1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-27 00:27:45 +00:00

AK: Do not trim away non-ASCII bytes when parsing URL

Because non-ASCII code points have negative byte values, trimming away
control characters requires checking for negative bytes values.

This also adds a test case with a URL containing non-ASCII code points.
This commit is contained in:
Max Wipfli 2021-06-03 12:36:02 +02:00 committed by Andreas Kling
parent 44937e2dfc
commit 99d5555134
2 changed files with 11 additions and 2 deletions

View file

@ -328,3 +328,12 @@ TEST_CASE(leading_and_trailing_whitespace)
EXPECT(url.is_valid());
EXPECT_EQ(url.to_string(), "https://foo.com/");
}
TEST_CASE(unicode)
{
URL url { "http://example.com/_ünicöde_téxt_©" };
EXPECT(url.is_valid());
EXPECT_EQ(url.path(), "/_ünicöde_téxt_©");
EXPECT(url.query().is_null());
EXPECT(url.fragment().is_null());
}