infong/php-readability
1
0
Fork 0
mirror of https://github.com/j0k3r/php-readability.git synced 2026-09-27 06:26:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix discarding html[lang]

Browse Source 
`DOMDocument::loadHTML` will parse HTML documents as ISO-8859-1 if there is no `meta[charset]` tag. This means that UTF-8-encoded HTML fragments such as those coming from JSON-LD `articleBody` field would be parsed with incorrect encoding.

In f14428e4c0, we tried to resolve it by putting `meta[charset]` tag at the start of the HTML fragment. Unfortunately, it turns out that causes parser to auto-insert a `html` element, losing the attributes of the original `html` tag.

Let’s try to insert the `meta[charset]` tag into the proper place in the HTML document.

We do not need to use the same trick with `JSLikeHTMLElement::__set`.
That expects smaller HTML fragments, not `html` documents, so creating `html` and `head` elements will not be a problem.
This commit is contained in:
Jan Tojnar
2025-03-04 01:51:34 +01:00
parent 541fab34a0
commit efbbc86df9
2 changed files with 84 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ReadabilityTest.php
+42
View File
@@ -529,6 +529,48 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
}
}
/**
* @return array<string, array{0: string, 1: string, 2?: bool}>
*/
public function dataForHtmlLang(): array
{
return [
'meta' => [
'<html lang="fr"><head><meta charset="utf-8"></head><body><article>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</article></body></html>',
'fr',
],
'head' => [
'<html lang="fr"><head><title>Foo</title></head><body><article>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</article></body></html>',
'fr',
],
'headless' => [
'<html lang="fr"><body><article>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</article></body></html>',
'fr',
// tidy would add <head> tag.
false,
],
'fragment' => [
'<article>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</article>',
'',
// tidy would add <html>.
false,
],
];
}
/**
* @dataProvider dataForHtmlLang
*/
public function testHtmlLang(string $html, string $lang, bool $useTidy = true): void
{
$readability = $this->getReadability($html, 'http://0.0.0.0', 'libxml', $useTidy);
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf(\DOMDocument::class, $readability->dom);
$this->assertSame($lang, $readability->dom->documentElement->getAttribute('lang'));
}
private function getReadability(string $html, ?string $url = null, string $parser = 'libxml', bool $useTidy = true): Readability
{
$readability = new Readability($html, $url, $parser, $useTidy);