From b73f80719d704d46c3f906d6482adb4b4b9075cf Mon Sep 17 00:00:00 2001
From: Nikhil Marathe <nsm.nikhil@gmail.com>
Date: Wed, 9 Oct 2013 18:23:47 -0400
Subject: [PATCH] Bug 484305 - Worker scripts should always be decoded as
 UTF-8. r=bent

---
 dom/workers/ScriptLoader.cpp            |  4 +-
 dom/workers/test/loadEncoding_worker.js |  7 ++++
 dom/workers/test/mochitest.ini          |  2 +
 dom/workers/test/test_loadEncoding.html | 50 +++++++++++++++++++++++++
 4 files changed, 62 insertions(+), 1 deletion(-)
 create mode 100644 dom/workers/test/loadEncoding_worker.js
 create mode 100644 dom/workers/test/test_loadEncoding.html
diff --git a/dom/workers/ScriptLoader.cpp b/dom/workers/ScriptLoader.cpp
index 4b799d8c149..23a150419c7 100644
--- a/dom/workers/ScriptLoader.cpp
+++ b/dom/workers/ScriptLoader.cpp
@@ -440,8 +440,10 @@ public:
 
     // Use the regular nsScriptLoader for this grunt work! Should be just fine
     // because we're running on the main thread.
+    // Unlike <script> tags, Worker scripts are always decoded as UTF-8,
+    // per spec. So we explicitly pass in the charset hint.
     rv = nsScriptLoader::ConvertToUTF16(aLoadInfo.mChannel, aString, aStringLen,
-                                        EmptyString(), parentDoc,
+                                        NS_LITERAL_STRING("UTF-8"), parentDoc,
                                         aLoadInfo.mScriptText);
     if (NS_FAILED(rv)) {
       return rv;
diff --git a/dom/workers/test/loadEncoding_worker.js b/dom/workers/test/loadEncoding_worker.js
new file mode 100644
index 00000000000..5e40478445a
--- /dev/null
+++ b/dom/workers/test/loadEncoding_worker.js
@@ -0,0 +1,7 @@
+/*
+  Any copyright is dedicated to the Public Domain.
+  http://creativecommons.org/publicdomain/zero/1.0/
+*/
+// Bug 484305 - Load workers as UTF-8.
+postMessage({ encoding: "KOI8-R", text: "Привет" });
+postMessage({ encoding: "UTF-8", text: "п÷я─п╦п╡п╣я┌" });
diff --git a/dom/workers/test/mochitest.ini b/dom/workers/test/mochitest.ini
index 444a8d01118..817557c47a9 100644
--- a/dom/workers/test/mochitest.ini
+++ b/dom/workers/test/mochitest.ini
@@ -20,6 +20,7 @@ support-files =
   importScripts_worker_imported4.js
   instanceof_worker.js
   json_worker.js
+  loadEncoding_worker.js
   location_worker.js
   longThread_worker.js
   multi_sharedWorker_frame.html
@@ -73,6 +74,7 @@ support-files =
 [test_importScripts.html]
 [test_instanceof.html]
 [test_json.html]
+[test_loadEncoding.html]
 [test_loadError.html]
 [test_location.html]
 [test_longThread.html]
diff --git a/dom/workers/test/test_loadEncoding.html b/dom/workers/test/test_loadEncoding.html
new file mode 100644
index 00000000000..47e08f2f59c
--- /dev/null
+++ b/dom/workers/test/test_loadEncoding.html
@@ -0,0 +1,50 @@
+<!--
+  Any copyright is dedicated to the Public Domain.
+  http://creativecommons.org/publicdomain/zero/1.0/
+-->
+<!DOCTYPE HTML>
+<html>
+<head>
+  <title>Bug 484305 - Load workers as UTF-8</title>
+  <meta http-equiv="content-type" content="text/html; charset=KOI8-R">
+  <script type="text/javascript" src="/tests/SimpleTest/SimpleTest.js"></script>
+  <link rel="stylesheet" type="text/css" href="/tests/SimpleTest/test.css" />
+</head>
+<body>
+<a target="_blank" href="https://bugzilla.mozilla.org/show_bug.cgi?id=484305">Bug 484305 - Load workers as UTF-8</a>
+<p id="display"></p>
+<div id="content" style="display: none">
+
+</div>
+<pre id="test">
+<script class="testbody" type="text/javascript">
+
+SimpleTest.waitForExplicitFinish();
+
+var canonical = String.fromCharCode(0x41F, 0x440, 0x438, 0x432, 0x435, 0x442);
+ok(document.inputEncoding === "KOI8-R", "Document encoding is KOI8-R");
+
+// Worker sends two strings, one with `canonical` encoded in KOI8-R and one as UTF-8.
+// Since Worker scripts should always be decoded using UTF-8, even if the owning document's charset is different, the UTF-8 decode should match, while KOI8-R should fail.
+var counter = 0;
+var worker = new Worker("loadEncoding_worker.js");
+worker.onmessage = function(e) {
+  if (e.data.encoding === "KOI8-R") {
+    ok(e.data.text !== canonical, "KOI8-R decoded text should not match");
+  } else if (e.data.encoding === "UTF-8") {
+    ok(e.data.text === canonical, "UTF-8 decoded text should match");
+  }
+  counter++;
+  if (counter === 2)
+    SimpleTest.finish();
+}
+
+worker.onerror = function(e) {
+  ok(false, "Worker error");
+  SimpleTest.finish();
+}
+</script>
+
+</pre>
+</body>
+</html>
