The Tor Browser / file comparison
comparison: intl/uconv/tests/unit/test_bug340714.js
intl/uconv/tests/unit/test_bug340714.js
- branch
- TOR_BUG_9701
- changeset 15
- b8a032363ba2
equal
deleted
inserted
replaced
| -1:000000000000 | 0:b12cb459d86c |
|---|---|
| 1 /* Test case for bug 340714 | |
| 2 * | |
| 3 * Uses nsIConverterInputStream to decode UTF-16 text with all combinations | |
| 4 * of UTF-16BE and UTF-16LE with and without BOM. | |
| 5 * | |
| 6 * Sample text is: "Все счастливые семьи похожи друг на друга, каждая несчастливая семья несчастлива по-своему." | |
| 7 * | |
| 8 * The enclosing quotation marks are included in the sample text to test that | |
| 9 * UTF-16LE is recognized even when there is no BOM and the UTF-16LE decoder is | |
| 10 * not explicitly called. This only works when the first character of the text | |
| 11 * is an eight-bit character. | |
| 12 */ | |
| 13 | |
| 14 const beBOM="%FE%FF"; | |
| 15 const leBOM="%FF%FE"; | |
| 16 const sampleUTF16BE="%00%22%04%12%04%41%04%35%00%20%04%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%4B%04%35%00%20%04%41%04%35%04%3C%04%4C%04%38%00%20%04%3F%04%3E%04%45%04%3E%04%36%04%38%00%20%04%34%04%40%04%43%04%33%00%20%04%3D%04%30%00%20%04%34%04%40%04%43%04%33%04%30%00%2C%00%20%04%3A%04%30%04%36%04%34%04%30%04%4F%00%20%04%3D%04%35%04%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%30%04%4F%00%20%04%41%04%35%04%3C%04%4C%04%4F%00%20%04%3D%04%35%04%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%30%00%20%04%3F%04%3E%00%2D%04%41%04%32%04%3E%04%35%04%3C%04%43%00%2E%00%22"; | |
| 17 const sampleUTF16LE="%22%00%12%04%41%04%35%04%20%00%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%4B%04%35%04%20%00%41%04%35%04%3C%04%4C%04%38%04%20%00%3F%04%3E%04%45%04%3E%04%36%04%38%04%20%00%34%04%40%04%43%04%33%04%20%00%3D%04%30%04%20%00%34%04%40%04%43%04%33%04%30%04%2C%00%20%00%3A%04%30%04%36%04%34%04%30%04%4F%04%20%00%3D%04%35%04%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%30%04%4F%04%20%00%41%04%35%04%3C%04%4C%04%4F%04%20%00%3D%04%35%04%41%04%47%04%30%04%41%04%42%04%3B%04%38%04%32%04%30%04%20%00%3F%04%3E%04%2D%00%41%04%32%04%3E%04%35%04%3C%04%43%04%2E%00%22%00"; | |
| 18 const expected = "\"\u0412\u0441\u0435 \u0441\u0447\u0430\u0441\u0442\u043B\u0438\u0432\u044B\u0435 \u0441\u0435\u043C\u044C\u0438 \u043F\u043E\u0445\u043E\u0436\u0438 \u0434\u0440\u0443\u0433 \u043D\u0430 \u0434\u0440\u0443\u0433\u0430, \u043A\u0430\u0436\u0434\u0430\u044F \u043D\u0435\u0441\u0447\u0430\u0441\u0442\u043B\u0438\u0432\u0430\u044F \u0441\u0435\u043C\u044C\u044F \u043D\u0435\u0441\u0447\u0430\u0441\u0442\u043B\u0438\u0432\u0430 \u043F\u043E-\u0441\u0432\u043E\u0435\u043C\u0443.\""; | |
| 19 | |
| 20 function makeText(withBOM, charset) | |
| 21 { | |
| 22 var theText = eval("sample" + charset); | |
| 23 if (withBOM) { | |
| 24 if (charset == "UTF16BE") { | |
| 25 theText = beBOM + theText; | |
| 26 } else { | |
| 27 theText = leBOM + theText; | |
| 28 } | |
| 29 } | |
| 30 return theText; | |
| 31 } | |
| 32 | |
| 33 function testCase(withBOM, charset, charsetDec, decoder, bufferLength) | |
| 34 { | |
| 35 var dataURI = "data:text/plain;charset=" + charsetDec + "," + | |
| 36 makeText(withBOM, charset); | |
| 37 | |
| 38 var IOService = Components.Constructor("@mozilla.org/network/io-service;1", | |
| 39 "nsIIOService"); | |
| 40 var ConverterInputStream = | |
| 41 Components.Constructor("@mozilla.org/intl/converter-input-stream;1", | |
| 42 "nsIConverterInputStream", | |
| 43 "init"); | |
| 44 | |
| 45 var ios = new IOService(); | |
| 46 var channel = ios.newChannel(dataURI, "", null); | |
| 47 var testInputStream = channel.open(); | |
| 48 var testConverter = new ConverterInputStream(testInputStream, | |
| 49 decoder, | |
| 50 bufferLength, | |
| 51 0xFFFD); | |
| 52 | |
| 53 if (!(testConverter instanceof | |
| 54 Components.interfaces.nsIUnicharLineInputStream)) | |
| 55 throw "not line input stream"; | |
| 56 | |
| 57 var outStr = ""; | |
| 58 var more; | |
| 59 do { | |
| 60 // read the line and check for eof | |
| 61 var line = {}; | |
| 62 more = testConverter.readLine(line); | |
| 63 outStr += line.value; | |
| 64 } while (more); | |
| 65 | |
| 66 if (outStr != expected) { | |
| 67 dump("Failed with BOM = " + withBOM + "; charset = " + charset + | |
| 68 "; charset declaration = " + charsetDec + "; decoder = " + decoder + | |
| 69 "; bufferLength = " + bufferLength + "\n"); | |
| 70 if (outStr.length == expected.length) { | |
| 71 for (i = 0; i < outStr.length; ++i) { | |
| 72 if (outStr.charCodeAt(i) != expected.charCodeAt(i)) { | |
| 73 dump(i + ": " + outStr.charCodeAt(i).toString(16) + " != " + expected.charCodeAt(i).toString(16) + "\n"); | |
| 74 } | |
| 75 } | |
| 76 } | |
| 77 } | |
| 78 | |
| 79 // escape the strings before comparing for better readability | |
| 80 do_check_eq(escape(outStr), escape(expected)); | |
| 81 } | |
| 82 | |
| 83 function run_test() | |
| 84 { | |
| 85 /* BOM charset charset decoder buffer | |
| 86 declaration length */ | |
| 87 testCase(true, "UTF16LE", "UTF-16", "UTF-16", 64); | |
| 88 testCase(true, "UTF16BE", "UTF-16", "UTF-16", 64); | |
| 89 testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 64); | |
| 90 testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 64); | |
| 91 testCase(false, "UTF16LE", "UTF-16", "UTF-16", 64); | |
| 92 testCase(false, "UTF16BE", "UTF-16", "UTF-16", 64); | |
| 93 testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 64); | |
| 94 testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 64); | |
| 95 testCase(true, "UTF16LE", "UTF-16", "UTF-16", 65); | |
| 96 testCase(true, "UTF16BE", "UTF-16", "UTF-16", 65); | |
| 97 testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 65); | |
| 98 testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 65); | |
| 99 testCase(false, "UTF16LE", "UTF-16", "UTF-16", 65); | |
| 100 testCase(false, "UTF16BE", "UTF-16", "UTF-16", 65); | |
| 101 testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 65); | |
| 102 testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 65); | |
| 103 } |
