8000 [DomCrawler] fix HTML5 parser integration by nicolas-grekas · Pull Request #31257 · symfony/symfony · GitHub
[go: up one dir, main page]
Skip to content

[DomCrawler] fix HTML5 parser integration #31257 8000

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 9, 2019
Merged

[DomCrawler] fix HTML5 parser integration #31257

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 8 additions & 15 deletions src/Symfony/Component/DomCrawler/Crawler.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,7 @@ public function __construct($node = null, string $uri = null, string $baseHref =
{
$this->uri = $uri;
$this->baseHref = $baseHref ?: $uri;
$this->html5Parser = class_exists(HTML5::class) ? new HTML5(['disable_html_ns' => true]) : null;

$this->add($node);
}
Expand Down Expand Up @@ -190,13 +191,7 @@ public function addContent($content, $type = null)
public function addHtmlContent($content, $charset = 'UTF-8')
{
// Use HTML5 parser if the content is HTML5 and the library is available
if (!$this->html5Parser
&& class_exists(HTML5::class)
&& '<!doctype html>' === strtolower(substr(ltrim($content), 0, 15))) {
$this->html5Parser = new HTML5(['disable_html_ns' => true]);
}

$dom = null !== $this->html5Parser ? $this->parseHtml5($content, $charset) : $this->parseXhtml($content, $charset);
$dom = null !== $this->html5Parser && strspn($content, " \t\r\n") === stripos($content, '<!doctype html>') ? $this->parseHtml5($content, $charset) : $this->parseXhtml($content, $charset);
$this->addDocument($dom);

$base = $this->filterRelativeXPath('descendant-or-self::base')->extract(['href']);
Expand Down Expand Up @@ -599,18 +594,16 @@ public function html(/* $default = null */)
throw new \InvalidArgumentException('The current node list is empty.');
}

if (null !== $this->html5Parser) {
$html = '';
foreach ($this->getNode(0)->childNodes as $child) {
$html .= $this->html5Parser->saveHTML($child);
}
$node = $this->getNode(0);
$owner = $node->ownerDocument;

return $html;
if (null !== $this->html5Parser && '<!DOCTYPE html>' === $owner->saveXML($owner->childNodes[0])) {
$owner = $this->html5Parser;
}

$html = '';
foreach ($this->getNode(0)->childNodes as $child) {
$html .= $child->ownerDocument->saveHTML($child);
foreach ($node->childNodes as $child) {
$html .= $owner->saveHTML($child);
}

return $html;
Expand Down
0