Add tests for URL parsing of lone surrogates in the query string (#32446)
Co-authored-by: Anne van Kesteren <annevk@annevk.nl>
diff --git a/html/infrastructure/urls/resolving-urls/query-encoding/lone-surrogates.sub.html b/html/infrastructure/urls/resolving-urls/query-encoding/lone-surrogates.sub.html
new file mode 100644
index 0000000..e47ab0f
--- /dev/null
+++ b/html/infrastructure/urls/resolving-urls/query-encoding/lone-surrogates.sub.html
@@ -0,0 +1,30 @@
+<!doctype html>
+<meta charset={{GET[encoding]}}> <!-- ends up as <meta charset> by default which is windows-1252 -->
+<meta name=variant content="?encoding=windows-1252">
+<meta name=variant content="?encoding=utf8">
+<script src=/resources/testharness.js></script>
+<script src=/resources/testharnessreport.js></script>
+<div id=log></div>
+<script>
+function expected(encoding) {
+ return "?" + {
+ // Replacement character (not bogus UTF-8)
+ "UTF-8": "%EF%BF%BD",
+ // Charref for the replacement character (not the lone surrogate)
+ "windows-1252": "%26%2365533%3B",
+ }[encoding];
+}
+
+test(t => {
+ const elm = document.createElement("a");
+ document.body.appendChild(elm);
+ t.add_cleanup(() => elm.remove());
+ elm.setAttribute("href", "?\uD800");
+
+ const shouldEndWith = expected(document.characterSet);
+ assert_true(
+ elm.href.endsWith(shouldEndWith),
+ `${elm.href} did not end with ${shouldEndWith}`
+ );
+}, `Query parsing with lone surrogates in ${document.characterSet}`);
+</script>