Skip to content

[HtmlSanitizer] reject URLs containing whitespaces #59321

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.

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
Dec 30, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -358,10 +358,10 @@ public static function provideParse(): iterable
'non-special://:@untrusted.com/x' => ['scheme' => 'non-special', 'host' => 'untrusted.com'],
'http:foo.com' => ['scheme' => 'http', 'host' => null],
" :foo.com \n" => null,
' foo.com ' => ['scheme' => null, 'host' => null],
' foo.com ' => null,
'a: foo.com' => null,
'http://f:21/ b ? d # e ' => ['scheme' => 'http', 'host' => 'f'],
'lolscheme:x x#x x' => ['scheme' => 'lolscheme', 'host' => null],
'http://f:21/ b ? d # e ' => null,
'lolscheme:x x#x x' => null,
'http://f:/c' => ['scheme' => 'http', 'host' => 'f'],
'http://f:0/c' => ['scheme' => 'http', 'host' => 'f'],
'http://f:00000000000000/c' => ['scheme' => 'http', 'host' => 'f'],
Expand Down Expand Up @@ -434,7 +434,7 @@ public static function provideParse(): iterable
'javascript:example.com/' => ['scheme' => 'javascript', 'host' => null],
'mailto:example.com/' => ['scheme' => 'mailto', 'host' => null],
'/a/b/c' => ['scheme' => null, 'host' => null],
'/a/ /c' => ['scheme' => null, 'host' => null],
'/a/ /c' => null,
'/a%2fc' => ['scheme' => null, 'host' => null],
'/a/%2f/c' => ['scheme' => null, 'host' => null],
'#β' => ['scheme' => null, 'host' => null],
Expand Down Expand Up @@ -495,10 +495,10 @@ public static function provideParse(): iterable
'http://example.com/你好你好' => ['scheme' => 'http', 'host' => 'example.com'],
'http://example.com/‥/foo' => ['scheme' => 'http', 'host' => 'example.com'],
"http://example.com/\u{feff}/foo" => ['scheme' => 'http', 'host' => 'example.com'],
"http://example.com\u{002f}\u{202e}\u{002f}\u{0066}\u{006f}\u{006f}\u{002f}\u{202d}\u{002f}\u{0062}\u{0061}\u{0072}\u{0027}\u{0020}" => ['scheme' => 'http', 'host' => 'example.com'],
"http://example.com\u{002f}\u{202e}\u{002f}\u{0066}\u{006f}\u{006f}\u{002f}\u{202d}\u{002f}\u{0062}\u{0061}\u{0072}\u{0027}\u{0020}" => null,
'http://www.google.com/foo?bar=baz#' => ['scheme' => 'http', 'host' => 'www.google.com'],
'http://www.google.com/foo?bar=baz# »' => ['scheme' => 'http', 'host' => 'www.google.com'],
'data:test# »' => ['scheme' => 'data', 'host' => null],
'http://www.google.com/foo?bar=baz# »' => null,
'data:test# »' => null,
'http://www.google.com' => ['scheme' => 'http', 'host' => 'www.google.com'],
'http://192.0x00A80001' => ['scheme' => 'http', 'host' => '192.0x00A80001'],
'http://www/foo%2Ehtml' => ['scheme' => 'http', 'host' => 'www'],
Expand Down Expand Up @@ -706,11 +706,11 @@ public static function provideParse(): iterable
'test-a-colon-slash-slash-b.html' => ['scheme' => null, 'host' => null],
'http://example.org/test?a#bc' => ['scheme' => 'http', 'host' => 'example.org'],
'http:\\/\\/f:b\\/c' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/f: \\/c' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/f: \\/c' => null,
'http:\\/\\/f:fifty-two\\/c' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/f:999999\\/c' => ['scheme' => 'http', 'host' => null],
'non-special:\\/\\/f:999999\\/c' => ['scheme' => 'non-special', 'host' => null],
'http:\\/\\/f: 21 \\/ b ? d # e ' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/f: 21 \\/ b ? d # e ' => null,
'http:\\/\\/[1::2]:3:4' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/2001::1' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/2001::1]' => ['scheme' => 'http', 'host' => null],
Expand All @@ -734,8 +734,8 @@ public static function provideParse(): iterable
'http:@:www.example.com' => ['scheme' => 'http', 'host' => null],
'http:\\/@:www.example.com' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/@:www.example.com' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/example example.com' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/Goo%20 goo%7C|.com' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/example example.com' => null,
'http:\\/\\/Goo%20 goo%7C|.com' => null,
'http:\\/\\/[]' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/[:]' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/GOO\\u00a0\\u3000goo.com' => ['scheme' => 'http', 'host' => null],
Expand All @@ -752,8 +752,8 @@ public static function provideParse(): iterable
'http:\\/\\/hello%00' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/192.168.0.257' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/%3g%78%63%30%2e%30%32%35%30%2E.01' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/192.168.0.1 hello' => ['scheme' => 'http', 'host' => null],
'https:\\/\\/x x:12' => ['scheme' => 'https', 'host' => null],
'http:\\/\\/192.168.0.1 hello' => null,
'https:\\/\\/x x:12' => null,
'http:\\/\\/[www.google.com]\\/' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/[google.com]' => ['scheme' => 'http', 'host' => null],
'http:\\/\\/[::1.2.3.4x]' => ['scheme' => 'http', 'host' => null],
Expand All @@ -763,7 +763,7 @@ public static function provideParse(): iterable
'..\\/i' => ['scheme' => null, 'host' => null],
'\\/i' => ['scheme' => null, 'host' => null],
'sc:\\/\\/\\u0000\\/' => ['scheme' => 'sc', 'host' => null],
'sc:\\/\\/ \\/' => ['scheme' => 'sc', 'host' => null],
'sc:\\/\\/ \\/' => null,
'sc:\\/\\/@\\/' => ['scheme' => 'sc', 'host' => null],
'sc:\\/\\/te@s:t@\\/' => ['scheme' => 'sc', 'host' => null],
'sc:\\/\\/:\\/' => ['scheme' => 'sc', 'host' => null],
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,13 @@ public static function parse(string $url): ?array
}

try {
return UriString::parse($url);
$parsedUrl = UriString::parse($url);

if (preg_match('/\s/', $url)) {
return null;
}

return $parsedUrl;
} catch (SyntaxError) {
return null;
}
Expand Down