DomQuery:: fixed UTF-8 handling

dg · dg · commit e800eba80b43 · 2025-06-19T05:04:58.000+02:00
diff --git a/src/Framework/DomQuery.php b/src/Framework/DomQuery.php
@@ -24,6 +24,8 @@ public static function fromHtml(string $html): self
 			$html = '<body>' . $html;
 		}
 
+		$html = @mb_convert_encoding($html, 'HTML', 'UTF-8'); // @ - deprecated
+
 		// parse these elements as void
 		$html = preg_replace('#<(keygen|source|track|wbr)(?=\s|>)((?:"[^"]*"|\'[^\']*\'|[^"\'>])*+)(?<!/)>#', '<$1$2 />', $html);
 
diff --git a/tests/Framework/DomQuery.fromHtml.phpt b/tests/Framework/DomQuery.fromHtml.phpt
@@ -38,3 +38,7 @@ Assert::true($q->has('script[type]'));
 
 $q = @DomQuery::fromHtml('<custom-element></custom-element>');
 Assert::true($q->has('custom-element'));
+
+
+$q = DomQuery::fromHtml('<p>žluťoučký</p>');
+Assert::same('žluťoučký', (string) $q->find('p')[0]);

Original file line number	Diff line number	Diff line change
`@@ -24,6 +24,8 @@ public static function fromHtml(string $html): self`
`24`	`24`	`$html = '<body>' . $html;`
`25`	`25`	`}`
`26`	`26`
	`27`	`+ $html = @mb_convert_encoding($html, 'HTML', 'UTF-8'); // @ - deprecated`
	`28`	`+`
`27`	`29`	`// parse these elements as void`
`28`	`30`	`$html = preg_replace('#<(keygen\|source\|track\|wbr)(?=\s\|>)((?:"[^"]"\|\'[^\']\'\|[^"\'>])*+)(?<!/)>#', '<$1$2 />', $html);`
`29`	`31`