mirror of
https://github.com/j0k3r/php-readability.git
synced 2026-09-27 06:26:17 +00:00
Fix hasSingleTagInsideElement method
It would fail for e.g. `<div> <p>foo</p> </div>`.
mozilla/readability uses children for the tag lookup, which return only elements.
PHP does not have children property so b580cf216d
mistakenly used `childNodes` instead, but that can return any node type.
Let’s filter the children ourselves.
Also add comments from mozilla/readability’s `_hasSingleTagInsideElement`.
This commit is contained in:
+11
-2
@@ -1477,14 +1477,23 @@ class Readability implements LoggerAwareInterface
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if `$node` has only whitespace and a single element with `$tag` for the tag name.
|
||||
* Returns false if `$node` contains non-empty text nodes
|
||||
* or if it contains no element with given tag or more than 1 element.
|
||||
*/
|
||||
private function hasSingleTagInsideElement(\DOMElement $node, string $tag): bool
|
||||
{
|
||||
if (1 !== $node->childNodes->length || $node->childNodes->item(0)->nodeName !== $tag) {
|
||||
$childNodes = iterator_to_array($node->childNodes);
|
||||
$children = array_filter($childNodes, fn ($childNode) => $childNode instanceof \DOMElement);
|
||||
|
||||
// There should be exactly 1 element child with given tag
|
||||
if (1 !== \count($children) || $children[0]->nodeName !== $tag) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$a = array_filter(
|
||||
iterator_to_array($node->childNodes),
|
||||
$childNodes,
|
||||
fn ($childNode) => $childNode instanceof \DOMText && preg_match($this->regexps['hasContent'], $this->getInnerText($childNode))
|
||||
);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user