Replace unpaired surrogates in result of javascript URLs

Given a URL like javascript:String.fromCodePoint(0xDE0D), Chrome currently displays three U+FFFD replacement characters rather than just one, due to the incorrect UTF-8 conversion mode. We fix that by using kStrictUTF8ConversionReplacingUnpairedSurrogatesWithFFFD. This CL fully implements whatwg/html#6781. Tests are partially taken from #29419. Co-authored-by: Domenic Denicola <domenic@chromium.org> Bug: 1221018 Change-Id: Ic1282d0a88eabb40b4d5d8d8c68e040e9a0a938d
web-platform-tests · Jun 17, 2021 · ae1f6e6 · ae1f6e6
1 parent ec5c1fc
commit ae1f6e6
Show file tree

Hide file tree

Showing 2 changed files with 58 additions and 51 deletions.
diff --git a/...ing-the-web/navigating-across-documents/javascript-url-return-value-handling-dynamic.html b/...ing-the-web/navigating-across-documents/javascript-url-return-value-handling-dynamic.html
diff --git a/...b/navigating-across-documents/javascript-url-return-value-handling-dynamic.tentative.html b/...b/navigating-across-documents/javascript-url-return-value-handling-dynamic.tentative.html
@@ -0,0 +1,58 @@
+<!doctype html>
+<meta charset=windows-1252> <!-- intentionally not UTF-8 to test that the javascript: frames are forced to UTF-8 -->
+<title>Test javascript URL string return values in direct and indirect (target) frame contexts.</title>
+<!-- Waiting on https://github.com/whatwg/html/pull/6781 to be non-tentative. -->
+<script src=/resources/testharness.js></script>
+<script src=/resources/testharnessreport.js></script>
+<div id=log></div>
+<script>
+const testCases = [
+  [[0x41]],
+  [[0x80,0xFF]],
+  [[0x80,0xFF,0x100]],
+  [[0xD83D,0xDE0D]],
+  [[0xDE0D,0x41], [0xFFFD,0x41]]
+];
+
+function formatCharCodes(charCodes) {
+  return charCodes.map(code => code.toString(16).toUpperCase().padStart(4, '0')).join(" ");
+}
+
+for (const [input, expected = input] of testCases) {
+  const javascriptURL = `javascript:String.fromCharCode(${input})`;
+  const output = String.fromCharCode(...expected);
+
+  async_test(t => {
+    const frame = document.createElement("iframe");
+    t.add_cleanup(() => frame.remove());
+    frame.src = javascriptURL;
+
+    t.step_timeout(() => {
+      assert_equals(frame.contentDocument.body.textContent, output);
+      assert_equals(frame.contentDocument.charset, "UTF-8");
+      t.done();
+    }, 200);
+
+    document.body.appendChild(frame);
+  }, `${formatCharCodes(input)} set in src=""`);
+
+  async_test(t => {
+    const frame = document.createElement("iframe");
+    const href = document.createElement("a");
+    t.add_cleanup(() => { frame.remove(); href.remove(); });
+    frame.name = "hi" + input;
+    href.target = "hi" + input;
+    href.href = javascriptURL;
+
+    t.step_timeout(() => {
+      assert_equals(frame.contentDocument.body.textContent, output);
+      assert_equals(frame.contentDocument.charset, "UTF-8");
+      t.done();
+    }, 200)
+
+    document.body.appendChild(frame);
+    document.body.appendChild(href);
+    href.click();
+  }, `${formatCharCodes(input)} set in href="" targeting a frame and clicked`);
+}
+</script>