| Index: LayoutTests/fast/encoding/api/utf-round-trip.html
|
| diff --git a/LayoutTests/fast/encoding/api/utf-round-trip.html b/LayoutTests/fast/encoding/api/utf-round-trip.html
|
| new file mode 100644
|
| index 0000000000000000000000000000000000000000..ef50a1b6f027de8d5981daa83faa114c2d0c8a6f
|
| --- /dev/null
|
| +++ b/LayoutTests/fast/encoding/api/utf-round-trip.html
|
| @@ -0,0 +1,97 @@
|
| +<!DOCTYPE html>
|
| +<script src="../../js/resources/js-test-pre.js"></script>
|
| +<script src="resources/shared.js"></script>
|
| +<script>
|
| +
|
| +description("Sanity check the Encoding API's handling of UTF encodings.");
|
| +
|
| +BATCH_SIZE = 0x1000; // Convert in batches spanning this made code points.
|
| +SKIP_SIZE = 0x77; // For efficiency, don't test every code point.
|
| +quiet = true; // Don't log every matching range.
|
| +
|
| +function fromCodePoint(cp) {
|
| + if (0xd800 <= cp && cp <= 0xdfff) throw new Error('Invalid code point');
|
| +
|
| + if (cp > 0xffff) {
|
| + // outside BMP - encode as surrogate pair
|
| + return String.fromCharCode(0xd800 + ((cp >> 10) & 0x3ff), 0xdc00 + (cp & 0x3ff));
|
| + }
|
| + return String.fromCharCode(i);
|
| +}
|
| +
|
| +function makeBatch(cp) {
|
| + var string = '';
|
| + for (var i = cp; i < cp + BATCH_SIZE && cp < 0x10FFFF; i += SKIP_SIZE) {
|
| + if (0xd800 <= i && i <= 0xdfff) {
|
| + // surrogate half
|
| + continue;
|
| + }
|
| + string += fromCodePoint(i);
|
| + }
|
| + return string;
|
| + }
|
| +
|
| +function testEncodeDecode(encoding, min, max) {
|
| + debug(encoding + " - Encode/Decode Range " + cpname(min) + " - " + cpname(max));
|
| +
|
| + function cpname(n) {
|
| + return 'U+' + ((n <= 0xFFFF) ?
|
| + ('0000' + n.toString(16).toUpperCase()).slice(-4) :
|
| + n.toString(16).toUpperCase());
|
| + }
|
| +
|
| + for (i = min; i < max; i += BATCH_SIZE) {
|
| + string = makeBatch(i);
|
| + encoded = new TextEncoder(encoding).encode(string);
|
| + decoded = new TextDecoder(encoding).decode(encoded);
|
| + shouldBe("string", "decoded", quiet);
|
| + }
|
| +
|
| + debug("no output means all ranges matched");
|
| + debug("");
|
| +}
|
| +
|
| +utf_encodings.forEach(function(encoding) {
|
| + testEncodeDecode(encoding, 0, 0x10FFFF);
|
| +});
|
| +
|
| +
|
| +// Inspired by:
|
| +// http://ecmanaut.blogspot.com/2006/07/encoding-decoding-utf8-in-javascript.html
|
| +function encode_utf8(string) {
|
| + var utf8 = unescape(encodeURIComponent(string));
|
| + var octets = [], i;
|
| + for (i = 0; i < utf8.length; i += 1) {
|
| + octets.push(utf8.charCodeAt(i));
|
| + }
|
| + return octets;
|
| +}
|
| +
|
| +function decode_utf8(octets) {
|
| + var utf8 = String.fromCharCode.apply(null, octets);
|
| + return decodeURIComponent(escape(utf8));
|
| +}
|
| +
|
| +debug("UTF-8 encoding (compare against unescape/encodeURIComponent)");
|
| +for (i = 0; i < 0x10FFFF; i += BATCH_SIZE) {
|
| + str = makeBatch(i);
|
| + expected = encode_utf8(str);
|
| + actual = new TextEncoder('UTF-8').encode(str);
|
| + shouldBe("actual", "expected", quiet);
|
| +}
|
| +debug("no output means all ranges matched");
|
| +debug("");
|
| +
|
| +debug("UTF-8 decoding (compare against decodeURIComponent/escape)");
|
| +for (i = 0; i < 0x10FFFF; i += BATCH_SIZE) {
|
| + str = makeBatch(i);
|
| + encoded = encode_utf8(str);
|
| + expected = decode_utf8(encoded);
|
| + actual = new TextDecoder('UTF-8').decode(new Uint8Array(encoded));
|
| + shouldBe("actual", "expected", quiet);
|
| +}
|
| +debug("no output means all ranges matched");
|
| +debug("");
|
| +
|
| +</script>
|
| +<script src="../../js/resources/js-test-post.js"></script>
|
|
|
Chromium Code Reviews
