<!DOCTYPE html>
<html>
<head>
<meta charset="big5"> <!-- test breaks if the server overrides this -->
<title>Big5 encoding errors (href, han)</title>
<meta name="timeout" content="long">
<script src="/resources/testharness.js"></script>
<script src="/resources/testharnessreport.js"></script>
<script src="big5_index.js"></script>
<script src="big5-encoder.js"></script>
<link rel="author" title="Richard Ishida" href="mailto:ishida@w3.org">
<link rel="help" href="https://encoding.spec.whatwg.org/#big5">
<meta name="assert" content="The browser produces percent-escaped character references when writing characters to an href value and encoding han characters that are not in the gbk encoding.">
<script>
function encode(input, expected, desc) {
	// tests whether a Unicode character is converted to an equivalent byte sequence by href
	// input: a Unicode character
	// expected: expected byte sequence
	// desc: what's being tested
	test(function() {
		var a = document.createElement("a"); // <a> uses document encoding for URL's query
		a.href = "https://example.com/?" + input;
		result = a.search.substr(1); // remove leading "?"
		assert_equals(normalizeStr(result), normalizeStr(expected));
	}, desc);
}

// create a simple list of just those code points for which there is no encoding is possible, from a representative subset of the BMP
codepoints = [];

for (i = 0x4e00; i < 0x9fba; i++) {
	result = big5Encoder(String.fromCodePoint(i));
	if (!result) {
		var item = {};
		codepoints.push(item);
		item.cp = i;
		item.expected = "%26%23" + item.cp + "%3B";
		item.desc = "cjk ";
	}
}

for (i = 0xf900; i < 0xfa6e; i++) {
	// compatibility
	result = big5Encoder(String.fromCodePoint(i));
	if (!result) {
		var item = {};
		codepoints.push(item);
		item.cp = i;
		item.expected = "%26%23" + item.cp + "%3B";
		item.desc = "compatibility ";
	}
}

for (i = 0xfa70; i < 0xfada; i++) {
	result = big5Encoder(String.fromCodePoint(i));
	if (!result) {
		var item = {};
		codepoints.push(item);
		item.cp = i;
		item.expected = "%26%23" + item.cp + "%3B";
		item.desc = "compatibility ";
	}
}

for (i = 0x3400; i < 0x4dbf; i++) {
	// cjk extension A
	result = big5Encoder(String.fromCodePoint(i));
	if (!result) {
		var item = {};
		codepoints.push(item);
		item.cp = i;
		item.expected = "%26%23" + item.cp + "%3B";
		item.desc = "extension A ";
	}
}

// run the tests
for (var x = 0; x < codepoints.length; x++) {
	encode(
		String.fromCodePoint(codepoints[x].cp),
		codepoints[x].expected,
		codepoints[x].desc +
			" U+" +
			codepoints[x].cp.toString(16).toUpperCase() +
			" " +
			String.fromCodePoint(codepoints[x].cp) +
			" " +
			codepoints[x].expected
	);
}

// NOTES
// this test relies on support for String.fromCodePoint, which appears to be supported by major desktop browsers
// the test excludes ASCII characters
</script>
</head>
<body>
<div id="log"></div>
</body>
</html>