LayoutTests/http/tests/workers/text-encoding.html - WebKit - Git at Google

 <html>
 <meta http-equiv="content-type" content="text/html; charset=windows-1251">
 <body>
 This test verifies handling of text encoding in workers. The behavior matches FF3.1b2 with a single exclusion (see below).<br>
 This is what's tested:<br>
 - If http header 'Content-Type' with 'charset' specified is on response with worker script or XHR payload, that encoding is used.<br>
 - In absence of http header, the script of the worker is decoded using UTF-8.<br>
 - In absence of http header, the content of the XHR request is decoded using UTF-8.<br>
 - The URLs used in workers (for subworkers or XHR) are always encoded using UTF-8 (in regular html documents parts of the query an hash may be encoded with other encodings).<br>
 - The base URL for the worker (used to resolve relative URLs for subworkers and XHR) is the URL of its script.<br>
 - importScripts() decodes the scripts using UTF-8.<br>

 <div style="background:beige; padding:10px;" id="status"></div>

 <script>
 if (window.testRunner) {
     testRunner.dumpAsText();
     testRunner.waitUntilDone();
 }

 // Wait for this many workers to finish their tests.
 // When worker is done, it sends 'exit' message.
 var workerCount = 2;

 // Messages from workers in separate threads will come in unstable order. Sort them to have a stable test.
 var statusStrings = new Array;

 function finishTest()
 {
     statusStrings.sort();
     var status_panel = document.getElementById("status");
     for (var i = 0; i < statusStrings.length; ++i) {
         status_panel.appendChild(document.createTextNode(statusStrings[i]));
         status_panel.appendChild(document.createElement("br"));
     }
     if (window.testRunner)
         testRunner.notifyDone();
 }

 function log(source, msg)
 {
     statusStrings.push(source + ": " + msg);

     if (msg == "exit" && --workerCount == 0)
         finishTest();
 }

 // Output current charset and a string in that encoding to make
 // sure this document is decoded as Windows-1251.
 log("Document encoding", document.inputEncoding);
 log("Document", "Ïðîâåðêà");

 log("Document, Workers", "All XHR responses should match this: " + String.fromCharCode(0x41F, 0x440, 0x438, 0x432, 0x435, 0x442));

 // Run a worker w/o http header. It should inherit the encoding of the document.
 var worker1 = new Worker("resources/worker-encoded.py");
 worker1.onmessage = function(evt) { log("worker 1", evt.data); };

 // Run a worker with http header specifying charset. This new charset should be in effect.
 var worker2 = new Worker("resources/worker-encoded.py?charset=koi8-r");
 worker2.onmessage = function(evt) { log("worker 2", evt.data); };

 // Request some content. It should be decoded using UTF-8 even though current document is Windows-1251.
 var xhr = new XMLHttpRequest();xhr.open("GET", "resources/xhr-response.py", false);
 xhr.send();log("Document: ", xhr.responseText);

 </script>
 </body>
 </html>
	<html>
	<meta http-equiv="content-type" content="text/html; charset=windows-1251">
	<body>
	This test verifies handling of text encoding in workers. The behavior matches FF3.1b2 with a single exclusion (see below).<br>
	This is what's tested:<br>
	- If http header 'Content-Type' with 'charset' specified is on response with worker script or XHR payload, that encoding is used.<br>
	- In absence of http header, the script of the worker is decoded using UTF-8.<br>
	- In absence of http header, the content of the XHR request is decoded using UTF-8.<br>
	- The URLs used in workers (for subworkers or XHR) are always encoded using UTF-8 (in regular html documents parts of the query an hash may be encoded with other encodings).<br>
	- The base URL for the worker (used to resolve relative URLs for subworkers and XHR) is the URL of its script.<br>
	- importScripts() decodes the scripts using UTF-8.<br>

	<div style="background:beige; padding:10px;" id="status"></div>

	<script>
	if (window.testRunner) {
	testRunner.dumpAsText();
	testRunner.waitUntilDone();
	}

	// Wait for this many workers to finish their tests.
	// When worker is done, it sends 'exit' message.
	var workerCount = 2;

	// Messages from workers in separate threads will come in unstable order. Sort them to have a stable test.
	var statusStrings = new Array;

	function finishTest()
	{
	statusStrings.sort();
	var status_panel = document.getElementById("status");
	for (var i = 0; i < statusStrings.length; ++i) {
	status_panel.appendChild(document.createTextNode(statusStrings[i]));
	status_panel.appendChild(document.createElement("br"));
	}
	if (window.testRunner)
	testRunner.notifyDone();
	}

	function log(source, msg)
	{
	statusStrings.push(source + ": " + msg);

	if (msg == "exit" && --workerCount == 0)
	finishTest();
	}

	// Output current charset and a string in that encoding to make
	// sure this document is decoded as Windows-1251.
	log("Document encoding", document.inputEncoding);
	log("Document", "Ïðîâåðêà");

	log("Document, Workers", "All XHR responses should match this: " + String.fromCharCode(0x41F, 0x440, 0x438, 0x432, 0x435, 0x442));

	// Run a worker w/o http header. It should inherit the encoding of the document.
	var worker1 = new Worker("resources/worker-encoded.py");
	worker1.onmessage = function(evt) { log("worker 1", evt.data); };

	// Run a worker with http header specifying charset. This new charset should be in effect.
	var worker2 = new Worker("resources/worker-encoded.py?charset=koi8-r");
	worker2.onmessage = function(evt) { log("worker 2", evt.data); };

	// Request some content. It should be decoded using UTF-8 even though current document is Windows-1251.
	var xhr = new XMLHttpRequest();xhr.open("GET", "resources/xhr-response.py", false);
	xhr.send();log("Document: ", xhr.responseText);

	</script>
	</body>
	</html>