dom/encoding/test/unit/test_misc.js@6474c204b198
dom/encoding/test/unit/test_misc.js
Wed, 31 Dec 2014 06:09:35 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 06:09:35 +0100
- changeset 0
- 6474c204b198
- permissions
- -rw-r--r--
Cloned upstream origin tor-browser at tor-browser-31.3.0esr-4.5-1-build1
revision ID fc1c9ff7c1b2defdbc039f12214767608f46423f for hacking purpose.
1 // NOTE: Requires testharness.js
2 // http://www.w3.org/2008/webapps/wiki/Harness
4 test(
5 function() {
6 var badStrings = [
7 { input: '\ud800', expected: '\ufffd' }, // Surrogate half
8 { input: '\udc00', expected: '\ufffd' }, // Surrogate half
9 { input: 'abc\ud800def', expected: 'abc\ufffddef' }, // Surrogate half
10 { input: 'abc\udc00def', expected: 'abc\ufffddef' }, // Surrogate half
11 { input: '\udc00\ud800', expected: '\ufffd\ufffd' } // Wrong order
12 ];
14 badStrings.forEach(
15 function(t) {
16 var encoded = new TextEncoder('utf-8').encode(t.input);
17 var decoded = new TextDecoder('utf-8').decode(encoded);
18 assert_equals(t.expected, decoded);
19 });
20 },
21 "bad data"
22 );
24 test(
25 function() {
26 var bad = [
27 { encoding: 'utf-8', input: [0xC0] }, // ends early
28 { encoding: 'utf-8', input: [0xC0, 0x00] }, // invalid trail
29 { encoding: 'utf-8', input: [0xC0, 0xC0] }, // invalid trail
30 { encoding: 'utf-8', input: [0xE0] }, // ends early
31 { encoding: 'utf-8', input: [0xE0, 0x00] }, // invalid trail
32 { encoding: 'utf-8', input: [0xE0, 0xC0] }, // invalid trail
33 { encoding: 'utf-8', input: [0xE0, 0x80, 0x00] }, // invalid trail
34 { encoding: 'utf-8', input: [0xE0, 0x80, 0xC0] }, // invalid trail
35 { encoding: 'utf-8', input: [0xFC, 0x80, 0x80, 0x80, 0x80, 0x80] }, // > 0x10FFFF
36 { encoding: 'utf-16le', input: [0x00] }, // truncated code unit
37 { encoding: 'utf-16le', input: [0x00, 0xd8] }, // surrogate half
38 { encoding: 'utf-16le', input: [0x00, 0xd8, 0x00, 0x00] }, // surrogate half
39 { encoding: 'utf-16le', input: [0x00, 0xdc, 0x00, 0x00] }, // trail surrogate
40 { encoding: 'utf-16le', input: [0x00, 0xdc, 0x00, 0xd8] } // swapped surrogates
41 // TODO: Single byte encoding cases
42 ];
44 bad.forEach(
45 function(t) {
46 assert_throws({name: 'EncodingError'}, function () {
47 new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input));
48 });
49 });
50 },
51 "fatal flag"
52 );
54 test(
55 function() {
56 var encodings = [
57 { label: 'utf-8', encoding: 'utf-8' },
58 { label: 'utf-16', encoding: 'utf-16le' },
59 { label: 'utf-16le', encoding: 'utf-16le' },
60 { label: 'utf-16be', encoding: 'utf-16be' },
61 { label: 'ascii', encoding: 'windows-1252' },
62 { label: 'iso-8859-1', encoding: 'windows-1252' }
63 ];
65 encodings.forEach(
66 function(test) {
67 assert_equals(new TextDecoder(test.label.toLowerCase()).encoding, test.encoding);
68 assert_equals(new TextDecoder(test.label.toUpperCase()).encoding, test.encoding);
69 });
70 },
71 "Encoding names are case insensitive"
72 );
74 test(
75 function() {
76 var utf8_bom = [0xEF, 0xBB, 0xBF];
77 var utf8 = [0x7A, 0xC2, 0xA2, 0xE6, 0xB0, 0xB4, 0xF0, 0x9D, 0x84, 0x9E, 0xF4, 0x8F, 0xBF, 0xBD];
79 var utf16le_bom = [0xff, 0xfe];
80 var utf16le = [0x7A, 0x00, 0xA2, 0x00, 0x34, 0x6C, 0x34, 0xD8, 0x1E, 0xDD, 0xFF, 0xDB, 0xFD, 0xDF];
82 var utf16be_bom = [0xfe, 0xff];
83 var utf16be = [0x00, 0x7A, 0x00, 0xA2, 0x6C, 0x34, 0xD8, 0x34, 0xDD, 0x1E, 0xDB, 0xFF, 0xDF, 0xFD];
85 var string = "z\xA2\u6C34\uD834\uDD1E\uDBFF\uDFFD"; // z, cent, CJK water, G-Clef, Private-use character
87 // missing BOMs
88 assert_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf8)), string);
89 assert_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16le)), string);
90 assert_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16be)), string);
92 // matching BOMs
93 assert_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf8_bom.concat(utf8))), string);
94 assert_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16le_bom.concat(utf16le))), string)
95 assert_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16be_bom.concat(utf16be))), string);
97 // matching BOMs split
98 var decoder8 = new TextDecoder('utf-8');
99 assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(0, 1)), {stream: true}), '');
100 assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(1).concat(utf8))), string);
101 assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(0, 2)), {stream: true}), '');
102 assert_equals(decoder8.decode(new Uint8Array(utf8_bom.slice(2).concat(utf8))), string);
103 var decoder16le = new TextDecoder('utf-16le');
104 assert_equals(decoder16le.decode(new Uint8Array(utf16le_bom.slice(0, 1)), {stream: true}), '');
105 assert_equals(decoder16le.decode(new Uint8Array(utf16le_bom.slice(1).concat(utf16le))), string);
106 var decoder16be = new TextDecoder('utf-16be');
107 assert_equals(decoder16be.decode(new Uint8Array(utf16be_bom.slice(0, 1)), {stream: true}), '');
108 assert_equals(decoder16be.decode(new Uint8Array(utf16be_bom.slice(1).concat(utf16be))), string);
110 // mismatching BOMs
111 assert_not_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf16le_bom.concat(utf8))), string);
112 assert_not_equals(new TextDecoder('utf-8').decode(new Uint8Array(utf16be_bom.concat(utf8))), string);
113 assert_not_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf8_bom.concat(utf16le))), string);
114 assert_not_equals(new TextDecoder('utf-16le').decode(new Uint8Array(utf16be_bom.concat(utf16le))), string);
115 assert_not_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf8_bom.concat(utf16be))), string);
116 assert_not_equals(new TextDecoder('utf-16be').decode(new Uint8Array(utf16le_bom.concat(utf16be))), string);
117 },
118 "Byte-order marks"
119 );
121 test(
122 function () {
123 assert_equals(new TextDecoder("utf-8").encoding, "utf-8"); // canonical case
124 assert_equals(new TextDecoder("UTF-16").encoding, "utf-16le"); // canonical case and name
125 assert_equals(new TextDecoder("UTF-16BE").encoding, "utf-16be"); // canonical case and name
126 assert_equals(new TextDecoder("iso8859-1").encoding, "windows-1252"); // canonical case and name
127 assert_equals(new TextDecoder("iso-8859-1").encoding, "windows-1252"); // canonical case and name
128 },
129 "Encoding names"
130 );
132 test(
133 function () {
134 ["utf-8", "utf-16le", "utf-16be"].forEach(function (encoding) {
135 var string = "\x00123ABCabc\x80\xFF\u0100\u1000\uFFFD\uD800\uDC00\uDBFF\uDFFF";
136 var encoded = new TextEncoder(encoding).encode(string);
138 for (var len = 1; len <= 5; ++len) {
139 var out = "", decoder = new TextDecoder(encoding);
140 for (var i = 0; i < encoded.length; i += len) {
141 var sub = [];
142 for (var j = i; j < encoded.length && j < i + len; ++j) {
143 sub.push(encoded[j]);
144 }
145 out += decoder.decode(new Uint8Array(sub), {stream: true});
146 }
147 out += decoder.decode();
148 assert_equals(out, string, "streaming decode " + encoding);
149 }
150 });
151 },
152 "Streaming Decode"
153 );
155 test(
156 function () {
157 var jis = [0x82, 0xC9, 0x82, 0xD9, 0x82, 0xF1];
158 var expected = "\u306B\u307B\u3093"; // Nihon
159 assert_equals(new TextDecoder("shift_jis").decode(new Uint8Array(jis)), expected);
160 },
161 "Shift_JIS Decode"
162 );
164 test(
165 function () {
166 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"];
168 encodings.forEach(function (encoding) {
169 var string = '', bytes = [];
170 for (var i = 0; i < 128; ++i) {
172 // Encodings that have escape codes in 0x00-0x7F
173 if (encoding === "hz-gb-2312" && i === 0x7E)
174 continue;
175 if (encoding === "iso-2022-jp" && i === 0x1B)
176 continue;
178 string += String.fromCharCode(i);
179 bytes.push(i);
180 }
181 var ascii_encoded = new TextEncoder('utf-8').encode(string);
182 assert_equals(new TextDecoder(encoding).decode(ascii_encoded), string, encoding);
183 //assert_array_equals(new TextEncoder(encoding).encode(string), bytes, encoding);
184 });
185 },
186 "Supersets of ASCII decode ASCII correctly"
187 );
189 test(
190 function () {
191 assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-8", {fatal: true}).decode(new Uint8Array([0xff])); });
192 // This should not hang:
193 new TextDecoder("utf-8").decode(new Uint8Array([0xff]));
195 assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-16", {fatal: true}).decode(new Uint8Array([0x00])); });
196 // This should not hang:
197 new TextDecoder("utf-16").decode(new Uint8Array([0x00]));
199 assert_throws({name: 'EncodingError'}, function() { new TextDecoder("utf-16be", {fatal: true}).decode(new Uint8Array([0x00])); });
200 // This should not hang:
201 new TextDecoder("utf-16be").decode(new Uint8Array([0x00]));
202 },
203 "Non-fatal errors at EOF"
204 );
206 test(
207 function () {
209 var utf_encodings = ["utf-8", "utf-16le", "utf-16be"];
211 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"];
213 utf_encodings.forEach(function(encoding) {
214 assert_equals(new TextDecoder(encoding).encoding, encoding);
215 assert_equals(new TextEncoder(encoding).encoding, encoding);
216 });
218 legacy_encodings.forEach(function(encoding) {
219 assert_equals(new TextDecoder(encoding).encoding, encoding);
220 assert_throws({name: 'TypeError'}, function() { new TextEncoder(encoding); });
221 });
222 },
223 "Non-UTF encodings supported only for decode, not encode"
224 );
