| OLD | NEW |
|---|
| (Empty) | |
| 1 <!DOCTYPE html> |
| 2 <script src="../../js/resources/js-test-pre.js"></script> |
| 3 <script src="resources/shared.js"></script> |
| 4 <script> |
| 5 |
| 6 description("Sanity check the Encoding API's handling of UTF encodings."); |
| 7 |
| 8 BATCH_SIZE = 0x1000; // Convert in batches spanning this made code points. |
| 9 SKIP_SIZE = 0x77; // For efficiency, don't test every code point. |
| 10 quiet = true; // Don't log every matching range. |
| 11 |
| 12 function fromCodePoint(cp) { |
| 13 if (0xd800 <= cp && cp <= 0xdfff) throw new Error('Invalid code point'); |
| 14 |
| 15 if (cp > 0xffff) { |
| 16 // outside BMP - encode as surrogate pair |
| 17 return String.fromCharCode(0xd800 + ((cp >> 10) & 0x3ff), 0xdc00 + (cp &
0x3ff)); |
| 18 } |
| 19 return String.fromCharCode(i); |
| 20 } |
| 21 |
| 22 function makeBatch(cp) { |
| 23 var string = ''; |
| 24 for (var i = cp; i < cp + BATCH_SIZE && cp < 0x10FFFF; i += SKIP_SIZE) { |
| 25 if (0xd800 <= i && i <= 0xdfff) { |
| 26 // surrogate half |
| 27 continue; |
| 28 } |
| 29 string += fromCodePoint(i); |
| 30 } |
| 31 return string; |
| 32 } |
| 33 |
| 34 function testEncodeDecode(encoding, min, max) { |
| 35 debug(encoding + " - Encode/Decode Range " + cpname(min) + " - " + cpname(ma
x)); |
| 36 |
| 37 function cpname(n) { |
| 38 return 'U+' + ((n <= 0xFFFF) ? |
| 39 ('0000' + n.toString(16).toUpperCase()).slice(-4) : |
| 40 n.toString(16).toUpperCase()); |
| 41 } |
| 42 |
| 43 for (i = min; i < max; i += BATCH_SIZE) { |
| 44 string = makeBatch(i); |
| 45 encoded = new TextEncoder(encoding).encode(string); |
| 46 decoded = new TextDecoder(encoding).decode(encoded); |
| 47 shouldBe("string", "decoded", quiet); |
| 48 } |
| 49 |
| 50 debug("no output means all ranges matched"); |
| 51 debug(""); |
| 52 } |
| 53 |
| 54 utf_encodings.forEach(function(encoding) { |
| 55 testEncodeDecode(encoding, 0, 0x10FFFF); |
| 56 }); |
| 57 |
| 58 |
| 59 // Inspired by: |
| 60 // http://ecmanaut.blogspot.com/2006/07/encoding-decoding-utf8-in-javascript.htm
l |
| 61 function encode_utf8(string) { |
| 62 var utf8 = unescape(encodeURIComponent(string)); |
| 63 var octets = [], i; |
| 64 for (i = 0; i < utf8.length; i += 1) { |
| 65 octets.push(utf8.charCodeAt(i)); |
| 66 } |
| 67 return octets; |
| 68 } |
| 69 |
| 70 function decode_utf8(octets) { |
| 71 var utf8 = String.fromCharCode.apply(null, octets); |
| 72 return decodeURIComponent(escape(utf8)); |
| 73 } |
| 74 |
| 75 debug("UTF-8 encoding (compare against unescape/encodeURIComponent)"); |
| 76 for (i = 0; i < 0x10FFFF; i += BATCH_SIZE) { |
| 77 str = makeBatch(i); |
| 78 expected = encode_utf8(str); |
| 79 actual = new TextEncoder('UTF-8').encode(str); |
| 80 shouldBe("actual", "expected", quiet); |
| 81 } |
| 82 debug("no output means all ranges matched"); |
| 83 debug(""); |
| 84 |
| 85 debug("UTF-8 decoding (compare against decodeURIComponent/escape)"); |
| 86 for (i = 0; i < 0x10FFFF; i += BATCH_SIZE) { |
| 87 str = makeBatch(i); |
| 88 encoded = encode_utf8(str); |
| 89 expected = decode_utf8(encoded); |
| 90 actual = new TextDecoder('UTF-8').decode(new Uint8Array(encoded)); |
| 91 shouldBe("actual", "expected", quiet); |
| 92 } |
| 93 debug("no output means all ranges matched"); |
| 94 debug(""); |
| 95 |
| 96 </script> |
| 97 <script src="../../js/resources/js-test-post.js"></script> |
| OLD | NEW |
|---|
Chromium Code Reviews
