1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/dom/encoding/test/unit/test_misc.js Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,224 @@
1.4 +// NOTE: Requires testharness.js
1.5 +// http://www.w3.org/2008/webapps/wiki/Harness
1.6 +
1.7 +test(
1.8 + function() {
1.9 + var badStrings = [
1.10 + { input: '\ud800', expected: '\ufffd' }, // Surrogate half
1.11 + { input: '\udc00', expected: '\ufffd' }, // Surrogate half
1.12 + { input: 'abc\ud800def', expected: 'abc\ufffddef' }, // Surrogate half
1.13 + { input: 'abc\udc00def', expected: 'abc\ufffddef' }, // Surrogate half
1.14 + { input: '\udc00\ud800', expected: '\ufffd\ufffd' } // Wrong order
1.15 + ];
1.16 +
1.17 + badStrings.forEach(
1.18 + function(t) {
1.19 + var encoded = new TextEncoder('utf-8').encode(t.input);
1.20 + var decoded = new TextDecoder('utf-8').decode(encoded);
1.21 + assert_equals(t.expected, decoded);
1.22 + });
1.23 + },
1.24 + "bad data"
1.25 +);
1.26 +
1.27 +test(
1.28 + function() {
1.29 + var bad = [
1.30 + { encoding: 'utf-8', input: [0xC0] }, // ends early
1.31 + { encoding: 'utf-8', input: [0xC0, 0x00] }, // invalid trail
1.32 + { encoding: 'utf-8', input: [0xC0, 0xC0] }, // invalid trail
1.33 + { encoding: 'utf-8', input: [0xE0] }, // ends early
1.34 + { encoding: 'utf-8', input: [0xE0, 0x00] }, // invalid trail
1.35 + { encoding: 'utf-8', input: [0xE0, 0xC0] }, // invalid trail
1.36 + { encoding: 'utf-8', input: [0xE0, 0x80, 0x00] }, // invalid trail
1.37 + { encoding: 'utf-8', input: [0xE0, 0x80, 0xC0] }, // invalid trail
1.38 + { encoding: 'utf-8', input: [0xFC, 0x80, 0x80, 0x80, 0x80, 0x80] }, // > 0x10FFFF
1.39 + { encoding: 'utf-16le', input: [0x00] }, // truncated code unit
1.40 + { encoding: 'utf-16le', input: [0x00, 0xd8] }, // surrogate half
1.41 + { encoding: 'utf-16le', input: [0x00, 0xd8, 0x00, 0x00] }, // surrogate half
1.42 + { encoding: 'utf-16le', input: [0x00, 0xdc, 0x00, 0x00] }, // trail surrogate
1.43 + { encoding: 'utf-16le', input: [0x00, 0xdc, 0x00, 0xd8] } // swapped surrogates
1.44 + // TODO: Single byte encoding cases
1.45 + ];
1.46 +
1.47 + bad.forEach(
1.48 + function(t) {
1.49 + assert_throws({name: 'EncodingError'}, function () {
1.50 + new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input));
1.51 + });
1.52 + });
1.53 + },
1.54 + "fatal flag"
1.55 +);
1.56 +
1.57 +test(
1.58 + function() {
1.59 + var encodings = [
1.60 + { label: 'utf-8', encoding: 'utf-8' },
1.61 + { label: 'utf-16', encoding: 'utf-16le' },
1.62 + { label: 'utf-16le', encoding: 'utf-16le' },
1.63 + { label: 'utf-16be', encoding: 'utf-16be' },
1.64 + { label: 'ascii', encoding: 'windows-1252' },
1.65 + { label: 'iso-8859-1', encoding: 'windows-1252' }
1.66 + ];
1.67 +
1.68 + encodings.forEach(
1.69 + function(test) {
1.70 + assert_equals(new TextDecoder(test.label.toLowerCase()).encoding, test.encoding);
1.71 + assert_equals(new TextDecoder(test.label.toUpperCase()).encoding, test.encoding);
1.72 + });
1.73 + },
1.74 + "Encoding names are case insensitive"
1.75 +);
1.76 +
1.77 +test(
1.78 + function() {
1.79 + var utf8_bom = [0xEF, 0xBB, 0xBF];
1.80 + var utf8 = [0x7A, 0xC2, 0xA2, 0xE6, 0xB0, 0xB4, 0xF0, 0x9D, 0x84, 0x9E, 0xF4, 0x8F, 0xBF, 0xBD];
1.81 +
1.82 + var utf16le_bom = [0xff, 0xfe];
1.83 + var utf16le = [0x7A, 0x00, 0xA2, 0x00, 0x34, 0x6C, 0x34, 0xD8, 0x1E, 0xDD, 0xFF, 0xDB, 0xFD, 0xDF];
1.84 +
1.85 + var utf16be_bom = [0xfe, 0xff];
1.86 + var utf16be = [0x00, 0x7A, 0x00, 0xA2, 0x6C, 0x34, 0xD8, 0x34, 0xDD, 0x1E, 0xDB, 0xFF, 0xDF, 0xFD];
1.87 +
1.88 + var string = "z\xA2\u6C34\uD834\uDD1E\uDBFF\uDFFD"; // z, cent, CJK water, G-Clef, Private-use character
1.89 +
1.90 + // missing BOMs
1.91 + assert_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf8)), string);
1.92 + assert_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16le)), string);
1.93 + assert_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16be)), string);
1.94 +
1.95 + // matching BOMs
1.96 + assert_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf8_bom.concat(utf8))), string);
1.97 + assert_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16le_bom.concat(utf16le))), string)
1.98 + assert_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16be_bom.concat(utf16be))), string);
1.99 +
1.100 + // matching BOMs split
1.101 + var decoder8 = new TextDecoder('utf-8');
1.102 + assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(0, 1)), {stream: true}), '');
1.103 + assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(1).concat(utf8))), string);
1.104 + assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(0, 2)), {stream: true}), '');
1.105 + assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(2).concat(utf8))), string);
1.106 + var decoder16le = new TextDecoder('utf-16le');
1.107 + assert_equals(decoder16le.decode(new Uint8Array(utf16le_bom.slice(0, 1)), {stream: true}), '');
1.108 + assert_equals(decoder16le.decode(new Uint8Array(utf16le_bom.slice(1).concat(utf16le))), string);
1.109 + var decoder16be = new TextDecoder('utf-16be');
1.110 + assert_equals(decoder16be.decode(new Uint8Array(utf16be_bom.slice(0, 1)), {stream: true}), '');
1.111 + assert_equals(decoder16be.decode(new Uint8Array(utf16be_bom.slice(1).concat(utf16be))), string);
1.112 +
1.113 + // mismatching BOMs
1.114 + assert_not_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf16le_bom.concat(utf8))), string);
1.115 + assert_not_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf16be_bom.concat(utf8))), string);
1.116 + assert_not_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf8_bom.concat(utf16le))), string);
1.117 + assert_not_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16be_bom.concat(utf16le))), string);
1.118 + assert_not_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf8_bom.concat(utf16be))), string);
1.119 + assert_not_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16le_bom.concat(utf16be))), string);
1.120 + },
1.121 + "Byte-order marks"
1.122 +);
1.123 +
1.124 +test(
1.125 + function () {
1.126 + assert_equals(new TextDecoder("utf-8").encoding, "utf-8"); // canonical case
1.127 + assert_equals(new TextDecoder("UTF-16").encoding, "utf-16le"); // canonical case and name
1.128 + assert_equals(new TextDecoder("UTF-16BE").encoding, "utf-16be"); // canonical case and name
1.129 + assert_equals(new TextDecoder("iso8859-1").encoding, "windows-1252"); // canonical case and name
1.130 + assert_equals(new TextDecoder("iso-8859-1").encoding, "windows-1252"); // canonical case and name
1.131 + },
1.132 + "Encoding names"
1.133 +);
1.134 +
1.135 +test(
1.136 + function () {
1.137 + ["utf-8", "utf-16le", "utf-16be"].forEach(function (encoding) {
1.138 + var string = "\x00123ABCabc\x80\xFF\u0100\u1000\uFFFD\uD800\uDC00\uDBFF\uDFFF";
1.139 + var encoded = new TextEncoder(encoding).encode(string);
1.140 +
1.141 + for (var len = 1; len <= 5; ++len) {
1.142 + var out = "", decoder = new TextDecoder(encoding);
1.143 + for (var i = 0; i < encoded.length; i += len) {
1.144 + var sub = [];
1.145 + for (var j = i; j < encoded.length && j < i + len; ++j) {
1.146 + sub.push(encoded[j]);
1.147 + }
1.148 + out += decoder.decode(new Uint8Array(sub), {stream: true});
1.149 + }
1.150 + out += decoder.decode();
1.151 + assert_equals(out, string, "streaming decode " + encoding);
1.152 + }
1.153 + });
1.154 + },
1.155 + "Streaming Decode"
1.156 +);
1.157 +
1.158 +test(
1.159 + function () {
1.160 + var jis = [0x82, 0xC9, 0x82, 0xD9, 0x82, 0xF1];
1.161 + var expected = "\u306B\u307B\u3093"; // Nihon
1.162 + assert_equals(new TextDecoder("shift_jis").decode(new Uint8Array(jis)), expected);
1.163 + },
1.164 + "Shift_JIS Decode"
1.165 +);
1.166 +
1.167 +test(
1.168 + function () {
1.169 + var encodings = ["utf-8", "ibm866", "iso-8859-2", "iso-8859-3", "iso-8859-4", "iso-8859-5", "iso-8859-6", "iso-8859-7", "iso-8859-8", "iso-8859-8-i", "iso-8859-10", "iso-8859-13", "iso-8859-14", "iso-8859-15", "iso-8859-16", "koi8-r", "koi8-u", "macintosh", "windows-874", "windows-1250", "windows-1251", "windows-1252", "windows-1253", "windows-1254", "windows-1255", "windows-1256", "windows-1257", "windows-1258", "x-mac-cyrillic", "gbk", "gb18030", "hz-gb-2312", "big5", "euc-jp", "iso-2022-jp", "shift_jis", "euc-kr", "x-user-defined"];
1.170 +
1.171 + encodings.forEach(function (encoding) {
1.172 + var string = '', bytes = [];
1.173 + for (var i = 0; i < 128; ++i) {
1.174 +
1.175 + // Encodings that have escape codes in 0x00-0x7F
1.176 + if (encoding === "hz-gb-2312" && i === 0x7E)
1.177 + continue;
1.178 + if (encoding === "iso-2022-jp" && i === 0x1B)
1.179 + continue;
1.180 +
1.181 + string += String.fromCharCode(i);
1.182 + bytes.push(i);
1.183 + }
1.184 + var ascii_encoded = new TextEncoder('utf-8').encode(string);
1.185 + assert_equals(new TextDecoder(encoding).decode(ascii_encoded), string, encoding);
1.186 + //assert_array_equals(new TextEncoder(encoding).encode(string), bytes, encoding);
1.187 + });
1.188 + },
1.189 + "Supersets of ASCII decode ASCII correctly"
1.190 +);
1.191 +
1.192 +test(
1.193 + function () {
1.194 + assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-8", {fatal: true}).decode(new Uint8Array([0xff])); });
1.195 + // This should not hang:
1.196 + new TextDecoder("utf-8").decode(new Uint8Array([0xff]));
1.197 +
1.198 + assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-16", {fatal: true}).decode(new Uint8Array([0x00])); });
1.199 + // This should not hang:
1.200 + new TextDecoder("utf-16").decode(new Uint8Array([0x00]));
1.201 +
1.202 + assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-16be", {fatal: true}).decode(new Uint8Array([0x00])); });
1.203 + // This should not hang:
1.204 + new TextDecoder("utf-16be").decode(new Uint8Array([0x00]));
1.205 + },
1.206 + "Non-fatal errors at EOF"
1.207 +);
1.208 +
1.209 +test(
1.210 + function () {
1.211 +
1.212 + var utf_encodings = ["utf-8", "utf-16le", "utf-16be"];
1.213 +
1.214 + var legacy_encodings = ["ibm866", "iso-8859-2", "iso-8859-3", "iso-8859-4", "iso-8859-5", "iso-8859-6", "iso-8859-7", "iso-8859-8", "iso-8859-8-i", "iso-8859-10", "iso-8859-13", "iso-8859-14", "iso-8859-15", "iso-8859-16", "koi8-r", "koi8-u", "macintosh", "windows-874", "windows-1250", "windows-1251", "windows-1252", "windows-1253", "windows-1254", "windows-1255", "windows-1256", "windows-1257", "windows-1258", "x-mac-cyrillic", "gbk", "gb18030", "hz-gb-2312", "big5", "euc-jp", "iso-2022-jp", "shift_jis", "euc-kr", "x-user-defined"];
1.215 +
1.216 + utf_encodings.forEach(function(encoding) {
1.217 + assert_equals(new TextDecoder(encoding).encoding, encoding);
1.218 + assert_equals(new TextEncoder(encoding).encoding, encoding);
1.219 + });
1.220 +
1.221 + legacy_encodings.forEach(function(encoding) {
1.222 + assert_equals(new TextDecoder(encoding).encoding, encoding);
1.223 + assert_throws({name: 'TypeError'}, function() { new TextEncoder(encoding); });
1.224 + });
1.225 + },
1.226 + "Non-UTF encodings supported only for decode, not encode"
1.227 +);
