') !== false && !preg_match('/:\\S+\\-(child|type)\\(/i', $selector)) { |
| 280 |
continue; |
| 281 |
} |
| 282 |
|
| 283 |
$allSelectors[] = array('selector' => trim($selector), |
| 284 |
'attributes' => trim($selectorString[2]), |
| 285 |
// keep track of where it appears in the file, since order is important |
| 286 |
'line' => $key, |
| 287 |
); |
| 288 |
} |
| 289 |
} |
| 290 |
|
| 291 |
// now sort the selectors by precedence |
| 292 |
usort($allSelectors, array($this,'sortBySelectorPrecedence')); |
| 293 |
|
| 294 |
$this->caches[self::CACHE_KEY_CSS][$cssKey] = $allSelectors; |
| 295 |
} |
| 296 |
|
| 297 |
foreach ($this->caches[self::CACHE_KEY_CSS][$cssKey] as $value) { |
| 298 |
// query the body for the xpath selector |
| 299 |
$nodesMatchingCssSelectors = $xpath->query($this->translateCssToXpath($value['selector'])); |
| 300 |
|
| 301 |
/** @var $node \DOMNode */ |
| 302 |
foreach ($nodesMatchingCssSelectors as $node) { |
| 303 |
// if it has a style attribute, get it, process it, and append (overwrite) new stuff |
| 304 |
if ($node->hasAttribute('style')) { |
| 305 |
// break it up into an associative array |
| 306 |
$oldStyleDeclarations = $this->parseCssDeclarationBlock($node->getAttribute('style')); |
| 307 |
} else { |
| 308 |
$oldStyleDeclarations = array(); |
| 309 |
} |
| 310 |
$newStyleDeclarations = $this->parseCssDeclarationBlock($value['attributes']); |
| 311 |
$node->setAttribute('style', $this->generateStyleStringFromDeclarationsArrays($oldStyleDeclarations, $newStyleDeclarations)); |
| 312 |
} |
| 313 |
} |
| 314 |
|
| 315 |
// now iterate through the nodes that contained inline styles in the original HTML |
| 316 |
foreach ($this->styleAttributesForNodes as $nodePath => $styleAttributesForNode) { |
| 317 |
$node = $this->visitedNodes[$nodePath]; |
| 318 |
$currentStyleAttributes = $this->parseCssDeclarationBlock($node->getAttribute('style')); |
| 319 |
$node->setAttribute('style', $this->generateStyleStringFromDeclarationsArrays($currentStyleAttributes, $styleAttributesForNode)); |
| 320 |
} |
| 321 |
|
| 322 |
// This removes styles from your email that contain display:none. |
| 323 |
// We need to look for display:none, but we need to do a case-insensitive search. Since DOMDocument only supports XPath 1.0, |
| 324 |
// lower-case() isn't available to us. We've thus far only set attributes to lowercase, not attribute values. Consequently, we need |
| 325 |
// to translate() the letters that would be in 'NONE' ("NOE") to lowercase. |
| 326 |
$nodesWithStyleDisplayNone = $xpath->query('//*[contains(translate(translate(@style," ",""),"NOE","noe"),"display:none")]'); |
| 327 |
// The checks on parentNode and is_callable below ensure that if we've deleted the parent node, |
| 328 |
// we don't try to call removeChild on a nonexistent child node |
| 329 |
if ($nodesWithStyleDisplayNone->length > 0) { |
| 330 |
/** @var $node \DOMNode */ |
| 331 |
foreach ($nodesWithStyleDisplayNone as $node) { |
| 332 |
if ($node->parentNode && is_callable(array($node->parentNode,'removeChild'))) { |
| 333 |
$node->parentNode->removeChild($node); |
| 334 |
} |
| 335 |
} |
| 336 |
} |
| 337 |
|
| 338 |
$this->copyCssWithMediaToStyleNode($cssParts, $xmlDocument); |
| 339 |
|
| 340 |
if ($this->preserveEncoding) { |
| 341 |
// Deprecated since PHP 8.2 |
| 342 |
if ( version_compare( PHP_VERSION, '8.2', '<' ) && function_exists( 'mb_convert_encoding' ) ) { |
| 343 |
return mb_convert_encoding( $xmlDocument->saveHTML(), self::ENCODING, 'HTML-ENTITIES' ); |
| 344 |
} else { |
| 345 |
return mb_encode_numericentity( $xmlDocument->saveHTML(), [0x80, 0x10FFFF, 0, ~0], self::ENCODING ); |
| 346 |
//return htmlspecialchars_decode( utf8_encode( html_entity_decode( $xmlDocument->saveHTML(), ENT_COMPAT, self::ENCODING ) ) ); |
| 347 |
} |
| 348 |
} else { |
| 349 |
return $xmlDocument->saveHTML(); |
| 350 |
} |
| 351 |
} |
| 352 |
|
| 353 |
/** |
| 354 |
* String to lower. |
| 355 |
* |
| 356 |
* @since 2.0.0 |
| 357 |
* |
| 358 |
* @param array $m |
| 359 |
* @return string |
| 360 |
*/ |
| 361 |
public function strtolower(array $m) { |
| 362 |
return strtolower($m[0]); |
| 363 |
} |
| 364 |
|
| 365 |
|
| 366 |
/** |
| 367 |
* This method merges old or existing name/value array with new name/value array. |
| 368 |
* and then generates a string of the combined style suitable for placing inline. |
| 369 |
* This becomes the single point for CSS string generation allowing for consistent. |
| 370 |
* CSS output no matter where the CSS originally came from. |
| 371 |
* @param array $oldStyles |
| 372 |
* @param array $newStyles |
| 373 |
* @return string |
| 374 |
*/ |
| 375 |
private function generateStyleStringFromDeclarationsArrays(array $oldStyles, array $newStyles) { |
| 376 |
$combinedStyles = array_merge($oldStyles, $newStyles); |
| 377 |
$style = ''; |
| 378 |
foreach ($combinedStyles as $attributeName => $attributeValue) { |
| 379 |
$style .= (strtolower(trim($attributeName)) . ': ' . trim($attributeValue) . '; '); |
| 380 |
} |
| 381 |
return trim($style); |
| 382 |
} |
| 383 |
|
| 384 |
|
| 385 |
/** |
| 386 |
* Copies the media part from CSS array parts to $xmlDocument. |
| 387 |
* |
| 388 |
* @param array $cssParts |
| 389 |
* @param DOMDocument $xmlDocument |
| 390 |
*/ |
| 391 |
public function copyCssWithMediaToStyleNode(array $cssParts, DOMDocument $xmlDocument) { |
| 392 |
if (isset($cssParts['media']) && $cssParts['media'] !== '') { |
| 393 |
$this->addStyleElementToDocument($xmlDocument, $cssParts['media']); |
| 394 |
} |
| 395 |
} |
| 396 |
|
| 397 |
/** |
| 398 |
* Returns CSS content. |
| 399 |
* |
| 400 |
* @param DOMXPath $xpath |
| 401 |
* @return string |
| 402 |
*/ |
| 403 |
private function getCssFromAllStyleNodes(DOMXPath $xpath) { |
| 404 |
$styleNodes = $xpath->query('//style'); |
| 405 |
|
| 406 |
if ($styleNodes === false) { |
| 407 |
return ''; |
| 408 |
} |
| 409 |
|
| 410 |
$css = ''; |
| 411 |
/** @var $styleNode DOMNode */ |
| 412 |
foreach ($styleNodes as $styleNode) { |
| 413 |
$css .= "\n\n" . $styleNode->nodeValue; |
| 414 |
$styleNode->parentNode->removeChild($styleNode); |
| 415 |
} |
| 416 |
|
| 417 |
return $css; |
| 418 |
} |
| 419 |
|
| 420 |
/** |
| 421 |
* Adds a style element with $css to $document. |
| 422 |
* |
| 423 |
* @param DOMDocument $document |
| 424 |
* @param string $css |
| 425 |
*/ |
| 426 |
private function addStyleElementToDocument(DOMDocument $document, $css) { |
| 427 |
$styleElement = $document->createElement('style', $css); |
| 428 |
$styleAttribute = $document->createAttribute('type'); |
| 429 |
$styleAttribute->value = 'text/css'; |
| 430 |
$styleElement->appendChild($styleAttribute); |
| 431 |
|
| 432 |
$head = $this->getOrCreateHeadElement($document); |
| 433 |
$head->appendChild($styleElement); |
| 434 |
} |
| 435 |
|
| 436 |
/** |
| 437 |
* Returns the existing or creates a new head element in $document. |
| 438 |
* |
| 439 |
* @param DOMDocument $document |
| 440 |
* @return DOMNode the head element |
| 441 |
*/ |
| 442 |
private function getOrCreateHeadElement(DOMDocument $document) { |
| 443 |
$head = $document->getElementsByTagName('head')->item(0); |
| 444 |
|
| 445 |
if ($head === null) { |
| 446 |
$head = $document->createElement('head'); |
| 447 |
$html = $document->getElementsByTagName('html')->item(0); |
| 448 |
$html->insertBefore($head, $document->getElementsByTagName('body')->item(0)); |
| 449 |
} |
| 450 |
|
| 451 |
return $head; |
| 452 |
} |
| 453 |
|
| 454 |
/** |
| 455 |
* Splits input CSS code to an array where: |
| 456 |
* |
| 457 |
* - key "css" will be contains clean CSS code. |
| 458 |
* - key "media" will be contains all valuable media queries. |
| 459 |
* |
| 460 |
* Example: |
| 461 |
* |
| 462 |
* The CSS code. |
| 463 |
* |
| 464 |
* "@import "file.css"; h1 { color:red; } @media { h1 {}} @media tv { h1 {}}" |
| 465 |
* |
| 466 |
* will be parsed into the following array: |
| 467 |
* |
| 468 |
* "css" => "h1 { color:red; }" |
| 469 |
* "media" => "@media { h1 {}}" |
| 470 |
* |
| 471 |
* @param string $css |
| 472 |
* @return array |
| 473 |
*/ |
| 474 |
private function splitCssAndMediaQuery($css) { |
| 475 |
$css = preg_replace_callback( '#@media\\s+(?:only\\s)?(?:[\\s{\(]|screen|all)\\s?[^{]+{.*}\\s*}\\s*#misU', array( $this, '_media_concat' ), $css ); |
| 476 |
|
| 477 |
// filter the CSS |
| 478 |
$search = array( |
| 479 |
// get rid of css comment code |
| 480 |
'/\\/\\*.*\\*\\//sU', |
| 481 |
// strip out any import directives |
| 482 |
'/^\\s*@import\\s[^;]+;/misU', |
| 483 |
// strip remains media enclosures |
| 484 |
'/^\\s*@media\\s[^{]+{(.*)}\\s*}\\s/misU', |
| 485 |
); |
| 486 |
|
| 487 |
$replace = array( |
| 488 |
'', |
| 489 |
'', |
| 490 |
'', |
| 491 |
); |
| 492 |
|
| 493 |
// clean CSS before output |
| 494 |
$css = preg_replace($search, $replace, $css); |
| 495 |
|
| 496 |
return array('css' => $css, 'media' => self::$_media); |
| 497 |
} |
| 498 |
|
| 499 |
/** |
| 500 |
* Media concat. |
| 501 |
* |
| 502 |
* @since 2.0.0 |
| 503 |
* |
| 504 |
* @param array $matches Matches result array. |
| 505 |
*/ |
| 506 |
private function _media_concat( $matches ) { |
| 507 |
self::$_media .= $matches[0]; |
| 508 |
} |
| 509 |
|
| 510 |
/** |
| 511 |
* Creates a DOMDocument instance with the current HTML. |
| 512 |
* |
| 513 |
* @return DOMDocument |
| 514 |
*/ |
| 515 |
private function createXmlDocument() { |
| 516 |
$xmlDocument = new DOMDocument; |
| 517 |
$xmlDocument->encoding = self::ENCODING; |
| 518 |
$xmlDocument->strictErrorChecking = false; |
| 519 |
$xmlDocument->formatOutput = true; |
| 520 |
$libXmlState = libxml_use_internal_errors(true); |
| 521 |
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged |
| 522 |
/** @scrutinizer ignore-unhandled */ @$xmlDocument->loadHTML($this->getUnifiedHtml()); |
| 523 |
libxml_clear_errors(); |
| 524 |
libxml_use_internal_errors($libXmlState); |
| 525 |
$xmlDocument->normalizeDocument(); |
| 526 |
|
| 527 |
return $xmlDocument; |
| 528 |
} |
| 529 |
|
| 530 |
/** |
| 531 |
* Returns the HTML with the non-ASCII characters converts into HTML entities and the unprocessable HTML tags removed. |
| 532 |
* |
| 533 |
* @return string the unified HTML |
| 534 |
* |
| 535 |
* @throws BadMethodCallException |
| 536 |
*/ |
| 537 |
private function getUnifiedHtml() { |
| 538 |
if (!empty($this->unprocessableHtmlTags)) { |
| 539 |
$unprocessableHtmlTags = implode('|', $this->unprocessableHtmlTags); |
| 540 |
$bodyWithoutUnprocessableTags = preg_replace('/<\\/?(' . $unprocessableHtmlTags . ')[^>]*>/i', '', $this->html); |
| 541 |
} else { |
| 542 |
$bodyWithoutUnprocessableTags = $this->html; |
| 543 |
} |
| 544 |
|
| 545 |
// Deprecated since PHP 8.2 |
| 546 |
if ( version_compare( PHP_VERSION, '8.2', '<' ) && function_exists( 'mb_convert_encoding' ) ) { |
| 547 |
return mb_convert_encoding( $bodyWithoutUnprocessableTags, 'HTML-ENTITIES', self::ENCODING ); |
| 548 |
} else { |
| 549 |
return mb_encode_numericentity( $bodyWithoutUnprocessableTags, [0x80, 0x10FFFF, 0, ~0], self::ENCODING ); |
| 550 |
//return htmlspecialchars_decode( utf8_decode( htmlentities( $bodyWithoutUnprocessableTags, ENT_COMPAT, self::ENCODING, false ) ) ); |
| 551 |
} |
| 552 |
} |
| 553 |
|
| 554 |
/** |
| 555 |
* @param array $a |
| 556 |
* @param array $b |
| 557 |
* |
| 558 |
* @return integer |
| 559 |
*/ |
| 560 |
private function sortBySelectorPrecedence(array $a, array $b) { |
| 561 |
$precedenceA = $this->getCssSelectorPrecedence($a['selector']); |
| 562 |
$precedenceB = $this->getCssSelectorPrecedence($b['selector']); |
| 563 |
|
| 564 |
// We want these sorted in ascending order so selectors with lesser precedence get processed first and |
| 565 |
// selectors with greater precedence get sorted last. |
| 566 |
// The parenthesis around the -1 are necessary to avoid a PHP_CodeSniffer warning about missing spaces around |
| 567 |
// arithmetic operators. |
| 568 |
// @see http://forge.typo3.org/issues/55605 |
| 569 |
$precedenceForEquals = ($a['line'] < $b['line'] ? (-1) : 1); |
| 570 |
$precedenceForNotEquals = ($precedenceA < $precedenceB ? (-1) : 1); |
| 571 |
return ($precedenceA === $precedenceB) ? $precedenceForEquals : $precedenceForNotEquals; |
| 572 |
} |
| 573 |
|
| 574 |
/** |
| 575 |
* @param string $selector |
| 576 |
* |
| 577 |
* @return integer |
| 578 |
*/ |
| 579 |
private function getCssSelectorPrecedence($selector) { |
| 580 |
$selectorKey = md5($selector); |
| 581 |
if (!isset($this->caches[self::CACHE_KEY_SELECTOR][$selectorKey])) { |
| 582 |
$precedence = 0; |
| 583 |
$value = 100; |
| 584 |
// ids: worth 100, classes: worth 10, elements: worth 1 |
| 585 |
$search = array('\\#','\\.',''); |
| 586 |
|
| 587 |
foreach ($search as $s) { |
| 588 |
if (trim($selector == '')) { |
| 589 |
break; |
| 590 |
} |
| 591 |
$number = 0; |
| 592 |
$selector = preg_replace('/' . $s . '\\w+/', '', $selector, -1, $number); |
| 593 |
$precedence += ($value * $number); |
| 594 |
$value /= 10; |
| 595 |
} |
| 596 |
$this->caches[self::CACHE_KEY_SELECTOR][$selectorKey] = $precedence; |
| 597 |
} |
| 598 |
|
| 599 |
return $this->caches[self::CACHE_KEY_SELECTOR][$selectorKey]; |
| 600 |
} |
| 601 |
|
| 602 |
/** |
| 603 |
* Right now, we support all CSS 1 selectors and most CSS2/3 selectors. |
| 604 |
* |
| 605 |
* @see http://plasmasturm.org/log/444/ |
| 606 |
* |
| 607 |
* @param string $paramCssSelector |
| 608 |
* |
| 609 |
* @return string |
| 610 |
*/ |
| 611 |
private function translateCssToXpath($paramCssSelector) { |
| 612 |
$cssSelector = ' ' . $paramCssSelector . ' '; |
| 613 |
$cssSelector = preg_replace_callback( '/\s+\w+\s+/', array( $this, 'strtolower' ), $cssSelector ); |
| 614 |
$cssSelector = trim($cssSelector); |
| 615 |
$xpathKey = md5($cssSelector); |
| 616 |
if (!isset($this->caches[self::CACHE_KEY_XPATH][$xpathKey])) { |
| 617 |
// returns an Xpath selector |
| 618 |
$search = array( |
| 619 |
// Matches any element that is a child of parent. |
| 620 |
'/\\s+>\\s+/', |
| 621 |
// Matches any element that is an adjacent sibling. |
| 622 |
'/\\s+\\+\\s+/', |
| 623 |
// Matches any element that is a descendant of an parent element element. |
| 624 |
'/\\s+/', |
| 625 |
// first-child pseudo-selector |
| 626 |
'/([^\\/]+):first-child/i', |
| 627 |
// last-child pseudo-selector |
| 628 |
'/([^\\/]+):last-child/i', |
| 629 |
// Matches attribute only selector |
| 630 |
'/^\\[(\\w+)\\]/', |
| 631 |
// Matches element with attribute |
| 632 |
'/(\\w)\\[(\\w+)\\]/', |
| 633 |
// Matches element with EXACT attribute |
| 634 |
'/(\\w)\\[(\\w+)\\=[\'"]?(\\w+)[\'"]?\\]/', |
| 635 |
); |
| 636 |
$replace = array( |
| 637 |
'/', |
| 638 |
'/following-sibling::*[1]/self::', |
| 639 |
'//', |
| 640 |
'*[1]/self::\\1', |
| 641 |
'*[last()]/self::\\1', |
| 642 |
'*[@\\1]', |
| 643 |
'\\1[@\\2]', |
| 644 |
'\\1[@\\2="\\3"]', |
| 645 |
); |
| 646 |
|
| 647 |
$cssSelector = '//' . preg_replace($search, $replace, $cssSelector); |
| 648 |
|
| 649 |
$cssSelector = preg_replace_callback(self::ID_ATTRIBUTE_MATCHER, array($this, 'matchIdAttributes'), $cssSelector); |
| 650 |
$cssSelector = preg_replace_callback(self::CLASS_ATTRIBUTE_MATCHER, array($this, 'matchClassAttributes'), $cssSelector); |
| 651 |
|
| 652 |
// Advanced selectors are going to require a bit more advanced emogrification. |
| 653 |
// When we required PHP 5.3, we could do this with closures. |
| 654 |
$cssSelector = preg_replace_callback( |
| 655 |
'/([^\\/]+):nth-child\\(\s*(odd|even|[+\-]?\\d|[+\\-]?\\d?n(\\s*[+\\-]\\s*\\d)?)\\s*\\)/i', |
| 656 |
array($this, 'translateNthChild'), $cssSelector |
| 657 |
); |
| 658 |
$cssSelector = preg_replace_callback( |
| 659 |
'/([^\\/]+):nth-of-type\\(\s*(odd|even|[+\-]?\\d|[+\\-]?\\d?n(\\s*[+\\-]\\s*\\d)?)\\s*\\)/i', |
| 660 |
array($this, 'translateNthOfType'), $cssSelector |
| 661 |
); |
| 662 |
|
| 663 |
$this->caches[self::CACHE_KEY_SELECTOR][$xpathKey] = $cssSelector; |
| 664 |
} |
| 665 |
return $this->caches[self::CACHE_KEY_SELECTOR][$xpathKey]; |
| 666 |
} |
| 667 |
|
| 668 |
/** |
| 669 |
* @param array $match |
| 670 |
* |
| 671 |
* @return string |
| 672 |
*/ |
| 673 |
private function matchIdAttributes(array $match) { |
| 674 |
return (strlen($match[1]) ? $match[1] : '*') . '[@id="' . $match[2] . '"]'; |
| 675 |
} |
| 676 |
|
| 677 |
/** |
| 678 |
* @param array $match |
| 679 |
* |
| 680 |
* @return string |
| 681 |
*/ |
| 682 |
private function matchClassAttributes(array $match) { |
| 683 |
return (strlen($match[1]) ? $match[1] : '*') . '[contains(concat(" ",@class," "),concat(" ","' . |
| 684 |
implode( |
| 685 |
'"," "))][contains(concat(" ",@class," "),concat(" ","', |
| 686 |
explode('.', substr($match[2], 1)) |
| 687 |
) . '"," "))]'; |
| 688 |
} |
| 689 |
|
| 690 |
/** |
| 691 |
* @param array $match |
| 692 |
* |
| 693 |
* @return string |
| 694 |
*/ |
| 695 |
private function translateNthChild(array $match) { |
| 696 |
$result = $this->parseNth($match); |
| 697 |
|
| 698 |
if (isset($result[self::MULTIPLIER])) { |
| 699 |
if ($result[self::MULTIPLIER] < 0) { |
| 700 |
$result[self::MULTIPLIER] = abs($result[self::MULTIPLIER]); |
| 701 |
return sprintf('*[(last() - position()) mod %u = %u]/self::%s', $result[self::MULTIPLIER], $result[self::INDEX], $match[1]); |
| 702 |
} else { |
| 703 |
return sprintf('*[position() mod %u = %u]/self::%s', $result[self::MULTIPLIER], $result[self::INDEX], $match[1]); |
| 704 |
} |
| 705 |
} else { |
| 706 |
return sprintf('*[%u]/self::%s', $result[self::INDEX], $match[1]); |
| 707 |
} |
| 708 |
} |
| 709 |
|
| 710 |
/** |
| 711 |
* @param array $match |
| 712 |
* |
| 713 |
* @return string |
| 714 |
*/ |
| 715 |
private function translateNthOfType(array $match) { |
| 716 |
$result = $this->parseNth($match); |
| 717 |
|
| 718 |
if (isset($result[self::MULTIPLIER])) { |
| 719 |
if ($result[self::MULTIPLIER] < 0) { |
| 720 |
$result[self::MULTIPLIER] = abs($result[self::MULTIPLIER]); |
| 721 |
return sprintf('%s[(last() - position()) mod %u = %u]', $match[1], $result[self::MULTIPLIER], $result[self::INDEX]); |
| 722 |
} else { |
| 723 |
return sprintf('%s[position() mod %u = %u]', $match[1], $result[self::MULTIPLIER], $result[self::INDEX]); |
| 724 |
} |
| 725 |
} else { |
| 726 |
return sprintf('%s[%u]', $match[1], $result[self::INDEX]); |
| 727 |
} |
| 728 |
} |
| 729 |
|
| 730 |
/** |
| 731 |
* @param array $match |
| 732 |
* |
| 733 |
* @return array |
| 734 |
*/ |
| 735 |
private function parseNth(array $match) { |
| 736 |
if (in_array(strtolower($match[2]), array('even','odd'))) { |
| 737 |
$index = strtolower($match[2]) == 'even' ? 0 : 1; |
| 738 |
return array(self::MULTIPLIER => 2, self::INDEX => $index); |
| 739 |
} elseif (stripos($match[2], 'n') === false) { |
| 740 |
// if there is a multiplier |
| 741 |
$index = intval(str_replace(' ', '', $match[2])); |
| 742 |
return array(self::INDEX => $index); |
| 743 |
} else { |
| 744 |
if (isset($match[3])) { |
| 745 |
$multipleTerm = str_replace($match[3], '', $match[2]); |
| 746 |
$index = intval(str_replace(' ', '', $match[3])); |
| 747 |
} else { |
| 748 |
$multipleTerm = $match[2]; |
| 749 |
$index = 0; |
| 750 |
} |
| 751 |
|
| 752 |
$multiplier = str_ireplace('n', '', $multipleTerm); |
| 753 |
|
| 754 |
if (!strlen($multiplier)) { |
| 755 |
$multiplier = 1; |
| 756 |
} elseif ($multiplier == 0) { |
| 757 |
return array(self::INDEX => $index); |
| 758 |
} else { |
| 759 |
$multiplier = intval($multiplier); |
| 760 |
} |
| 761 |
|
| 762 |
while ($index < 0) { |
| 763 |
$index += abs($multiplier); |
| 764 |
} |
| 765 |
|
| 766 |
return array(self::MULTIPLIER => $multiplier, self::INDEX => $index); |
| 767 |
} |
| 768 |
} |
| 769 |
|
| 770 |
/** |
| 771 |
* Parses a CSS declaration block into property name/value pairs. |
| 772 |
* |
| 773 |
* Example: |
| 774 |
* |
| 775 |
* The declaration block. |
| 776 |
* |
| 777 |
* "color: #000; font-weight: bold;". |
| 778 |
* |
| 779 |
* will be parsed into the following array: |
| 780 |
* |
| 781 |
* "color" => "#000" |
| 782 |
* "font-weight" => "bold" |
| 783 |
* |
| 784 |
* @param string $cssDeclarationBlock the CSS declaration block without the curly braces, may be empty |
| 785 |
* |
| 786 |
* @return array the CSS declarations with the property names as array keys and the property values as array values |
| 787 |
*/ |
| 788 |
private function parseCssDeclarationBlock($cssDeclarationBlock) { |
| 789 |
if (isset($this->caches[self::CACHE_KEY_CSS_DECLARATION_BLOCK][$cssDeclarationBlock])) { |
| 790 |
return $this->caches[self::CACHE_KEY_CSS_DECLARATION_BLOCK][$cssDeclarationBlock]; |
| 791 |
} |
| 792 |
|
| 793 |
$properties = array(); |
| 794 |
$declarations = explode(';', $cssDeclarationBlock); |
| 795 |
foreach ($declarations as $declaration) { |
| 796 |
$matches = array(); |
| 797 |
if (!preg_match('/ *([A-Za-z\\-]+) *: *([^;]+) */', $declaration, $matches)) { |
| 798 |
continue; |
| 799 |
} |
| 800 |
$propertyName = strtolower($matches[1]); |
| 801 |
$propertyValue = $matches[2]; |
| 802 |
$properties[$propertyName] = $propertyValue; |
| 803 |
} |
| 804 |
$this->caches[self::CACHE_KEY_CSS_DECLARATION_BLOCK][$cssDeclarationBlock] = $properties; |
| 805 |
|
| 806 |
return $properties; |
| 807 |
} |
| 808 |
} |
| 809 |
|
