Skip to content

Allow reading not strictly valid HTML #2010

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
norberttech merged 1 commit into from
Nov 15, 2025
Merged

Allow reading not strictly valid HTML #2010

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion src/core/etl/src/Flow/ETL/Row/Entry/HTMLEntry.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ public function __construct(
?Metadata $metadata = null,
) {
if (\is_string($value)) {
$this->value = HTMLDocument::createFromString($value);
$this->value = HTMLDocument::createFromString($value, \LIBXML_NOERROR);
} else {
$this->value = $value;
}
Expand Down
42 changes: 42 additions & 0 deletions src/core/etl/tests/Flow/ETL/Tests/Unit/Row/Entry/HTMLEntryTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,6 +166,36 @@ public function test_renames_entry() : void
self::assertEquals($entry->type(), $newEntry->type());
}

public function test_with_non_fully_valid_html_string() : void
{
$invalidHtml = <<<'HTML'
<!DOCTYPE html>
<html lang="en">
<head></head>
<body>
<div>foo</div>
<div><p><span>bar</span></span></p></div>
</body>
</html>
HTML;

$validHtml = <<<'HTML'
<!DOCTYPE html>
<html lang="en">
<head></head>
<body>
<div>foo</div>
<div><p><span>bar</span></p></div>
</body>
</html>
HTML;

$entry = html_entry('html', $invalidHtml);

self::assertHtml($invalidHtml, $entry->toString(), false);
self::assertHtml($validHtml, $entry->toString(), true);
}

public function test_with_value() : void
{
$entry = html_entry('html', '<!DOCTYPE html><html lang="en"><head></head><body><div>foobar</div></body></html>');
Expand All @@ -178,4 +208,16 @@ public function test_with_value() : void
self::assertNotEquals($entry->toString(), $newEntry->toString());
self::assertEquals($html, $newEntry->value());
}

private function assertHtml(string $expected, string $html, bool $equals) : void
{
$expected = \preg_replace('/\s*/', '', $expected);
$html = \preg_replace('/\s*/', '', $html);

if ($equals) {
self::assertEquals($expected, $html);
} else {
self::assertNotEquals($expected, $html);
}
}
}
2 changes: 1 addition & 1 deletion src/lib/types/src/Flow/Types/Type/Logical/HTMLType.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ public function cast(mixed $value) : HTMLDocument

/* @phpstan-ignore-next-line */
if (\is_string($value)) {
return HTMLDocument::createFromString($value);
return HTMLDocument::createFromString($value, \LIBXML_NOERROR);
}

return $value;
Expand Down
Loading