1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/uconv/tests/unit/test_bug340714.js Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,103 @@
1.4 +/* Test case for bug 340714
1.5 + *
1.6 + * Uses nsIConverterInputStream to decode UTF-16 text with all combinations
1.7 + * of UTF-16BE and UTF-16LE with and without BOM.
1.8 + *
1.9 + * Sample text is: "Все счастливые семьи похожи друг на друга, каждая несчастливая семья несчастлива по-своему."
1.10 + *
1.11 + * The enclosing quotation marks are included in the sample text to test that
1.12 + * UTF-16LE is recognized even when there is no BOM and the UTF-16LE decoder is
1.13 + * not explicitly called. This only works when the first character of the text
1.14 + * is an eight-bit character.
1.15 + */
1.16 +
1.17 +const beBOM="%FE%FF";
1.18 +const leBOM="%FF%FE";
1.19 +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";
1.20 +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";
1.21 +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.\"";
1.22 +
1.23 +function makeText(withBOM, charset)
1.24 +{
1.25 + var theText = eval("sample" + charset);
1.26 + if (withBOM) {
1.27 + if (charset == "UTF16BE") {
1.28 + theText = beBOM + theText;
1.29 + } else {
1.30 + theText = leBOM + theText;
1.31 + }
1.32 + }
1.33 + return theText;
1.34 +}
1.35 +
1.36 +function testCase(withBOM, charset, charsetDec, decoder, bufferLength)
1.37 +{
1.38 + var dataURI = "data:text/plain;charset=" + charsetDec + "," +
1.39 + makeText(withBOM, charset);
1.40 +
1.41 + var IOService = Components.Constructor("@mozilla.org/network/io-service;1",
1.42 + "nsIIOService");
1.43 + var ConverterInputStream =
1.44 + Components.Constructor("@mozilla.org/intl/converter-input-stream;1",
1.45 + "nsIConverterInputStream",
1.46 + "init");
1.47 +
1.48 + var ios = new IOService();
1.49 + var channel = ios.newChannel(dataURI, "", null);
1.50 + var testInputStream = channel.open();
1.51 + var testConverter = new ConverterInputStream(testInputStream,
1.52 + decoder,
1.53 + bufferLength,
1.54 + 0xFFFD);
1.55 +
1.56 + if (!(testConverter instanceof
1.57 + Components.interfaces.nsIUnicharLineInputStream))
1.58 + throw "not line input stream";
1.59 +
1.60 + var outStr = "";
1.61 + var more;
1.62 + do {
1.63 + // read the line and check for eof
1.64 + var line = {};
1.65 + more = testConverter.readLine(line);
1.66 + outStr += line.value;
1.67 + } while (more);
1.68 +
1.69 + if (outStr != expected) {
1.70 + dump("Failed with BOM = " + withBOM + "; charset = " + charset +
1.71 + "; charset declaration = " + charsetDec + "; decoder = " + decoder +
1.72 + "; bufferLength = " + bufferLength + "\n");
1.73 + if (outStr.length == expected.length) {
1.74 + for (i = 0; i < outStr.length; ++i) {
1.75 + if (outStr.charCodeAt(i) != expected.charCodeAt(i)) {
1.76 + dump(i + ": " + outStr.charCodeAt(i).toString(16) + " != " + expected.charCodeAt(i).toString(16) + "\n");
1.77 + }
1.78 + }
1.79 + }
1.80 + }
1.81 +
1.82 + // escape the strings before comparing for better readability
1.83 + do_check_eq(escape(outStr), escape(expected));
1.84 +}
1.85 +
1.86 +function run_test()
1.87 +{
1.88 + /* BOM charset charset decoder buffer
1.89 + declaration length */
1.90 + testCase(true, "UTF16LE", "UTF-16", "UTF-16", 64);
1.91 + testCase(true, "UTF16BE", "UTF-16", "UTF-16", 64);
1.92 + testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 64);
1.93 + testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 64);
1.94 + testCase(false, "UTF16LE", "UTF-16", "UTF-16", 64);
1.95 + testCase(false, "UTF16BE", "UTF-16", "UTF-16", 64);
1.96 + testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 64);
1.97 + testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 64);
1.98 + testCase(true, "UTF16LE", "UTF-16", "UTF-16", 65);
1.99 + testCase(true, "UTF16BE", "UTF-16", "UTF-16", 65);
1.100 + testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 65);
1.101 + testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 65);
1.102 + testCase(false, "UTF16LE", "UTF-16", "UTF-16", 65);
1.103 + testCase(false, "UTF16BE", "UTF-16", "UTF-16", 65);
1.104 + testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 65);
1.105 + testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 65);
1.106 +}
