diff options
Diffstat (limited to 'intl/uconv/tests/unit')
89 files changed, 3362 insertions, 0 deletions
diff --git a/intl/uconv/tests/unit/data/unicode-conversion.utf16.txt b/intl/uconv/tests/unit/data/unicode-conversion.utf16.txt Binary files differnew file mode 100644 index 0000000000..8a28caadfc --- /dev/null +++ b/intl/uconv/tests/unit/data/unicode-conversion.utf16.txt diff --git a/intl/uconv/tests/unit/data/unicode-conversion.utf16be.txt b/intl/uconv/tests/unit/data/unicode-conversion.utf16be.txt Binary files differnew file mode 100644 index 0000000000..e1c4e86dba --- /dev/null +++ b/intl/uconv/tests/unit/data/unicode-conversion.utf16be.txt diff --git a/intl/uconv/tests/unit/data/unicode-conversion.utf16le.txt b/intl/uconv/tests/unit/data/unicode-conversion.utf16le.txt Binary files differnew file mode 100644 index 0000000000..cde8acb70b --- /dev/null +++ b/intl/uconv/tests/unit/data/unicode-conversion.utf16le.txt diff --git a/intl/uconv/tests/unit/data/unicode-conversion.utf8.txt b/intl/uconv/tests/unit/data/unicode-conversion.utf8.txt new file mode 100644 index 0000000000..b45dff35d0 --- /dev/null +++ b/intl/uconv/tests/unit/data/unicode-conversion.utf8.txt @@ -0,0 +1,43 @@ +This is a Unicode converter test file containing Unicode data. Its encoding is +determined by the second-to-last dot-separated component of the filename. For +example, if this file is named foo.utf8.txt, its encoding is UTF-8; if this file +is named foo.utf16le.txt, its encoding is UTF-16LE. This file is marked as +binary in Mozilla's version control system so that it's not accidentally +"mangled". + +The contents of each file must differ ONLY by encoding, so if you edit this file +you must edit all files with the name of this file (with the encoding-specific +part changed). + +== BEGIN UNICODE TEST DATA == + +== U+000000 -- U+00007F == + +BELL: "" +DATA LINK ESCAPE: "" +DELETE: "" + +== U+000080 -- U+0007FF == + +CONTROL: "" +NO-BREAK SPACE: " " +POUND SIGN: "£" +YEN SIGN: "¥" +CURRENCY SIGN: "¢" +LATIN SMALL LETTER SCHWA: "ə" +LATIN LETTER BILABIAL PERCUSSIVE: "ʬ" + +== U+000800 -- U+00FFFF == + +BUGINESE LETTER TA: "ᨈ" +BUGINESE LETTER DA: "ᨉ" +AIRPLANE: "✈" +ZERO WIDTH NO-BREAK SPACE: "" + + +== U+010000 -- U+10FFFF == + +SHAVIAN LETTER IAN: "𐑾" +MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE: "𝅘𝅥𝅲" +CJK UNIFIED IDEOGRAPH-20000: "𠀀" +(private use U+10FEFF): "" diff --git a/intl/uconv/tests/unit/head_charsetConversionTests.js b/intl/uconv/tests/unit/head_charsetConversionTests.js new file mode 100644 index 0000000000..4fbf6e9af7 --- /dev/null +++ b/intl/uconv/tests/unit/head_charsetConversionTests.js @@ -0,0 +1,110 @@ +var CC = Components.Constructor; + +function CreateScriptableConverter() { + var ScriptableUnicodeConverter = CC( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + return new ScriptableUnicodeConverter(); +} + +function checkDecode(converter, charset, inText, expectedText) { + try { + converter.charset = charset; + } catch (e) { + converter.charset = "iso-8859-1"; + } + + dump("testing decoding from " + charset + " to Unicode.\n"); + try { + var outText = converter.ConvertToUnicode(inText); + } catch (e) { + outText = "\ufffd"; + } + + if (outText != expectedText) { + for (var i = 0; i < inText.length; ++i) { + var inn = inText[i]; + var out = outText[i]; + var expected = expectedText[i]; + if (out != expected) { + dump( + "Decoding error at position " + + i + + ": for input " + + escape(inn) + + " expected " + + escape(expected) + + " but got " + + escape(out) + + "\n" + ); + } + } + } + Assert.equal(outText, expectedText); +} + +function checkEncode(converter, charset, inText, expectedText) { + try { + converter.charset = charset; + } catch (e) { + converter.charset = "iso-8859-1"; + } + + dump("testing encoding from Unicode to " + charset + "\n"); + var outText = converter.ConvertFromUnicode(inText) + converter.Finish(); + + if (outText != expectedText) { + for (var i = 0; i < inText.length; ++i) { + var inn = inText[i]; + var out = outText[i]; + var expected = expectedText[i]; + if (out != expected) { + dump( + "Encoding error at position " + + i + + ": for input " + + escape(inn) + + " expected " + + escape(expected) + + " but got " + + escape(out) + + "\n" + ); + } + } + } + Assert.equal(outText, expectedText); +} + +function testDecodeAliases(aliases, inString, expectedString) { + var converter = CreateScriptableConverter(); + for (var i = 0; i < aliases.length; ++i) { + checkDecode(converter, aliases[i], inString, expectedString); + } +} + +function testEncodeAliases(aliases, inString, expectedString) { + var converter = CreateScriptableConverter(); + for (var i = 0; i < aliases.length; ++i) { + checkEncode(converter, aliases[i], inString, expectedString); + } +} + +function testDecodeAliasesInternal(aliases, inString, expectedString) { + var converter = CreateScriptableConverter(); + converter.isInternal = true; + for (var i = 0; i < aliases.length; ++i) { + checkDecode(converter, aliases[i], inString, expectedString); + } +} + +function testEncodeAliasesInternal(aliases, inString, expectedString) { + var converter = CreateScriptableConverter(); + converter.isInternal = true; + for (var i = 0; i < aliases.length; ++i) { + checkEncode(converter, aliases[i], inString, expectedString); + } +} diff --git a/intl/uconv/tests/unit/test_bug116882.js b/intl/uconv/tests/unit/test_bug116882.js new file mode 100644 index 0000000000..5e76b30aa4 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug116882.js @@ -0,0 +1,11 @@ +/* Tests conversion of undefined and illegal sequences from Shift-JIS + * to Unicode (bug 116882) + */ + +const inText = "\xfd\xfe\xff\x81\x20\x81\x3f\x86\x3c"; +const expectedText = "\ufffd\ufffd\ufffd\ufffd \ufffd?\ufffd<"; +const charset = "Shift_JIS"; + +function run_test() { + checkDecode(CreateScriptableConverter(), charset, inText, expectedText); +} diff --git a/intl/uconv/tests/unit/test_bug317216.js b/intl/uconv/tests/unit/test_bug317216.js new file mode 100644 index 0000000000..cc10ef313e --- /dev/null +++ b/intl/uconv/tests/unit/test_bug317216.js @@ -0,0 +1,165 @@ +/* Test case for bug 317216 + * + * Uses nsIConverterInputStream to decode UTF-16 text with valid surrogate + * pairs and lone surrogate characters + * + * Sample text is: "A" in Mathematical Bold Capitals (U+1D400) + * + * The test uses buffers of 4 different lengths to test end of buffer in mid- + * UTF16 character and mid-surrogate pair + */ + +const { NetUtil } = ChromeUtils.importESModule( + "resource://gre/modules/NetUtil.sys.mjs" +); + +const test = [ + // 0: Valid surrogate pair + [ + "%D8%35%DC%20%00%2D%00%2D", + // expected: surrogate pair + "\uD835\uDC20--", + ], + // 1: Lone high surrogate + [ + "%D8%35%00%2D%00%2D", + // expected: one replacement char + "\uFFFD--", + ], + // 2: Lone low surrogate + [ + "%DC%20%00%2D%00%2D", + // expected: one replacement char + "\uFFFD--", + ], + // 3: Two high surrogates + [ + "%D8%35%D8%35%00%2D%00%2D", + // expected: two replacement chars + "\uFFFD\uFFFD--", + ], + // 4: Two low surrogates + [ + "%DC%20%DC%20%00%2D%00%2D", + // expected: two replacement chars + "\uFFFD\uFFFD--", + ], + // 5: Low surrogate followed by high surrogate + [ + "%DC%20%D8%35%00%2D%00%2D", + // expected: two replacement chars + "\uFFFD\uFFFD--", + ], + // 6: Lone high surrogate followed by valid surrogate pair + [ + "%D8%35%D8%35%DC%20%00%2D%00%2D", + // expected: replacement char followed by surrogate pair + "\uFFFD\uD835\uDC20--", + ], + // 7: Lone low surrogate followed by valid surrogate pair + [ + "%DC%20%D8%35%DC%20%00%2D%00%2D", + // expected: replacement char followed by surrogate pair + "\uFFFD\uD835\uDC20--", + ], + // 8: Valid surrogate pair followed by lone high surrogate + [ + "%D8%35%DC%20%D8%35%00%2D%00%2D", + // expected: surrogate pair followed by replacement char + "\uD835\uDC20\uFFFD--", + ], + // 9: Valid surrogate pair followed by lone low surrogate + [ + "%D8%35%DC%20%DC%20%00%2D%00%2D", + // expected: surrogate pair followed by replacement char + "\uD835\uDC20\uFFFD--", + ], + // 10: Lone high surrogate at the end of the input + [ + "%D8%35%", + // expected: one replacement char + "\uFFFD", + ], + // 11: Half code unit at the end of the input + [ + "%D8", + // expected: one replacement char + "\uFFFD", + ], +]; + +const ConverterInputStream = Components.Constructor( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" +); + +function testCase(testText, expectedText, bufferLength, charset) { + var dataURI = "data:text/plain;charset=" + charset + "," + testText; + var channel = NetUtil.newChannel({ + uri: dataURI, + loadUsingSystemPrincipal: true, + }); + var testInputStream = channel.open(); + var testConverter = new ConverterInputStream( + testInputStream, + charset, + bufferLength, + 0xfffd + ); + + if (!(testConverter instanceof Ci.nsIUnicharLineInputStream)) { + throw new Error("not line input stream"); + } + + var outStr = ""; + var more; + do { + // read the line and check for eof + var line = {}; + more = testConverter.readLine(line); + outStr += line.value; + } while (more); + + // escape the strings before comparing for better readability + Assert.equal(escape(outStr), escape(expectedText)); +} + +// Add 32 dummy characters to the test text to work around the minimum buffer +// size of an ns*Buffer +const MINIMUM_BUFFER_SIZE = 32; +function padBytes(str) { + var padding = ""; + for (var i = 0; i < MINIMUM_BUFFER_SIZE; ++i) { + padding += "%00%2D"; + } + return padding + str; +} + +function padUnichars(str) { + var padding = ""; + for (var i = 0; i < MINIMUM_BUFFER_SIZE; ++i) { + padding += "-"; + } + return padding + str; +} + +// Byte-swap %-encoded utf-16 +function flip(str) { + return str.replace(/(%..)(%..)/g, "$2$1"); +} + +function run_test() { + for (var i = 0; i < 12; ++i) { + for ( + var bufferLength = MINIMUM_BUFFER_SIZE; + bufferLength < MINIMUM_BUFFER_SIZE + 4; + ++bufferLength + ) { + var testText = padBytes(test[i][0]); + var expectedText = padUnichars(test[i][1]); + testCase(testText, expectedText, bufferLength, "UTF-16BE"); + testCase(flip(testText), expectedText, bufferLength, "UTF-16LE"); + } + } +} diff --git a/intl/uconv/tests/unit/test_bug321379.js b/intl/uconv/tests/unit/test_bug321379.js new file mode 100644 index 0000000000..338f59688e --- /dev/null +++ b/intl/uconv/tests/unit/test_bug321379.js @@ -0,0 +1,35 @@ +// Tests that calling close on a converter in/output stream doesn't crash +// (bug 321379) + +function run_test() { + var StorageStream = Components.Constructor( + "@mozilla.org/storagestream;1", + "nsIStorageStream", + "init" + ); + var ConverterInputStream = Components.Constructor( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" + ); + var ConverterOutputStream = Components.Constructor( + "@mozilla.org/intl/converter-output-stream;1", + "nsIConverterOutputStream", + "init" + ); + + var storage = new StorageStream(1024, -1, null); + + // Output + var outStr = storage.getOutputStream(0); + var out = new ConverterOutputStream(outStr, "UTF-8"); + out.writeString("Foo."); + out.close(); + out.close(); // This line should not crash. It should just do nothing. + + // Input + var inStr = storage.newInputStream(0); + var inp = new ConverterInputStream(inStr, "UTF-8", 1024, 0xfffd); + inp.close(); + inp.close(); // This line should not crash. It should just do nothing. +} diff --git a/intl/uconv/tests/unit/test_bug340714.js b/intl/uconv/tests/unit/test_bug340714.js new file mode 100644 index 0000000000..fdd30543f2 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug340714.js @@ -0,0 +1,123 @@ +/* Test case for bug 340714 + * + * Uses nsIConverterInputStream to decode UTF-16 text with all combinations + * of UTF-16BE and UTF-16LE with and without BOM. + * + * Sample text is: "Все счастливые семьи похожи друг на друга, каждая несчастливая семья несчастлива по-своему." + * + * The enclosing quotation marks are included in the sample text to test that + * UTF-16LE is recognized even when there is no BOM and the UTF-16LE decoder is + * not explicitly called. This only works when the first character of the text + * is an eight-bit character. + */ + +const { NetUtil } = ChromeUtils.importESModule( + "resource://gre/modules/NetUtil.sys.mjs" +); + +const beBOM = "%FE%FF"; +const leBOM = "%FF%FE"; +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"; +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"; +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."'; + +Services.prefs.setBoolPref("security.allow_eval_with_system_principal", true); +registerCleanupFunction(() => { + Services.prefs.clearUserPref("security.allow_eval_with_system_principal"); +}); + +function makeText(withBOM, charset) { + const isBE = charset === "UTF16BE"; + const sampleText = isBE ? sampleUTF16BE : sampleUTF16LE; + const bom = isBE ? beBOM : leBOM; + return withBOM ? bom + sampleText : sampleText; +} + +function testCase(withBOM, charset, charsetDec, decoder, bufferLength) { + var dataURI = + "data:text/plain;charset=" + charsetDec + "," + makeText(withBOM, charset); + + var ConverterInputStream = Components.Constructor( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" + ); + + var channel = NetUtil.newChannel({ + uri: dataURI, + loadUsingSystemPrincipal: true, + }); + var testInputStream = channel.open(); + var testConverter = new ConverterInputStream( + testInputStream, + decoder, + bufferLength, + 0xfffd + ); + + if (!(testConverter instanceof Ci.nsIUnicharLineInputStream)) { + throw new Error("not line input stream"); + } + + var outStr = ""; + var more; + do { + // read the line and check for eof + var line = {}; + more = testConverter.readLine(line); + outStr += line.value; + } while (more); + + if (outStr != expected) { + dump( + "Failed with BOM = " + + withBOM + + "; charset = " + + charset + + "; charset declaration = " + + charsetDec + + "; decoder = " + + decoder + + "; bufferLength = " + + bufferLength + + "\n" + ); + if (outStr.length == expected.length) { + for (let i = 0; i < outStr.length; ++i) { + if (outStr.charCodeAt(i) != expected.charCodeAt(i)) { + dump( + i + + ": " + + outStr.charCodeAt(i).toString(16) + + " != " + + expected.charCodeAt(i).toString(16) + + "\n" + ); + } + } + } + } + + // escape the strings before comparing for better readability + Assert.equal(escape(outStr), escape(expected)); +} + +function run_test() { + /* BOM charset charset decoder buffer + declaration length */ + testCase(true, "UTF16LE", "UTF-16", "UTF-16BE", 64); + testCase(true, "UTF16BE", "UTF-16", "UTF-16LE", 64); + testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 64); + testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 64); + testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 64); + testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 64); + testCase(true, "UTF16LE", "UTF-16", "UTF-16BE", 65); + testCase(true, "UTF16BE", "UTF-16", "UTF-16LE", 65); + testCase(true, "UTF16LE", "UTF-16", "UTF-16LE", 65); + testCase(true, "UTF16BE", "UTF-16", "UTF-16BE", 65); + testCase(false, "UTF16LE", "UTF-16", "UTF-16LE", 65); + testCase(false, "UTF16BE", "UTF-16", "UTF-16BE", 65); +} diff --git a/intl/uconv/tests/unit/test_bug381412.Big5-HKSCS.js b/intl/uconv/tests/unit/test_bug381412.Big5-HKSCS.js new file mode 100644 index 0000000000..4108dc1090 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.Big5-HKSCS.js @@ -0,0 +1,64 @@ +const charset = "Big5-HKSCS"; + +function dumpStrings(inString, outString) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); +} + +function error(inString, outString, msg) { + dumpStrings(inString, outString); + do_throw("security risk: " + msg); +} + +function run_test() { + var ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + var converter = new ScriptableUnicodeConverter(); + converter.charset = charset; + + var leadByte, trailByte; + var inString; + for (leadByte = 1; leadByte < 0x100; ++leadByte) { + for (trailByte = 1; trailByte < 0x100; ++trailByte) { + inString = String.fromCharCode(leadByte, trailByte, 65); + var outString = converter.ConvertToUnicode(inString) + converter.Finish(); + switch (outString.length) { + case 1: + error(inString, outString, "2 byte sequence eaten"); + break; + case 2: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 1 ASCII"); + } + break; + case 3: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 2 ASCII"); + } + break; + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug381412.Big5.js b/intl/uconv/tests/unit/test_bug381412.Big5.js new file mode 100644 index 0000000000..45c8bafc83 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.Big5.js @@ -0,0 +1,64 @@ +const charset = "Big5"; + +function dumpStrings(inString, outString) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); +} + +function error(inString, outString, msg) { + dumpStrings(inString, outString); + do_throw("security risk: " + msg); +} + +function run_test() { + var ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + var converter = new ScriptableUnicodeConverter(); + converter.charset = charset; + + var leadByte, trailByte; + var inString; + for (leadByte = 1; leadByte < 0x100; ++leadByte) { + for (trailByte = 1; trailByte < 0x100; ++trailByte) { + inString = String.fromCharCode(leadByte, trailByte, 65); + var outString = converter.ConvertToUnicode(inString) + converter.Finish(); + switch (outString.length) { + case 1: + error(inString, outString, "2 byte sequence eaten"); + break; + case 2: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 1 ASCII"); + } + break; + case 3: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 2 ASCII"); + } + break; + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug381412.euc-kr.js b/intl/uconv/tests/unit/test_bug381412.euc-kr.js new file mode 100644 index 0000000000..58d36c76f4 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.euc-kr.js @@ -0,0 +1,64 @@ +const charset = "EUC-KR"; + +function dumpStrings(inString, outString) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); +} + +function error(inString, outString, msg) { + dumpStrings(inString, outString); + do_throw("security risk: " + msg); +} + +function run_test() { + var ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + var converter = new ScriptableUnicodeConverter(); + converter.charset = charset; + + var leadByte, trailByte; + var inString; + for (leadByte = 1; leadByte < 0x100; ++leadByte) { + for (trailByte = 1; trailByte < 0x100; ++trailByte) { + inString = String.fromCharCode(leadByte, trailByte, 65); + var outString = converter.ConvertToUnicode(inString) + converter.Finish(); + switch (outString.length) { + case 1: + error(inString, outString, "2 byte sequence eaten"); + break; + case 2: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 1 ASCII"); + } + break; + case 3: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 2 ASCII"); + } + break; + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug381412.euc_jp.js b/intl/uconv/tests/unit/test_bug381412.euc_jp.js new file mode 100644 index 0000000000..7e07eb9e69 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.euc_jp.js @@ -0,0 +1,92 @@ +const charset = "EUC-JP"; +const ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" +); +var gConverter; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function test(inString) { + var outString = gConverter.ConvertToUnicode(inString) + gConverter.Finish(); + + switch (outString.length) { + case 0: + case 1: + case 2: + error(inString, outString, "Unexpected error"); + break; + case 3: + error(inString, outString, "3 byte sequence eaten"); + break; + case 4: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 && + outString.charCodeAt(2) < 0x80 && + outString.charCodeAt(3) < 0x80 + ) { + error(inString, outString, "3 byte sequence converted to 1 ASCII"); + } + break; + case 5: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 && + outString.charCodeAt(2) < 0x80 && + outString.charCodeAt(3) < 0x80 && + outString.charCodeAt(4) < 0x80 + ) { + error(inString, outString, "3 byte sequence converted to 2 ASCII"); + } + break; + case 6: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 && + outString.charCodeAt(2) < 0x80 && + outString.charCodeAt(3) < 0x80 && + outString.charCodeAt(4) < 0x80 && + outString.charCodeAt(5) < 0x80 + ) { + error(inString, outString, "3 byte sequence converted to 3 ASCII"); + } + break; + } +} + +function run_test() { + gConverter = new ScriptableUnicodeConverter(); + gConverter.charset = charset; + + var byte1, byte2, byte3; + for (byte1 = 1; byte1 < 0x100; ++byte1) { + for (byte2 = 1; byte2 < 0x100; ++byte2) { + if (byte1 == 0x8f) { + for (byte3 = 1; byte3 < 0x100; ++byte3) { + test(String.fromCharCode(byte1, byte2, byte3) + "foo"); + } + } else { + test(String.fromCharCode(byte1, byte2) + " foo"); + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug381412.gb2312.js b/intl/uconv/tests/unit/test_bug381412.gb2312.js new file mode 100644 index 0000000000..df680dadae --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.gb2312.js @@ -0,0 +1,60 @@ +const charset = "GB2312"; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function run_test() { + var ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + var converter = new ScriptableUnicodeConverter(); + converter.charset = charset; + + var leadByte, trailByte; + var inString; + for (leadByte = 1; leadByte < 0x100; ++leadByte) { + for (trailByte = 1; trailByte < 0x100; ++trailByte) { + inString = String.fromCharCode(leadByte, trailByte, 65); + var outString = converter.ConvertToUnicode(inString) + converter.Finish(); + switch (outString.length) { + case 1: + error(inString, outString, "2 byte sequence eaten"); + break; + case 2: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 1 ASCII"); + } + break; + case 3: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 2 ASCII"); + } + break; + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug381412.js b/intl/uconv/tests/unit/test_bug381412.js new file mode 100644 index 0000000000..89849bf5e6 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug381412.js @@ -0,0 +1,60 @@ +const charset = "Shift_JIS"; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function run_test() { + var ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" + ); + + var converter = new ScriptableUnicodeConverter(); + converter.charset = charset; + + var leadByte, trailByte; + var inString; + for (leadByte = 1; leadByte < 0x100; ++leadByte) { + for (trailByte = 1; trailByte < 0x100; ++trailByte) { + inString = String.fromCharCode(leadByte, trailByte, 65); + var outString = converter.ConvertToUnicode(inString) + converter.Finish(); + switch (outString.length) { + case 1: + error(inString, outString, "2 byte sequence eaten"); + break; + case 2: + if ( + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 1 ASCII"); + } + break; + case 3: + if ( + outString != inString && + outString.charCodeAt(0) < 0x80 && + outString.charCodeAt(1) < 0x80 + ) { + error(inString, outString, "2 byte sequence converted to 2 ASCII"); + } + break; + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug396637.js b/intl/uconv/tests/unit/test_bug396637.js new file mode 100644 index 0000000000..6aac53e5d1 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug396637.js @@ -0,0 +1,9 @@ +// Tests conversion of a single byte from UTF-16 to Unicode + +const inString = "A"; +const expectedString = ""; +const charset = "UTF-16BE"; + +function run_test() { + checkDecode(CreateScriptableConverter(), charset, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_bug399257.js b/intl/uconv/tests/unit/test_bug399257.js new file mode 100644 index 0000000000..9acd3e9b38 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug399257.js @@ -0,0 +1,80 @@ +// Tests encoding of characters below U+0020 +const inString = "Hello\u000aWorld"; +const expectedString = "Hello\nWorld"; + +function run_test() { + var failures = false; + var encodingConverter = CreateScriptableConverter(); + + var encoders = [ + "Big5", + "Big5-HKSCS", + "EUC-JP", + "EUC-KR", + "gb18030", + "gbk", + "IBM866", + "ISO-2022-JP", + "ISO-8859-1", + "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", + "Shift_JIS", + "windows-1250", + "windows-1251", + "windows-1252", + "windows-1253", + "windows-1254", + "windows-1255", + "windows-1256", + "windows-1257", + "windows-1258", + "windows-874", + "macintosh", + "x-mac-cyrillic", + "x-user-defined", + "UTF-8", + ]; + + var counter = 0; + while (counter < encoders.length) { + var charset = encoders[counter++]; + dump("testing " + counter + " " + charset + "\n"); + + encodingConverter.charset = charset; + var codepageString = + encodingConverter.ConvertFromUnicode(inString) + + encodingConverter.Finish(); + if (codepageString != expectedString) { + dump(charset + " encoding failed\n"); + for (var i = 0; i < expectedString.length; ++i) { + if (codepageString.charAt(i) != expectedString.charAt(i)) { + dump( + i.toString(16) + + ": 0x" + + codepageString.charCodeAt(i).toString(16) + + " != " + + expectedString.charCodeAt(i).toString(16) + + "\n" + ); + } + } + failures = true; + } + } + if (failures) { + do_throw("test failed\n"); + } +} diff --git a/intl/uconv/tests/unit/test_bug457886.js b/intl/uconv/tests/unit/test_bug457886.js new file mode 100644 index 0000000000..21c3036901 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug457886.js @@ -0,0 +1,12 @@ +// Tests conversion from Unicode to ISO-2022-JP + +const inString = + "\u3042\u3044\u3046\u3048\u304A\u000D\u000A\u304B\u304D\u304F\u3051\u3053"; + +const expectedString = '\x1B$B$"$$$&$($*\x1B(B\x0D\x0A\x1B$B$+$-$/$1$3\x1B(B'; + +const charset = "ISO-2022-JP"; + +function run_test() { + checkEncode(CreateScriptableConverter(), charset, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_bug522931.js b/intl/uconv/tests/unit/test_bug522931.js new file mode 100644 index 0000000000..2dae8d72e9 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug522931.js @@ -0,0 +1,4 @@ +// crash test with invaild parameter (bug 522931) +function run_test() { + Assert.equal(Services.textToSubURI.UnEscapeAndConvert("UTF-8", null), ""); +} diff --git a/intl/uconv/tests/unit/test_bug563283.js b/intl/uconv/tests/unit/test_bug563283.js new file mode 100644 index 0000000000..49c13dcfcb --- /dev/null +++ b/intl/uconv/tests/unit/test_bug563283.js @@ -0,0 +1,53 @@ +// Tests conversion from Unicode to ISO-2022-JP with Hankaku characters + +const inStrings = [ + // ｡｢｣､･ｦｧｨｩｪｫｬｭｮｯｰｱｲｳｴｵｶｷｸｹｺｻｼｽｾｿﾀﾁﾂﾃﾄﾅﾆﾇﾈﾉﾊﾋﾌﾍﾎﾏﾐﾑﾒﾓﾔﾕﾖﾗﾘﾙﾚﾛﾜﾝﾞﾟ + "\uFF61\uFF62\uFF63\uFF64\uFF65\uFF66\uFF67\uFF68\uFF69\uFF6A\uFF6B\uFF6C\uFF6D\uFF6E\uFF6F\uFF70\uFF71\uFF72\uFF73\uFF74\uFF75\uFF76\uFF77\uFF78\uFF79\uFF7A\uFF7B\uFF7C\uFF7D\uFF7E\uFF7F\uFF80\uFF81\uFF82\uFF83\uFF84\uFF85\uFF86\uFF87\uFF88\uFF89\uFF8A\uFF8B\uFF8C\uFF8D\uFF8E\uFF8F\uFF90\uFF91\uFF92\uFF93\uFF94\uFF95\uFF96\uFF97\uFF98\uFF99\uFF9A\uFF9B\uFF9C\uFF9D\uFF9E\uFF9F", + // equivalent to + // 。「」、・ヲァィゥェォャュョッーアイウエオカキクケコサシスセソタチツテトナニヌネノハヒフヘホマミムメモヤユヨラリルレロワン゛゜ + // \u3002\u300c\u300d\u3001\u30fb\u30f2\u30a1\u30a3\u30a5\u30a7\u30a9\u30e3\u30e5\u30e7\u30c3\u30fc\u30a2\u30a4\u30a6\u30a8\u30aa\u30ab\u30ad\u30af\u30b1\u30b3\u30b5\u30b7\u30b9\u30bb\u30bd\u30bf\u30c1\u30c4\u30c6\u30c8\u30ca\u30cb\u30cc\u30cd\u30ce\u30cf\u30d2\u30d5\u30d8\u30db\u30de\u30df\u30e0\u30e1\u30e2\u30e4\u30e6\u30e8\u30e9\u30ea\u30eb\u30ec\u30ed\u30ef\u30f3\u309b\u309c" + + // ｶﾞｷﾞｸﾞｹﾞｺﾞｻﾞｼﾞｽﾞｾﾞｿﾞﾀﾞﾁﾞﾂﾞﾃﾞﾄﾞﾊﾞﾋﾞﾌﾞﾍﾞﾎﾞ + "\uFF76\uFF9E\uFF77\uFF9E\uFF78\uFF9E\uFF79\uFF9E\uFF7A\uFF9E\uFF7B\uFF9E\uFF7C\uFF9E\uFF7D\uFF9E\uFF7E\uFF9E\uFF7F\uFF9E\uFF80\uFF9E\uFF81\uFF9E\uFF82\uFF9E\uFF83\uFF9E\uFF84\uFF9E\uFF8A\uFF9E\uFF8B\uFF9E\uFF8C\uFF9E\uFF8D\uFF9E\uFF8E\uFF9E", + // equivalent to + // カ゛キ゛ク゛ケ゛コ゛サ゛シ゛ス゛セ゛ソ゛タ゛チ゛ツ゛テ゛ト゛ハ゛ヒ゛フ゛ヘ゛ホ゛ + // \u30AB\u309B\u30AD\u309B\u30AF\u309B\u30B1\u309B\u30B3\u309B\u30B5\u309B\u30B7\u309B\u30B9\u309B\u30BB\u309B\u30BD\u309B\u30BF\u309B\u30C1\u309B\u30C4\u309B\u30C6\u309B\u30C8\u309B\u30CF\u309B\u30D2\u309B\u30D5\u309B\u30D8\u309B\u30DB\u309B + + // ﾊﾟﾋﾟﾌﾟﾍﾟﾎﾟ + "\uFF8A\uFF9F\uFF8B\uFF9F\uFF8C\uFF9F\uFF8D\uFF9F\uFF8E\uFF9F", + // equivalent to + // ハ゜ヒ゜フ゜ヘ゜ホ゜ + // \u30CF\u309C\u30D2\u309C\u30D5\u309C\u30D8\u309C\u30DB\u309C" + + // Hankaku preceded and followed by regular Katakana (no change of charset) + // フランツ・ﾖｰｾﾞﾌ・ハイドン + "\u30D5\u30E9\u30F3\u30C4\u30FB\uFF96\uFF70\uFF7E\uFF9E\uFF8C\u30FB\u30CF\u30A4\u30C9\u30F3", + + // Hankaku preceded and followed by Roman (charset change) + // Mozilla (ﾓｼﾞﾗ) Foundation + "Mozilla (\uFF93\uFF7C\uFF9E\uFF97) Foundation", + + // Hankaku preceded and followed by unencodable characters + // दिल्ली･ﾃﾞﾘｰ･ਦਿੱਲੀ + "\u0926\u093F\u0932\u094D\u0932\u0940\uFF65\uFF83\uFF9E\uFF98\uFF70\uFF65\u0A26\u0A3F\u0A71\u0A32\u0A40", +]; + +const expectedStrings = [ + "\x1B$B!#!V!W!\x22!&%r%!%#%%%'%)%c%e%g%C!<%\x22%$%&%(%*%+%-%/%1%3%5%7%9%;%=%?%A%D%F%H%J%K%L%M%N%O%R%U%X%[%^%_%`%a%b%d%f%h%i%j%k%l%m%o%s!+!,\x1B(B", + "\x1B$B%+!+%-!+%/!+%1!+%3!+%5!+%7!+%9!+%;!+%=!+%?!+%A!+%D!+%F!+%H!+%O!+%R!+%U!+%X!+%[!+\x1B(B", + "\x1B$B%O!,%R!,%U!,%X!,%[!,\x1B(B", + "\x1B$B%U%i%s%D!&%h!<%;!+%U!&%O%$%I%s\x1B(B", + "Mozilla (\x1B$B%b%7!+%i\x1B(B) Foundation", + "??????\x1B$B!&%F!+%j!<!&\x1B(B?????", +]; + +function run_test() { + for (var i = 0; i < inStrings.length; ++i) { + checkEncode( + CreateScriptableConverter(), + "ISO-2022-JP", + inStrings[i], + expectedStrings[i] + ); + } +} diff --git a/intl/uconv/tests/unit/test_bug563618.js b/intl/uconv/tests/unit/test_bug563618.js new file mode 100644 index 0000000000..f2d8a6e353 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug563618.js @@ -0,0 +1,99 @@ +/* Test case for bug 563618 + * + * Uses nsIConverterInputStream to decode invalid EUC-JP text + * + */ + +const { NetUtil } = ChromeUtils.importESModule( + "resource://gre/modules/NetUtil.sys.mjs" +); + +const test = [ + // 0: 0x8e followed by hi byte, not valid JIS X 0201 + [ + "abcdefghijklmnopqrstuvwxyz12test00%8e%80foobar", + // expected: one replacement character, invalid byte eaten + "abcdefghijklmnopqrstuvwxyz12test00\uFFFDfoobar", + ], + // 1: 0x8e followed by ASCII + [ + "abcdefghijklmnopqrstuvwxyz12test01%8efoobar", + // expected: one replacement character, invalid byte not eaten + "abcdefghijklmnopqrstuvwxyz12test01\uFFFDfoobar", + ], + // 2: JIS X 0208 lead byte followed by invalid hi byte + [ + "abcdefghijklmnopqrstuvwxyz12test02%bf%80foobar", + // expected: one replacement character, invalid byte eaten + "abcdefghijklmnopqrstuvwxyz12test02\uFFFDfoobar", + ], + // 3: JIS X 0208 lead byte followed by ASCII + [ + "abcdefghijklmnopqrstuvwxyz12test03%bffoobar", + // expected: one replacement character, invalid byte not eaten + "abcdefghijklmnopqrstuvwxyz12test03\uFFFDfoobar", + ], +]; + +const ConverterInputStream = Components.Constructor( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" +); + +function testCase(testText, expectedText, bufferLength, charset) { + var dataURI = "data:text/plain;charset=" + charset + "," + testText; + var channel = NetUtil.newChannel({ + uri: dataURI, + loadUsingSystemPrincipal: true, + }); + var testInputStream = channel.open(); + var testConverter = new ConverterInputStream( + testInputStream, + charset, + bufferLength, + 0xfffd + ); + + if (!(testConverter instanceof Ci.nsIUnicharLineInputStream)) { + throw new Error("not line input stream"); + } + + var outStr = ""; + var more; + do { + // read the line and check for eof + var line = {}; + more = testConverter.readLine(line); + outStr += line.value; + } while (more); + + if (outStr != expectedText) { + dump("Failed with bufferLength = " + bufferLength + "\n"); + if (outStr.length == expectedText.length) { + for (let i = 0; i < outStr.length; ++i) { + if (outStr.charCodeAt(i) != expectedText.charCodeAt(i)) { + dump( + i + + ": " + + outStr.charCodeAt(i).toString(16) + + " != " + + expectedText.charCodeAt(i).toString(16) + + "\n" + ); + } + } + } + } + + // escape the strings before comparing for better readability + Assert.equal(escape(outStr), escape(expectedText)); +} + +function run_test() { + for (var i = 0; i < test.length; ++i) { + for (var bufferLength = 32; bufferLength < 40; ++bufferLength) { + testCase(test[i][0], test[i][1], bufferLength, "EUC-JP"); + } + } +} diff --git a/intl/uconv/tests/unit/test_bug601429.js b/intl/uconv/tests/unit/test_bug601429.js new file mode 100644 index 0000000000..af5d357c50 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug601429.js @@ -0,0 +1,84 @@ +// Tests whether characters above 0x7F decode to ASCII characters liable to +// expose XSS vulnerabilities + +function run_test() { + var failures = false; + var decodingConverter = CreateScriptableConverter(); + + var decoders = [ + "Big5", + "Big5-HKSCS", + "EUC-JP", + "EUC-KR", + "gb18030", + "IBM866", + "ISO-2022-JP", + "ISO-8859-1", + "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", + "Shift_JIS", + "windows-1250", + "windows-1251", + "windows-1252", + "windows-1253", + "windows-1254", + "windows-1255", + "windows-1256", + "windows-1257", + "windows-1258", + "windows-874", + "macintosh", + "x-mac-cyrillic", + "x-user-defined", + "UTF-8", + ]; + + var counter = 0; + while (counter < decoders.length) { + var charset = decoders[counter++]; + dump("testing " + counter + " " + charset + "\n"); + + decodingConverter.charset = charset; + for (var i = 0x80; i < 0x100; ++i) { + var inString = String.fromCharCode(i); + var outString; + try { + outString = + decodingConverter.ConvertToUnicode(inString) + + decodingConverter.Finish(); + } catch (e) { + outString = String.fromCharCode(0xfffd); + } + for (var n = 0; n < outString.length; ++n) { + var outChar = outString.charAt(n); + if (outChar == "<" || outChar == ">" || outChar == "/") { + dump( + charset + + " has a problem: " + + escape(inString) + + " decodes to '" + + outString + + "'\n" + ); + failures = true; + } + } + } + } + if (failures) { + do_throw("test failed\n"); + } +} diff --git a/intl/uconv/tests/unit/test_bug715319.dbcs.js b/intl/uconv/tests/unit/test_bug715319.dbcs.js new file mode 100644 index 0000000000..3ba405a925 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug715319.dbcs.js @@ -0,0 +1,56 @@ +// 2-byte charsets: +const charsets = ["Big5", "EUC-KR"]; +const ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" +); +var gConverter; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function IsASCII(charCode) { + return charCode <= 0x7e; +} + +function test(inString) { + var outString = gConverter.ConvertToUnicode(inString) + gConverter.Finish(); + + var outLen = outString.length; + + if ( + IsASCII(inString.charCodeAt(1)) && + (outLen < 4 || outString.charCodeAt(outLen - 4) == 0xfffd) + ) { + error(inString, outString, "ASCII input eaten in " + gConverter.charset); + } +} + +function run_test() { + gConverter = new ScriptableUnicodeConverter(); + for (var i = 0; i < charsets.length; ++i) { + gConverter.charset = charsets[i]; + + var byte1, byte2; + for (byte1 = 1; byte1 < 0x100; ++byte1) { + for (byte2 = 1; byte2 < 0x100; ++byte2) { + test(String.fromCharCode(byte1, byte2) + "foo"); + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug715319.euc_jp.js b/intl/uconv/tests/unit/test_bug715319.euc_jp.js new file mode 100644 index 0000000000..537d073d14 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug715319.euc_jp.js @@ -0,0 +1,77 @@ +const charset = "EUC-JP"; +const ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" +); +var gConverter; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function IsASCII(charCode) { + return charCode <= 0x7e; +} + +function IsNotGR(charCode) { + return charCode < 0xa1 || charCode > 0xfe; +} + +function test(inString) { + var outString = gConverter.ConvertToUnicode(inString) + gConverter.Finish(); + + var outLen = outString.length; + if ( + IsASCII(inString.charCodeAt(1)) && + inString.charCodeAt(1) != outString.charCodeAt(outLen - 5) + ) { + error(inString, outString, "ASCII second byte eaten"); + } else if ( + IsASCII(inString.charCodeAt(2)) && + inString.charCodeAt(2) != outString.charCodeAt(outLen - 4) + ) { + error(inString, outString, "ASCII third byte eaten"); + } else if ( + inString.charCodeAt(0) == 0x8f && + inString.charCodeAt(1) > 0x7f && + IsNotGR(inString.charCodeAt(2)) && + !( + outString.charCodeAt(outLen - 4) == 0xfffd || + outString.charCodeAt(outLen - 4) == inString.charCodeAt(2) + ) + ) { + error(inString, outString, "non-GR third byte eaten"); + } +} + +function run_test() { + gConverter = new ScriptableUnicodeConverter(); + gConverter.charset = charset; + + var byte1, byte2, byte3; + for (byte1 = 1; byte1 < 0x100; ++byte1) { + for (byte2 = 1; byte2 < 0x100; ++byte2) { + if (byte1 == 0x8f) { + for (byte3 = 1; byte3 < 0x100; ++byte3) { + test(String.fromCharCode(byte1, byte2, byte3) + "foo"); + } + } else { + test(String.fromCharCode(byte1, byte2) + " foo"); + } + } + } +} diff --git a/intl/uconv/tests/unit/test_bug715319.gb2312.js b/intl/uconv/tests/unit/test_bug715319.gb2312.js new file mode 100644 index 0000000000..f780ab81d1 --- /dev/null +++ b/intl/uconv/tests/unit/test_bug715319.gb2312.js @@ -0,0 +1,87 @@ +const charset = "GB2312"; +const ScriptableUnicodeConverter = Components.Constructor( + "@mozilla.org/intl/scriptableunicodeconverter", + "nsIScriptableUnicodeConverter" +); +var gConverter; + +function error(inString, outString, msg) { + var dispIn = ""; + var dispOut = ""; + var i; + for (i = 0; i < inString.length; ++i) { + dispIn += " x" + inString.charCodeAt(i).toString(16); + } + if (!outString.length) { + dispOut = "<empty>"; + } else { + for (i = 0; i < outString.length; ++i) { + dispOut += " x" + outString.charCodeAt(i).toString(16); + } + } + dump('"' + dispIn + '" ==> "' + dispOut + '"\n'); + do_throw("security risk: " + msg); +} + +function IsASCII(charCode) { + return charCode <= 0x7e; +} + +function test(inString) { + var outString = gConverter.ConvertToUnicode(inString) + gConverter.Finish(); + + var outLen = outString.length; + for (var pos = 1; pos < 3; ++pos) { + let outPos = outLen - (9 - pos); + if (outPos < 0) { + outPos = 0; + } + let c0 = inString.charCodeAt(0); + let c1 = inString.charCodeAt(1); + let c2 = inString.charCodeAt(2); + let c3 = inString.charCodeAt(3); + if ( + IsASCII(inString.charCodeAt(pos)) && + !( + outString.charCodeAt(outPos) == inString.charCodeAt(pos) || + outString.charCodeAt(outPos) != 0xfffd || + // legal 4 byte range + (0x81 <= c0 && + c0 <= 0xfe && + 0x30 <= c1 && + c1 <= 0x39 && + 0x81 <= c2 && + c2 <= 0xfe && + 0x30 <= c3 && + c3 <= 0x39) + ) + ) { + dump("pos = " + pos + "; outPos = " + outPos + "\n"); + error(inString, outString, "ASCII input eaten"); + } + } +} + +function run_test() { + gConverter = new ScriptableUnicodeConverter(); + gConverter.charset = charset; + + var byte1, byte2, byte3, byte4; + + // 2-byte + for (byte1 = 1; byte1 < 0x100; ++byte1) { + for (byte2 = 1; byte2 < 0x100; ++byte2) { + test(String.fromCharCode(byte1, byte2) + " foo"); + } + } + // 4-byte (limited) + for (byte1 = 0x80; byte1 < 0x90; ++byte1) { + for (byte2 = 0x20; byte2 < 0x40; ++byte2) { + for (byte3 = 0x80; byte3 < 0x90; ++byte3) { + for (byte4 = 0x20; byte4 < 0x40; ++byte4) { + test(String.fromCharCode(byte1, byte2, byte3, byte4) + " foo"); + } + } + } + } +} diff --git a/intl/uconv/tests/unit/test_charset_conversion.js b/intl/uconv/tests/unit/test_charset_conversion.js new file mode 100644 index 0000000000..577a801081 --- /dev/null +++ b/intl/uconv/tests/unit/test_charset_conversion.js @@ -0,0 +1,373 @@ +const NS_ERROR_ILLEGAL_VALUE = Cr.NS_ERROR_ILLEGAL_VALUE; + +var BIS, BOS, _Pipe, COS, FIS, _SS, CIS; + +var dataDir; + +function run_test() { + BIS = Components.Constructor( + "@mozilla.org/binaryinputstream;1", + "nsIBinaryInputStream", + "setInputStream" + ); + BOS = Components.Constructor( + "@mozilla.org/binaryoutputstream;1", + "nsIBinaryOutputStream", + "setOutputStream" + ); + _Pipe = Components.Constructor("@mozilla.org/pipe;1", "nsIPipe", "init"); + COS = Components.Constructor( + "@mozilla.org/intl/converter-output-stream;1", + "nsIConverterOutputStream", + "init" + ); + FIS = Components.Constructor( + "@mozilla.org/network/file-input-stream;1", + "nsIFileInputStream", + "init" + ); + _SS = Components.Constructor( + "@mozilla.org/storagestream;1", + "nsIStorageStream", + "init" + ); + CIS = Components.Constructor( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" + ); + + dataDir = do_get_file("data/"); + + test_utf8_1(); + test_cross_conversion(); +} + +const UNICODE_STRINGS = [ + "\u00BD + \u00BE == \u00BD\u00B2 + \u00BC + \u00BE", + + "AZaz09 \u007F " + // U+000000 to U+00007F + "\u0080 \u0398 \u03BB \u0725 " + // U+000080 to U+0007FF + "\u0964 \u0F5F \u20AC \uFFFB", // U+000800 to U+00FFFF + + // there would be strings containing non-BMP code points here, but + // unfortunately JS strings are UCS-2 (and worse yet are treated as + // 16-bit values by the spec), so we have to do gymnastics to work + // with non-BMP -- manual surrogate decoding doesn't work because + // String.prototype.charCodeAt() ignores surrogate pairs and only + // returns 16-bit values +]; + +// test conversion equality -- keys are names of files containing equivalent +// Unicode data, values are the encoding of the file in the format expected by +// nsIConverter(In|Out)putStream.init +const UNICODE_FILES = { + "unicode-conversion.utf8.txt": "UTF-8", + "unicode-conversion.utf16.txt": "UTF-16", + "unicode-conversion.utf16le.txt": "UTF-16LE", + "unicode-conversion.utf16be.txt": "UTF-16BE", +}; + +function test_utf8_1() { + for (var i = 0; i < UNICODE_STRINGS.length; i++) { + var pipe = Pipe(); + var conv = new COS(pipe.outputStream, "UTF-8"); + Assert.ok(conv.writeString(UNICODE_STRINGS[i])); + conv.close(); + + if ( + !equalStreams( + new UTF8(pipe.inputStream), + stringToCodePoints(UNICODE_STRINGS[i]) + ) + ) { + do_throw("UNICODE_STRINGS[" + i + "] not handled correctly"); + } + } +} + +function test_cross_conversion() { + for (var fn1 in UNICODE_FILES) { + var fin = getBinaryInputStream(fn1); + var ss = StorageStream(); + + var bos = new BOS(ss.getOutputStream(0)); + var av; + while ((av = fin.available()) > 0) { + var data = fin.readByteArray(av); + bos.writeByteArray(data); + } + fin.close(); + bos.close(); + + for (var fn2 in UNICODE_FILES) { + var fin2 = getUnicharInputStream(fn2, UNICODE_FILES[fn2]); + var unichar = new CIS( + ss.newInputStream(0), + UNICODE_FILES[fn1], + 8192, + 0x0 + ); + + if (!equalUnicharStreams(unichar, fin2)) { + do_throw( + "unequal streams: " + UNICODE_FILES[fn1] + ", " + UNICODE_FILES[fn2] + ); + } + } + } +} + +// utility functions + +function StorageStream() { + return new _SS(8192, Math.pow(2, 32) - 1, null); +} + +function getUnicharInputStream(filename, encoding) { + var file = dataDir.clone(); + file.append(filename); + + const PR_RDONLY = 0x1; + var fis = new FIS( + file, + PR_RDONLY, + "0644", + Ci.nsIFileInputStream.CLOSE_ON_EOF + ); + return new CIS(fis, encoding, 8192, 0x0); +} + +function getBinaryInputStream(filename, encoding) { + var file = dataDir.clone(); + file.append(filename); + + const PR_RDONLY = 0x1; + var fis = new FIS( + file, + PR_RDONLY, + "0644", + Ci.nsIFileInputStream.CLOSE_ON_EOF + ); + return new BIS(fis); +} + +function equalStreams(stream, codePoints) { + var currIndex = 0; + while (true) { + var unit = stream.readUnit(); + if (unit < 0) { + return currIndex == codePoints.length; + } + if (unit !== codePoints[currIndex++]) { + return false; + } + } + // eslint-disable-next-line no-unreachable + do_throw("not reached"); + return false; +} + +function equalUnicharStreams(s1, s2) { + var r1, r2; + var str1 = {}, + str2 = {}; + while (true) { + r1 = s1.readString(1024, str1); + r2 = s2.readString(1024, str2); + + if (r1 != r2 || str1.value != str2.value) { + print("r1: " + r1 + ", r2: " + r2); + print(str1.value.length); + print(str2.value.length); + return false; + } + if (r1 == 0 && r2 == 0) { + return true; + } + } + + // not reached + // eslint-disable-next-line no-unreachable + return false; +} + +function stringToCodePoints(str) { + return str.split("").map(function (v) { + return v.charCodeAt(0); + }); +} + +function lowbits(n) { + return Math.pow(2, n) - 1; +} + +function Pipe() { + return new _Pipe(false, false, 1024, 10, null); +} + +// complex charset readers + +/** + * Wraps a UTF-8 stream to allow access to the Unicode code points in it. + * + * @param stream + * the stream to wrap + */ +function UTF8(stream) { + this._stream = new BIS(stream); +} +UTF8.prototype = { + // returns numeric code point at front of stream encoded in UTF-8, -1 if at + // end of stream, or throws if valid (and properly encoded!) code point not + // found + readUnit() { + var str = this._stream; + + var c, c2, c3, c4, rv; + + // if at end of stream, must distinguish failure to read any bytes + // (correct behavior) from failure to read some byte after the first + // in the character + try { + c = str.read8(); + } catch (e) { + return -1; + } + + if (c < 0x80) { + return c; + } + + if (c < 0xc0) { + // c < 11000000 + // byte doesn't have enough leading ones (must be at least two) + throw NS_ERROR_ILLEGAL_VALUE; + } + + c2 = str.read8(); + if (c2 >= 0xc0 || c2 < 0x80) { + throw NS_ERROR_ILLEGAL_VALUE; + } // not 10xxxxxx + + if (c < 0xe0) { + // c < 11100000 + // two-byte between U+000080 and U+0007FF + rv = ((lowbits(5) & c) << 6) + (lowbits(6) & c2); + // no upper bounds-check needed, by previous lines + if (rv >= 0x80) { + return rv; + } + throw NS_ERROR_ILLEGAL_VALUE; + } + + c3 = str.read8(); + if (c3 >= 0xc0 || c3 < 0x80) { + throw NS_ERROR_ILLEGAL_VALUE; + } // not 10xxxxxx + + if (c < 0xf0) { + // c < 11110000 + // three-byte between U+000800 and U+00FFFF + rv = + ((lowbits(4) & c) << 12) + ((lowbits(6) & c2) << 6) + (lowbits(6) & c3); + // no upper bounds-check needed, by previous lines + if (rv >= 0xe000 || (rv >= 0x800 && rv <= 0xd7ff)) { + return rv; + } + throw NS_ERROR_ILLEGAL_VALUE; + } + + c4 = str.read8(); + if (c4 >= 0xc0 || c4 < 0x80) { + throw NS_ERROR_ILLEGAL_VALUE; + } // not 10xxxxxx + + if (c < 0xf8) { + // c < 11111000 + // four-byte between U+010000 and U+10FFFF + rv = + ((lowbits(3) & c) << 18) + + ((lowbits(6) & c2) << 12) + + ((lowbits(6) & c3) << 6) + + (lowbits(6) & c4); + // need an upper bounds-check since 0x10FFFF isn't (2**n - 1) + if (rv >= 0x10000 && rv <= 0x10ffff) { + return rv; + } + throw NS_ERROR_ILLEGAL_VALUE; + } + + // 11111000 or greater -- no UTF-8 mapping + throw NS_ERROR_ILLEGAL_VALUE; + }, +}; + +/** + * Wraps a UTF-16 stream to allow access to the Unicode code points in it. + * + * @param stream + * the stream to wrap + * @param bigEndian + * true for UTF-16BE, false for UTF-16LE, not present at all for UTF-16 with + * a byte-order mark + */ +function UTF16(stream, bigEndian) { + this._stream = new BIS(stream); + if (arguments.length > 1) { + this._bigEndian = bigEndian; + } else { + var bom = this._stream.read16(); + if (bom == 0xfeff) { + this._bigEndian = true; + } else if (bom == 0xfffe) { + this._bigEndian = false; + } else { + do_throw("missing BOM: " + bom.toString(16).toUpperCase()); + } + } +} +UTF16.prototype = { + // returns numeric code point at front of stream encoded in UTF-16, + // -1 if at end of stream, or throws if UTF-16 code point not found + readUnit() { + var str = this._stream; + + // if at end of stream, must distinguish failure to read any bytes + // (correct behavior) from failure to read some byte after the first + // in the character + try { + var b1 = str.read8(); + } catch (e) { + return -1; + } + + var b2 = str.read8(); + + var w1 = this._bigEndian ? (b1 << 8) + b2 : (b2 << 8) + b1; + + if (w1 > 0xdbff && w1 < 0xe000) { + // second surrogate, but expecting none or first + throw NS_ERROR_ILLEGAL_VALUE; + } + + if (w1 > 0xd7ff && w1 < 0xdc00) { + // non-BMP, use surrogate pair + b1 = str.read8(); + b2 = str.read8(); + var w2 = this._bigEndian ? (b1 << 8) + b2 : (b2 << 8) + b1; + if (w2 < 0xdc00 || w2 > 0xdfff) { + throw NS_ERROR_ILLEGAL_VALUE; + } + + var rv = 0x100000 + ((lowbits(10) & w2) << 10) + (lowbits(10) & w1); + if (rv <= 0x10ffff) { + return rv; + } + throw NS_ERROR_ILLEGAL_VALUE; + } + + // non-surrogate + return w1; + }, +}; diff --git a/intl/uconv/tests/unit/test_decode_8859-1.js b/intl/uconv/tests/unit/test_decode_8859-1.js new file mode 100644 index 0000000000..d820b35ca8 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-1.js @@ -0,0 +1,26 @@ +// Tests conversion from ISO-8859-1 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const aliases = [ + "ISO-8859-1", + "iso-8859-1", + "latin1", + "iso_8859-1", + "iso8859-1", + "iso-ir-100", + "l1", + "ibm819", + "cp819", + "csisolatin1", + "iso88591", + "iso_8859-1:1987", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-10.js b/intl/uconv/tests/unit/test_decode_8859-10.js new file mode 100644 index 0000000000..47e934817e --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-10.js @@ -0,0 +1,22 @@ +// Tests conversion from ISO-8859-10 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u0112\u0122\u012a\u0128\u0136\u00a7\u013b\u0110\u0160\u0166\u017d\u00ad\u016a\u014a\u00b0\u0105\u0113\u0123\u012b\u0129\u0137\u00b7\u013c\u0111\u0161\u0167\u017e\u2015\u016b\u014b\u0100\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u012e\u010c\u00c9\u0118\u00cb\u0116\u00cd\u00ce\u00cf\u00d0\u0145\u014c\u00d3\u00d4\u00d5\u00d6\u0168\u00d8\u0172\u00da\u00db\u00dc\u00dd\u00de\u00df\u0101\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u012f\u010d\u00e9\u0119\u00eb\u0117\u00ed\u00ee\u00ef\u00f0\u0146\u014d\u00f3\u00f4\u00f5\u00f6\u0169\u00f8\u0173\u00fa\u00fb\u00fc\u00fd\u00fe\u0138"; + +const aliases = [ + "ISO-8859-10", + "iso-8859-10", + "iso8859-10", + "latin6", + "iso-ir-157", + "l6", + "csisolatin6", + "iso885910", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-11.js b/intl/uconv/tests/unit/test_decode_8859-11.js new file mode 100644 index 0000000000..b647ec503c --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-11.js @@ -0,0 +1,13 @@ +// Tests conversion from ISO-8859-11 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0e01\u0e02\u0e03\u0e04\u0e05\u0e06\u0e07\u0e08\u0e09\u0e0a\u0e0b\u0e0c\u0e0d\u0e0e\u0e0f\u0e10\u0e11\u0e12\u0e13\u0e14\u0e15\u0e16\u0e17\u0e18\u0e19\u0e1a\u0e1b\u0e1c\u0e1d\u0e1e\u0e1f\u0e20\u0e21\u0e22\u0e23\u0e24\u0e25\u0e26\u0e27\u0e28\u0e29\u0e2a\u0e2b\u0e2c\u0e2d\u0e2e\u0e2f\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37\u0e38\u0e39\u0e3a\u0e3f\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e46\u0e47\u0e48\u0e49\u0e4a\u0e4b\u0e4c\u0e4d\u0e4e\u0e4f\u0e50\u0e51\u0e52\u0e53\u0e54\u0e55\u0e56\u0e57\u0e58\u0e59\u0e5a\u0e5b"; + +const aliases = ["ISO-8859-11", "iso-8859-11", "iso8859-11", "iso885911"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-13.js b/intl/uconv/tests/unit/test_decode_8859-13.js new file mode 100644 index 0000000000..91443e6bee --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-13.js @@ -0,0 +1,13 @@ +// Tests conversion from ISO-8859-13 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u201d\u00a2\u00a3\u00a4\u201e\u00a6\u00a7\u00d8\u00a9\u0156\u00ab\u00ac\u00ad\u00ae\u00c6\u00b0\u00b1\u00b2\u00b3\u201c\u00b5\u00b6\u00b7\u00f8\u00b9\u0157\u00bb\u00bc\u00bd\u00be\u00e6\u0104\u012e\u0100\u0106\u00c4\u00c5\u0118\u0112\u010c\u00c9\u0179\u0116\u0122\u0136\u012a\u013b\u0160\u0143\u0145\u00d3\u014c\u00d5\u00d6\u00d7\u0172\u0141\u015a\u016a\u00dc\u017b\u017d\u00df\u0105\u012f\u0101\u0107\u00e4\u00e5\u0119\u0113\u010d\u00e9\u017a\u0117\u0123\u0137\u012b\u013c\u0161\u0144\u0146\u00f3\u014d\u00f5\u00f6\u00f7\u0173\u0142\u015b\u016b\u00fc\u017c\u017e\u2019"; + +const aliases = ["ISO-8859-13", "iso-8859-13", "iso8859-13", "iso885913"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-14.js b/intl/uconv/tests/unit/test_decode_8859-14.js new file mode 100644 index 0000000000..d1fdcb204c --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-14.js @@ -0,0 +1,13 @@ +// Tests conversion from ISO-8859-14 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u1e02\u1e03\u00a3\u010a\u010b\u1e0a\u00a7\u1e80\u00a9\u1e82\u1e0b\u1ef2\u00ad\u00ae\u0178\u1e1e\u1e1f\u0120\u0121\u1e40\u1e41\u00b6\u1e56\u1e81\u1e57\u1e83\u1e60\u1ef3\u1e84\u1e85\u1e61\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u0174\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u1e6a\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u0176\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u0175\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u1e6b\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u0177\u00ff"; + +const aliases = ["ISO-8859-14", "iso-8859-14", "iso8859-14", "iso885914"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-15.js b/intl/uconv/tests/unit/test_decode_8859-15.js new file mode 100644 index 0000000000..7344fb55a8 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-15.js @@ -0,0 +1,21 @@ +// Tests conversion from ISO-8859-15 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u20ac\u00a5\u0160\u00a7\u0161\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u017d\u00b5\u00b6\u00b7\u017e\u00b9\u00ba\u00bb\u0152\u0153\u0178\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const aliases = [ + "ISO-8859-15", + "iso-8859-15", + "iso8859-15", + "iso_8859-15", + "iso885915", + "csisolatin9", + "l9", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-2.js b/intl/uconv/tests/unit/test_decode_8859-2.js new file mode 100644 index 0000000000..0e3c15bdee --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-2.js @@ -0,0 +1,24 @@ +// Tests conversion from ISO-8859-2 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u02d8\u0141\u00a4\u013d\u015a\u00a7\u00a8\u0160\u015e\u0164\u0179\u00ad\u017d\u017b\u00b0\u0105\u02db\u0142\u00b4\u013e\u015b\u02c7\u00b8\u0161\u015f\u0165\u017a\u02dd\u017e\u017c\u0154\u00c1\u00c2\u0102\u00c4\u0139\u0106\u00c7\u010c\u00c9\u0118\u00cb\u011a\u00cd\u00ce\u010e\u0110\u0143\u0147\u00d3\u00d4\u0150\u00d6\u00d7\u0158\u016e\u00da\u0170\u00dc\u00dd\u0162\u00df\u0155\u00e1\u00e2\u0103\u00e4\u013a\u0107\u00e7\u010d\u00e9\u0119\u00eb\u011b\u00ed\u00ee\u010f\u0111\u0144\u0148\u00f3\u00f4\u0151\u00f6\u00f7\u0159\u016f\u00fa\u0171\u00fc\u00fd\u0163\u02d9"; + +const aliases = [ + "ISO-8859-2", + "iso-8859-2", + "latin2", + "iso_8859-2", + "iso8859-2", + "iso-ir-101", + "l2", + "csisolatin2", + "iso88592", + "iso_8859-2:1987", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-3.js b/intl/uconv/tests/unit/test_decode_8859-3.js new file mode 100644 index 0000000000..011f82de87 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-3.js @@ -0,0 +1,24 @@ +// Tests conversion from ISO-8859-3 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbf\xc0\xc1\xc2\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0126\u02d8\u00a3\u00a4\u0124\u00a7\u00a8\u0130\u015e\u011e\u0134\u00ad\u017b\u00b0\u0127\u00b2\u00b3\u00b4\u00b5\u0125\u00b7\u00b8\u0131\u015f\u011f\u0135\u00bd\u017c\u00c0\u00c1\u00c2\u00c4\u010a\u0108\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d1\u00d2\u00d3\u00d4\u0120\u00d6\u00d7\u011c\u00d9\u00da\u00db\u00dc\u016c\u015c\u00df\u00e0\u00e1\u00e2\u00e4\u010b\u0109\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u0121\u00f6\u00f7\u011d\u00f9\u00fa\u00fb\u00fc\u016d\u015d\u02d9"; + +const aliases = [ + "ISO-8859-3", + "iso-8859-3", + "latin3", + "iso_8859-3", + "iso8859-3", + "iso-ir-109", + "l3", + "csisolatin3", + "iso88593", + "iso_8859-3:1988", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-4.js b/intl/uconv/tests/unit/test_decode_8859-4.js new file mode 100644 index 0000000000..6a8b89c2ef --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-4.js @@ -0,0 +1,24 @@ +// Tests conversion from ISO-8859-4 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u0138\u0156\u00a4\u0128\u013b\u00a7\u00a8\u0160\u0112\u0122\u0166\u00ad\u017d\u00af\u00b0\u0105\u02db\u0157\u00b4\u0129\u013c\u02c7\u00b8\u0161\u0113\u0123\u0167\u014a\u017e\u014b\u0100\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u012e\u010c\u00c9\u0118\u00cb\u0116\u00cd\u00ce\u012a\u0110\u0145\u014c\u0136\u00d4\u00d5\u00d6\u00d7\u00d8\u0172\u00da\u00db\u00dc\u0168\u016a\u00df\u0101\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u012f\u010d\u00e9\u0119\u00eb\u0117\u00ed\u00ee\u012b\u0111\u0146\u014d\u0137\u00f4\u00f5\u00f6\u00f7\u00f8\u0173\u00fa\u00fb\u00fc\u0169\u016b\u02d9"; + +const aliases = [ + "ISO-8859-4", + "iso-8859-4", + "latin4", + "iso_8859-4", + "iso8859-4", + "iso-ir-110", + "l4", + "csisolatin4", + "iso88594", + "iso_8859-4:1988", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-5.js b/intl/uconv/tests/unit/test_decode_8859-5.js new file mode 100644 index 0000000000..220a12ab3a --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-5.js @@ -0,0 +1,22 @@ +// Tests conversion from ISO-8859-5 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0401\u0402\u0403\u0404\u0405\u0406\u0407\u0408\u0409\u040a\u040b\u040c\u00ad\u040e\u040f\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u2116\u0451\u0452\u0453\u0454\u0455\u0456\u0457\u0458\u0459\u045a\u045b\u045c\u00a7\u045e\u045f"; + +const aliases = [ + "ISO-8859-5", + "iso-8859-5", + "iso_8859-5", + "iso8859-5", + "iso-ir-144", + "csisolatincyrillic", + "iso88595", + "iso_8859-5:1988", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-6.js b/intl/uconv/tests/unit/test_decode_8859-6.js new file mode 100644 index 0000000000..9c94ef8673 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-6.js @@ -0,0 +1,25 @@ +// Tests conversion from ISO-8859-6 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa4\xac\xad\xbb\xbf\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a4\u060c\u00ad\u061b\u061f\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u064b\u064c\u064d\u064e\u064f\u0650\u0651\u0652"; + +const aliases = [ + "ISO-8859-6", + "iso-8859-6", + "iso_8859-6", + "iso8859-6", + "arabic", + "iso-ir-127", + "ecma-114", + "asmo-708", + "csisolatinarabic", + "iso88596", + "iso_8859-6:1987", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-7.js b/intl/uconv/tests/unit/test_decode_8859-7.js new file mode 100644 index 0000000000..9d74342345 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-7.js @@ -0,0 +1,27 @@ +// Tests conversion from ISO-8859-7 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u2018\u2019\u00a3\u20ac\u20af\u00a6\u00a7\u00a8\u00a9\u037a\u00ab\u00ac\u00ad\u2015\u00b0\u00b1\u00b2\u00b3\u0384\u0385\u0386\u00b7\u0388\u0389\u038a\u00bb\u038c\u00bd\u038e\u038f\u0390\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039a\u039b\u039c\u039d\u039e\u039f\u03a0\u03a1\u03a3\u03a4\u03a5\u03a6\u03a7\u03a8\u03a9\u03aa\u03ab\u03ac\u03ad\u03ae\u03af\u03b0\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c2\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03ca\u03cb\u03cc\u03cd\u03ce"; + +const aliases = [ + "ISO-8859-7", + "iso-8859-7", + "greek", + "greek8", + "sun_eu_greek", + "iso_8859-7", + "iso8859-7", + "iso-ir-126", + "elot_928", + "ecma-118", + "csisolatingreek", + "iso88597", + "iso_8859-7:1987", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-8.js b/intl/uconv/tests/unit/test_decode_8859-8.js new file mode 100644 index 0000000000..c7b758bf03 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-8.js @@ -0,0 +1,24 @@ +// Tests conversion from ISO-8859-8 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfd\xfe"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00d7\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00f7\u00bb\u00bc\u00bd\u00be\u2017\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05da\u05db\u05dc\u05dd\u05de\u05df\u05e0\u05e1\u05e2\u05e3\u05e4\u05e5\u05e6\u05e7\u05e8\u05e9\u05ea\u200e\u200f"; + +const aliases = [ + "ISO-8859-8", + "iso-8859-8", + "hebrew", + "visual", + "iso_8859-8", + "iso8859-8", + "iso-ir-138", + "csisolatinhebrew", + "iso88598", + "iso_8859-8:1988", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_8859-9.js b/intl/uconv/tests/unit/test_decode_8859-9.js new file mode 100644 index 0000000000..1582e2093f --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_8859-9.js @@ -0,0 +1,24 @@ +// Tests conversion from ISO-8859-9 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u011e\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u0130\u015e\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u011f\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u0131\u015f\u00ff"; + +const aliases = [ + "ISO-8859-9", + "iso-8859-9", + "latin5", + "iso_8859-9", + "iso8859-9", + "iso-ir-148", + "l5", + "csisolatin5", + "iso88599", + "iso_8859-9:1989", +]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1250.js b/intl/uconv/tests/unit/test_decode_CP1250.js new file mode 100644 index 0000000000..d044c67801 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1250.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1250 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0083\u201e\u2026\u2020\u2021\u0088\u2030\u0160\u2039\u015a\u0164\u017d\u0179\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u0161\u203a\u015b\u0165\u017e\u017a\u00a0\u02c7\u02d8\u0141\u00a4\u0104\u00a6\u00a7\u00a8\u00a9\u015e\u00ab\u00ac\u00ad\u00ae\u017b\u00b0\u00b1\u02db\u0142\u00b4\u00b5\u00b6\u00b7\u00b8\u0105\u015f\u00bb\u013d\u02dd\u013e\u017c\u0154\u00c1\u00c2\u0102\u00c4\u0139\u0106\u00c7\u010c\u00c9\u0118\u00cb\u011a\u00cd\u00ce\u010e\u0110\u0143\u0147\u00d3\u00d4\u0150\u00d6\u00d7\u0158\u016e\u00da\u0170\u00dc\u00dd\u0162\u00df\u0155\u00e1\u00e2\u0103\u00e4\u013a\u0107\u00e7\u010d\u00e9\u0119\u00eb\u011b\u00ed\u00ee\u010f\u0111\u0144\u0148\u00f3\u00f4\u0151\u00f6\u00f7\u0159\u016f\u00fa\u0171\u00fc\u00fd\u0163\u02d9"; + +const aliases = ["windows-1250", "x-cp1250", "cp1250"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1251.js b/intl/uconv/tests/unit/test_decode_CP1251.js new file mode 100644 index 0000000000..01153e8650 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1251.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1251 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0402\u0403\u201a\u0453\u201e\u2026\u2020\u2021\u20ac\u2030\u0409\u2039\u040a\u040c\u040b\u040f\u0452\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u0459\u203a\u045a\u045c\u045b\u045f\u00a0\u040e\u045e\u0408\u00a4\u0490\u00a6\u00a7\u0401\u00a9\u0404\u00ab\u00ac\u00ad\u00ae\u0407\u00b0\u00b1\u0406\u0456\u0491\u00b5\u00b6\u00b7\u0451\u2116\u0454\u00bb\u0458\u0405\u0455\u0457\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f"; + +const aliases = ["windows-1251", "x-cp1251", "cp1251"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1252.js b/intl/uconv/tests/unit/test_decode_CP1252.js new file mode 100644 index 0000000000..d41d7d72a3 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1252.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1252 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u008d\u017d\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u009d\u017e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const aliases = ["windows-1252", "x-cp1252", "cp1252"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1253.js b/intl/uconv/tests/unit/test_decode_CP1253.js new file mode 100644 index 0000000000..880e2dae74 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1253.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1253 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u0088\u2030\u008a\u2039\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u009a\u203a\u009c\u009d\u009e\u009f\u00a0\u0385\u0386\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\ufffd\u00ab\u00ac\u00ad\u00ae\u2015\u00b0\u00b1\u00b2\u00b3\u0384\u00b5\u00b6\u00b7\u0388\u0389\u038a\u00bb\u038c\u00bd\u038e\u038f\u0390\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039a\u039b\u039c\u039d\u039e\u039f\u03a0\u03a1\ufffd\u03a3\u03a4\u03a5\u03a6\u03a7\u03a8\u03a9\u03aa\u03ab\u03ac\u03ad\u03ae\u03af\u03b0\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c2\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03ca\u03cb\u03cc\u03cd\u03ce\ufffd"; + +const aliases = ["windows-1253", "x-cp1253", "cp1253"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1254.js b/intl/uconv/tests/unit/test_decode_CP1254.js new file mode 100644 index 0000000000..f4af7e2088 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1254.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1254 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u009d\u009e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u011e\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u0130\u015e\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u011f\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u0131\u015f\u00ff"; + +const aliases = ["windows-1254", "x-cp1254", "cp1254"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1255.js b/intl/uconv/tests/unit/test_decode_CP1255.js new file mode 100644 index 0000000000..57e1b54636 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1255.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1255 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u008a\u2039\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u009a\u203a\u009c\u009d\u009e\u009f\u00a0\u00a1\u00a2\u00a3\u20aa\u00a5\u00a6\u00a7\u00a8\u00a9\u00d7\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00f7\u00bb\u00bc\u00bd\u00be\u00bf\u05b0\u05b1\u05b2\u05b3\u05b4\u05b5\u05b6\u05b7\u05b8\u05b9\u05ba\u05bb\u05bc\u05bd\u05be\u05bf\u05c0\u05c1\u05c2\u05c3\u05f0\u05f1\u05f2\u05f3\u05f4\ufffd\ufffd\ufffd\ufffd\ufffd\ufffd\ufffd\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05da\u05db\u05dc\u05dd\u05de\u05df\u05e0\u05e1\u05e2\u05e3\u05e4\u05e5\u05e6\u05e7\u05e8\u05e9\u05ea\ufffd\ufffd\u200e\u200f\ufffd"; + +const aliases = ["windows-1255", "x-cp1255", "cp1255"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1256.js b/intl/uconv/tests/unit/test_decode_CP1256.js new file mode 100644 index 0000000000..b91e448a46 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1256.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1256 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u067e\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0679\u2039\u0152\u0686\u0698\u0688\u06af\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u06a9\u2122\u0691\u203a\u0153\u200c\u200d\u06ba\u00a0\u060c\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u06be\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u061b\u00bb\u00bc\u00bd\u00be\u061f\u06c1\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u00d7\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u00e0\u0644\u00e2\u0645\u0646\u0647\u0648\u00e7\u00e8\u00e9\u00ea\u00eb\u0649\u064a\u00ee\u00ef\u064b\u064c\u064d\u064e\u00f4\u064f\u0650\u00f7\u0651\u00f9\u0652\u00fb\u00fc\u200e\u200f\u06d2"; + +const aliases = ["windows-1256", "x-cp1256", "cp1256"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1257.js b/intl/uconv/tests/unit/test_decode_CP1257.js new file mode 100644 index 0000000000..a61bf2e870 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1257.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1257 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0083\u201e\u2026\u2020\u2021\u0088\u2030\u008a\u2039\u008c\u00a8\u02c7\u00b8\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u009a\u203a\u009c\u00af\u02db\u009f\u00a0\ufffd\u00a2\u00a3\u00a4\ufffd\u00a6\u00a7\u00d8\u00a9\u0156\u00ab\u00ac\u00ad\u00ae\u00c6\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00f8\u00b9\u0157\u00bb\u00bc\u00bd\u00be\u00e6\u0104\u012e\u0100\u0106\u00c4\u00c5\u0118\u0112\u010c\u00c9\u0179\u0116\u0122\u0136\u012a\u013b\u0160\u0143\u0145\u00d3\u014c\u00d5\u00d6\u00d7\u0172\u0141\u015a\u016a\u00dc\u017b\u017d\u00df\u0105\u012f\u0101\u0107\u00e4\u00e5\u0119\u0113\u010d\u00e9\u017a\u0117\u0123\u0137\u012b\u013c\u0161\u0144\u0146\u00f3\u014d\u00f5\u00f6\u00f7\u0173\u0142\u015b\u016b\u00fc\u017c\u017e\u02d9"; + +const aliases = ["windows-1257", "x-cp1257", "cp1257"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP1258.js b/intl/uconv/tests/unit/test_decode_CP1258.js new file mode 100644 index 0000000000..422e9a7985 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP1258.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-1258 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u008a\u2039\u0152\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u009a\u203a\u0153\u009d\u009e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u0102\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u0300\u00cd\u00ce\u00cf\u0110\u00d1\u0309\u00d3\u00d4\u01a0\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u01af\u0303\u00df\u00e0\u00e1\u00e2\u0103\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u0301\u00ed\u00ee\u00ef\u0111\u00f1\u0323\u00f3\u00f4\u01a1\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u01b0\u20ab\u00ff"; + +const aliases = ["windows-1258", "x-cp1258", "cp1258"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_CP874.js b/intl/uconv/tests/unit/test_decode_CP874.js new file mode 100644 index 0000000000..7f05e7669c --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_CP874.js @@ -0,0 +1,13 @@ +// Tests conversion from windows-874 to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u0082\u0083\u0084\u2026\u0086\u0087\u0088\u0089\u008a\u008b\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u0099\u009a\u009b\u009c\u009d\u009e\u009f\u00a0\u0e01\u0e02\u0e03\u0e04\u0e05\u0e06\u0e07\u0e08\u0e09\u0e0a\u0e0b\u0e0c\u0e0d\u0e0e\u0e0f\u0e10\u0e11\u0e12\u0e13\u0e14\u0e15\u0e16\u0e17\u0e18\u0e19\u0e1a\u0e1b\u0e1c\u0e1d\u0e1e\u0e1f\u0e20\u0e21\u0e22\u0e23\u0e24\u0e25\u0e26\u0e27\u0e28\u0e29\u0e2a\u0e2b\u0e2c\u0e2d\u0e2e\u0e2f\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37\u0e38\u0e39\u0e3a\ufffd\ufffd\ufffd\ufffd\u0e3f\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e46\u0e47\u0e48\u0e49\u0e4a\u0e4b\u0e4c\u0e4d\u0e4e\u0e4f\u0e50\u0e51\u0e52\u0e53\u0e54\u0e55\u0e56\u0e57\u0e58\u0e59\u0e5a\u0e5b\ufffd\ufffd\ufffd\ufffd"; + +const aliases = ["windows-874", "dos-874"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_gb18030.js b/intl/uconv/tests/unit/test_decode_gb18030.js new file mode 100644 index 0000000000..ca5796bbaa --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_gb18030.js @@ -0,0 +1,16 @@ +// Tests conversion from gb18030 to Unicode +// This is a sniff test which doesn't cover the full gb18030 range: the test string +// includes only the ASCII range and the first 63 double byte characters +// and border values of 4 byte characters + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x81@\x81A\x81B\x81C\x81D\x81E\x81F\x81G\x81H\x81I\x81J\x81K\x81L\x81M\x81N\x81O\x81P\x81Q\x81R\x81S\x81T\x81U\x81V\x81W\x81X\x81Y\x81Z\x81[\x81\\\x81]\x81^\x81_\x81`\x81a\x81b\x81c\x81d\x81e\x81f\x81g\x81h\x81i\x81j\x81k\x81l\x81m\x81n\x81o\x81p\x81q\x81r\x81s\x81t\x81u\x81v\x81w\x81x\x81y\x81z\x81{\x81|\x81}\x81~\x810\x810\x841\xa46\x841\xa47\x849\xfe9\x850\x810\x859\xfe9\x860\x810\x8f9\xfe9\x900\x810\xe32\x9a5\xe32\x9a6\xe39\xfe9\xe40\x810\xfc9\xfe9\xfd0\x810\xfe9\xfe9\xa8\xa0\xa8\xbc\xa8\xbf\xa8\xc1\x815\xf46\x815\xf47\x815\xf48"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u4E02\u4E04\u4E05\u4E06\u4E0F\u4E12\u4E17\u4E1F\u4E20\u4E21\u4E23\u4E26\u4E29\u4E2E\u4E2F\u4E31\u4E33\u4E35\u4E37\u4E3C\u4E40\u4E41\u4E42\u4E44\u4E46\u4E4A\u4E51\u4E55\u4E57\u4E5A\u4E5B\u4E62\u4E63\u4E64\u4E65\u4E67\u4E68\u4E6A\u4E6B\u4E6C\u4E6D\u4E6E\u4E6F\u4E72\u4E74\u4E75\u4E76\u4E77\u4E78\u4E79\u4E7A\u4E7B\u4E7C\u4E7D\u4E7F\u4E80\u4E81\u4E82\u4E83\u4E84\u4E85\u4E87\u4E8A\x80\uFFFC\uFFFD\uFFFD\uFFFD\uFFFD\uFFFD\uFFFD\uD800\uDC00\uDBFF\uDFFF\uFFFD\uFFFD\uFFFD\uFFFD\uFFFD\uFFFD\uE7C6\u1E3F\u01F9\uE7C9\u1E3E\uE7C7\u1E40"; + +const aliases = ["gb18030"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_gbk.js b/intl/uconv/tests/unit/test_decode_gbk.js new file mode 100644 index 0000000000..6e4414722d --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_gbk.js @@ -0,0 +1,15 @@ +// Tests conversion from gbk to Unicode +// This is a sniff test which doesn't cover the full gbk range: the test string +// includes only the ASCII range and the first 63 double byte characters + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x81@\x81A\x81B\x81C\x81D\x81E\x81F\x81G\x81H\x81I\x81J\x81K\x81L\x81M\x81N\x81O\x81P\x81Q\x81R\x81S\x81T\x81U\x81V\x81W\x81X\x81Y\x81Z\x81[\x81\\\x81]\x81^\x81_\x81`\x81a\x81b\x81c\x81d\x81e\x81f\x81g\x81h\x81i\x81j\x81k\x81l\x81m\x81n\x81o\x81p\x81q\x81r\x81s\x81t\x81u\x81v\x81w\x81x\x81y\x81z\x81{\x81|\x81}\x81~"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u4E02\u4E04\u4E05\u4E06\u4E0F\u4E12\u4E17\u4E1F\u4E20\u4E21\u4E23\u4E26\u4E29\u4E2E\u4E2F\u4E31\u4E33\u4E35\u4E37\u4E3C\u4E40\u4E41\u4E42\u4E44\u4E46\u4E4A\u4E51\u4E55\u4E57\u4E5A\u4E5B\u4E62\u4E63\u4E64\u4E65\u4E67\u4E68\u4E6A\u4E6B\u4E6C\u4E6D\u4E6E\u4E6F\u4E72\u4E74\u4E75\u4E76\u4E77\u4E78\u4E79\u4E7A\u4E7B\u4E7C\u4E7D\u4E7F\u4E80\u4E81\u4E82\u4E83\u4E84\u4E85\u4E87\u4E8A"; + +const aliases = ["gbk", "x-gbk"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_macintosh.js b/intl/uconv/tests/unit/test_decode_macintosh.js new file mode 100644 index 0000000000..5504a630ec --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_macintosh.js @@ -0,0 +1,13 @@ +// Tests conversion from x-mac-roman to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00c4\u00c5\u00c7\u00c9\u00d1\u00d6\u00dc\u00e1\u00e0\u00e2\u00e4\u00e3\u00e5\u00e7\u00e9\u00e8\u00ea\u00eb\u00ed\u00ec\u00ee\u00ef\u00f1\u00f3\u00f2\u00f4\u00f6\u00f5\u00fa\u00f9\u00fb\u00fc\u2020\u00b0\u00a2\u00a3\u00a7\u2022\u00b6\u00df\u00ae\u00a9\u2122\u00b4\u00a8\u2260\u00c6\u00d8\u221e\u00b1\u2264\u2265\u00a5\u00b5\u2202\u2211\u220f\u03c0\u222b\u00aa\u00ba\u03a9\u00e6\u00f8\u00bf\u00a1\u00ac\u221a\u0192\u2248\u2206\u00ab\u00bb\u2026\u00a0\u00c0\u00c3\u00d5\u0152\u0153\u2013\u2014\u201c\u201d\u2018\u2019\u00f7\u25ca\u00ff\u0178\u2044\u20ac\u2039\u203a\ufb01\ufb02\u2021\u00b7\u201a\u201e\u2030\u00c2\u00ca\u00c1\u00cb\u00c8\u00cd\u00ce\u00cf\u00cc\u00d3\u00d4\uf8ff\u00d2\u00da\u00db\u00d9\u0131\u02c6\u02dc\u00af\u02d8\u02d9\u02da\u00b8\u02dd\u02db\u02c7"; + +const aliases = ["csMacintosh", "mac", "macintosh", "x-mac-roman"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_x_mac_cyrillic.js b/intl/uconv/tests/unit/test_decode_x_mac_cyrillic.js new file mode 100644 index 0000000000..ad783b0e96 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_x_mac_cyrillic.js @@ -0,0 +1,13 @@ +// Tests conversion from x-mac-cyrillic to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u2020\u00b0\u0490\u00a3\u00a7\u2022\u00b6\u0406\u00ae\u00a9\u2122\u0402\u0452\u2260\u0403\u0453\u221e\u00b1\u2264\u2265\u0456\u00b5\u0491\u0408\u0404\u0454\u0407\u0457\u0409\u0459\u040a\u045a\u0458\u0405\u00ac\u221a\u0192\u2248\u2206\u00ab\u00bb\u2026\u00a0\u040b\u045b\u040c\u045c\u0455\u2013\u2014\u201c\u201d\u2018\u2019\u00f7\u201e\u040e\u045e\u040f\u045f\u2116\u0401\u0451\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u20ac"; + +const aliases = ["x-mac-cyrillic"]; + +function run_test() { + testDecodeAliasesInternal(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_decode_x_mac_ukrainian.js b/intl/uconv/tests/unit/test_decode_x_mac_ukrainian.js new file mode 100644 index 0000000000..b8b3d63018 --- /dev/null +++ b/intl/uconv/tests/unit/test_decode_x_mac_ukrainian.js @@ -0,0 +1,13 @@ +// Tests conversion from x-mac-ukrainian to Unicode + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u2020\u00b0\u0490\u00a3\u00a7\u2022\u00b6\u0406\u00ae\u00a9\u2122\u0402\u0452\u2260\u0403\u0453\u221e\u00b1\u2264\u2265\u0456\u00b5\u0491\u0408\u0404\u0454\u0407\u0457\u0409\u0459\u040a\u045a\u0458\u0405\u00ac\u221a\u0192\u2248\u2206\u00ab\u00bb\u2026\u00a0\u040b\u045b\u040c\u045c\u0455\u2013\u2014\u201c\u201d\u2018\u2019\u00f7\u201e\u040e\u045e\u040f\u045f\u2116\u0401\u0451\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u20ac"; + +const aliases = ["x-mac-ukrainian"]; + +function run_test() { + testDecodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-1.js b/intl/uconv/tests/unit/test_encode_8859-1.js new file mode 100644 index 0000000000..f5a6559de1 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-1.js @@ -0,0 +1,26 @@ +// Tests conversion from Unicode to ISO-8859-1 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-1", + "iso-8859-1", + "latin1", + "iso_8859-1", + "iso8859-1", + "iso-ir-100", + "l1", + "ibm819", + "cp819", + "csisolatin1", + "iso88591", + "iso_8859-1:1987", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-10.js b/intl/uconv/tests/unit/test_encode_8859-10.js new file mode 100644 index 0000000000..2ecad6013f --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-10.js @@ -0,0 +1,22 @@ +// Tests conversion from Unicode to ISO-8859-10 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u0112\u0122\u012a\u0128\u0136\u00a7\u013b\u0110\u0160\u0166\u017d\u00ad\u016a\u014a\u00b0\u0105\u0113\u0123\u012b\u0129\u0137\u00b7\u013c\u0111\u0161\u0167\u017e\u2015\u016b\u014b\u0100\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u012e\u010c\u00c9\u0118\u00cb\u0116\u00cd\u00ce\u00cf\u00d0\u0145\u014c\u00d3\u00d4\u00d5\u00d6\u0168\u00d8\u0172\u00da\u00db\u00dc\u00dd\u00de\u00df\u0101\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u012f\u010d\u00e9\u0119\u00eb\u0117\u00ed\u00ee\u00ef\u00f0\u0146\u014d\u00f3\u00f4\u00f5\u00f6\u0169\u00f8\u0173\u00fa\u00fb\u00fc\u00fd\u00fe\u0138"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-10", + "iso-8859-10", + "iso8859-10", + "latin6", + "iso-ir-157", + "l6", + "csisolatin6", + "iso885910", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-11.js b/intl/uconv/tests/unit/test_encode_8859-11.js new file mode 100644 index 0000000000..7011c26688 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-11.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to ISO-8859-11 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0e01\u0e02\u0e03\u0e04\u0e05\u0e06\u0e07\u0e08\u0e09\u0e0a\u0e0b\u0e0c\u0e0d\u0e0e\u0e0f\u0e10\u0e11\u0e12\u0e13\u0e14\u0e15\u0e16\u0e17\u0e18\u0e19\u0e1a\u0e1b\u0e1c\u0e1d\u0e1e\u0e1f\u0e20\u0e21\u0e22\u0e23\u0e24\u0e25\u0e26\u0e27\u0e28\u0e29\u0e2a\u0e2b\u0e2c\u0e2d\u0e2e\u0e2f\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37\u0e38\u0e39\u0e3a\u0e3f\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e46\u0e47\u0e48\u0e49\u0e4a\u0e4b\u0e4c\u0e4d\u0e4e\u0e4f\u0e50\u0e51\u0e52\u0e53\u0e54\u0e55\u0e56\u0e57\u0e58\u0e59\u0e5a\u0e5b"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb"; + +const aliases = ["ISO-8859-11", "iso-8859-11", "iso8859-11", "iso885911"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-13.js b/intl/uconv/tests/unit/test_encode_8859-13.js new file mode 100644 index 0000000000..cf6ad98466 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-13.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to ISO-8859-13 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u201d\u00a2\u00a3\u00a4\u201e\u00a6\u00a7\u00d8\u00a9\u0156\u00ab\u00ac\u00ad\u00ae\u00c6\u00b0\u00b1\u00b2\u00b3\u201c\u00b5\u00b6\u00b7\u00f8\u00b9\u0157\u00bb\u00bc\u00bd\u00be\u00e6\u0104\u012e\u0100\u0106\u00c4\u00c5\u0118\u0112\u010c\u00c9\u0179\u0116\u0122\u0136\u012a\u013b\u0160\u0143\u0145\u00d3\u014c\u00d5\u00d6\u00d7\u0172\u0141\u015a\u016a\u00dc\u017b\u017d\u00df\u0105\u012f\u0101\u0107\u00e4\u00e5\u0119\u0113\u010d\u00e9\u017a\u0117\u0123\u0137\u012b\u013c\u0161\u0144\u0146\u00f3\u014d\u00f5\u00f6\u00f7\u0173\u0142\u015b\u016b\u00fc\u017c\u017e\u2019"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["ISO-8859-13", "iso-8859-13", "iso8859-13", "iso885913"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-14.js b/intl/uconv/tests/unit/test_encode_8859-14.js new file mode 100644 index 0000000000..9a0e8dc00a --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-14.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to ISO-8859-14 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u1e02\u1e03\u00a3\u010a\u010b\u1e0a\u00a7\u1e80\u00a9\u1e82\u1e0b\u1ef2\u00ad\u00ae\u0178\u1e1e\u1e1f\u0120\u0121\u1e40\u1e41\u00b6\u1e56\u1e81\u1e57\u1e83\u1e60\u1ef3\u1e84\u1e85\u1e61\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u0174\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u1e6a\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u0176\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u0175\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u1e6b\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u0177\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["ISO-8859-14", "iso-8859-14", "iso8859-14", "iso885914"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-15.js b/intl/uconv/tests/unit/test_encode_8859-15.js new file mode 100644 index 0000000000..ed5cd2ec90 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-15.js @@ -0,0 +1,21 @@ +// Tests conversion from Unicode to ISO-8859-15 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u20ac\u00a5\u0160\u00a7\u0161\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u017d\u00b5\u00b6\u00b7\u017e\u00b9\u00ba\u00bb\u0152\u0153\u0178\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-15", + "iso-8859-15", + "iso8859-15", + "iso_8859-15", + "iso885915", + "csisolatin9", + "l9", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-2.js b/intl/uconv/tests/unit/test_encode_8859-2.js new file mode 100644 index 0000000000..1b34672bcb --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-2.js @@ -0,0 +1,24 @@ +// Tests conversion from Unicode to ISO-8859-2 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u02d8\u0141\u00a4\u013d\u015a\u00a7\u00a8\u0160\u015e\u0164\u0179\u00ad\u017d\u017b\u00b0\u0105\u02db\u0142\u00b4\u013e\u015b\u02c7\u00b8\u0161\u015f\u0165\u017a\u02dd\u017e\u017c\u0154\u00c1\u00c2\u0102\u00c4\u0139\u0106\u00c7\u010c\u00c9\u0118\u00cb\u011a\u00cd\u00ce\u010e\u0110\u0143\u0147\u00d3\u00d4\u0150\u00d6\u00d7\u0158\u016e\u00da\u0170\u00dc\u00dd\u0162\u00df\u0155\u00e1\u00e2\u0103\u00e4\u013a\u0107\u00e7\u010d\u00e9\u0119\u00eb\u011b\u00ed\u00ee\u010f\u0111\u0144\u0148\u00f3\u00f4\u0151\u00f6\u00f7\u0159\u016f\u00fa\u0171\u00fc\u00fd\u0163\u02d9"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-2", + "iso-8859-2", + "latin2", + "iso_8859-2", + "iso8859-2", + "iso-ir-101", + "l2", + "csisolatin2", + "iso88592", + "iso_8859-2:1987", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-3.js b/intl/uconv/tests/unit/test_encode_8859-3.js new file mode 100644 index 0000000000..fff6243431 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-3.js @@ -0,0 +1,24 @@ +// Tests conversion from Unicode to ISO-8859-3 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0126\u02d8\u00a3\u00a4\u0124\u00a7\u00a8\u0130\u015e\u011e\u0134\u00ad\u017b\u00b0\u0127\u00b2\u00b3\u00b4\u00b5\u0125\u00b7\u00b8\u0131\u015f\u011f\u0135\u00bd\u017c\u00c0\u00c1\u00c2\u00c4\u010a\u0108\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d1\u00d2\u00d3\u00d4\u0120\u00d6\u00d7\u011c\u00d9\u00da\u00db\u00dc\u016c\u015c\u00df\u00e0\u00e1\u00e2\u00e4\u010b\u0109\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u0121\u00f6\u00f7\u011d\u00f9\u00fa\u00fb\u00fc\u016d\u015d\u02d9"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbf\xc0\xc1\xc2\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-3", + "iso-8859-3", + "latin3", + "iso_8859-3", + "iso8859-3", + "iso-ir-109", + "l3", + "csisolatin3", + "iso88593", + "iso_8859-3:1988", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-4.js b/intl/uconv/tests/unit/test_encode_8859-4.js new file mode 100644 index 0000000000..192d13fd52 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-4.js @@ -0,0 +1,24 @@ +// Tests conversion from Unicode to ISO-8859-4 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0104\u0138\u0156\u00a4\u0128\u013b\u00a7\u00a8\u0160\u0112\u0122\u0166\u00ad\u017d\u00af\u00b0\u0105\u02db\u0157\u00b4\u0129\u013c\u02c7\u00b8\u0161\u0113\u0123\u0167\u014a\u017e\u014b\u0100\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u012e\u010c\u00c9\u0118\u00cb\u0116\u00cd\u00ce\u012a\u0110\u0145\u014c\u0136\u00d4\u00d5\u00d6\u00d7\u00d8\u0172\u00da\u00db\u00dc\u0168\u016a\u00df\u0101\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u012f\u010d\u00e9\u0119\u00eb\u0117\u00ed\u00ee\u012b\u0111\u0146\u014d\u0137\u00f4\u00f5\u00f6\u00f7\u00f8\u0173\u00fa\u00fb\u00fc\u0169\u016b\u02d9"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-4", + "iso-8859-4", + "latin4", + "iso_8859-4", + "iso8859-4", + "iso-ir-110", + "l4", + "csisolatin4", + "iso88594", + "iso_8859-4:1988", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-5.js b/intl/uconv/tests/unit/test_encode_8859-5.js new file mode 100644 index 0000000000..fb2a05a693 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-5.js @@ -0,0 +1,22 @@ +// Tests conversion from Unicode to ISO-8859-5 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u0401\u0402\u0403\u0404\u0405\u0406\u0407\u0408\u0409\u040a\u040b\u040c\u00ad\u040e\u040f\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u2116\u0451\u0452\u0453\u0454\u0455\u0456\u0457\u0458\u0459\u045a\u045b\u045c\u00a7\u045e\u045f"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-5", + "iso-8859-5", + "iso_8859-5", + "iso8859-5", + "iso-ir-144", + "csisolatincyrillic", + "iso88595", + "iso_8859-5:1988", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-6.js b/intl/uconv/tests/unit/test_encode_8859-6.js new file mode 100644 index 0000000000..1768b89d82 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-6.js @@ -0,0 +1,25 @@ +// Tests conversion from Unicode to ISO-8859-6 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a4\u060c\u00ad\u061b\u061f\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u064b\u064c\u064d\u064e\u064f\u0650\u0651\u0652"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa4\xac\xad\xbb\xbf\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2"; + +const aliases = [ + "ISO-8859-6", + "iso-8859-6", + "iso_8859-6", + "iso8859-6", + "arabic", + "iso-ir-127", + "ecma-114", + "asmo-708", + "csisolatinarabic", + "iso88596", + "iso_8859-6:1987", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-7.js b/intl/uconv/tests/unit/test_encode_8859-7.js new file mode 100644 index 0000000000..3452130e74 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-7.js @@ -0,0 +1,27 @@ +// Tests conversion from Unicode to ISO-8859-7 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u2018\u2019\u00a3\u20ac\u20af\u00a6\u00a7\u00a8\u00a9\u037a\u00ab\u00ac\u00ad\u2015\u00b0\u00b1\u00b2\u00b3\u0384\u0385\u0386\u00b7\u0388\u0389\u038a\u00bb\u038c\u00bd\u038e\u038f\u0390\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039a\u039b\u039c\u039d\u039e\u039f\u03a0\u03a1\u03a3\u03a4\u03a5\u03a6\u03a7\u03a8\u03a9\u03aa\u03ab\u03ac\u03ad\u03ae\u03af\u03b0\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c2\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03ca\u03cb\u03cc\u03cd\u03ce"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe"; + +const aliases = [ + "ISO-8859-7", + "iso-8859-7", + "greek", + "greek8", + "sun_eu_greek", + "iso_8859-7", + "iso8859-7", + "iso-ir-126", + "elot_928", + "ecma-118", + "csisolatingreek", + "iso88597", + "iso_8859-7:1987", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-8.js b/intl/uconv/tests/unit/test_encode_8859-8.js new file mode 100644 index 0000000000..12402dfb56 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-8.js @@ -0,0 +1,24 @@ +// Tests conversion from Unicode to ISO-8859-8 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00d7\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00f7\u00bb\u00bc\u00bd\u00be\u2017\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05da\u05db\u05dc\u05dd\u05de\u05df\u05e0\u05e1\u05e2\u05e3\u05e4\u05e5\u05e6\u05e7\u05e8\u05e9\u05ea\u200e\u200f"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfd\xfe"; + +const aliases = [ + "ISO-8859-8", + "iso-8859-8", + "hebrew", + "visual", + "iso_8859-8", + "iso8859-8", + "iso-ir-138", + "csisolatinhebrew", + "iso88598", + "iso_8859-8:1988", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_8859-9.js b/intl/uconv/tests/unit/test_encode_8859-9.js new file mode 100644 index 0000000000..7658ebe5ef --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_8859-9.js @@ -0,0 +1,24 @@ +// Tests conversion from Unicode to ISO-8859-9 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u011e\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u0130\u015e\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u011f\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u0131\u015f\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = [ + "ISO-8859-9", + "iso-8859-9", + "latin5", + "iso_8859-9", + "iso8859-9", + "iso-ir-148", + "l5", + "csisolatin5", + "iso88599", + "iso_8859-9:1989", +]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1250.js b/intl/uconv/tests/unit/test_encode_CP1250.js new file mode 100644 index 0000000000..5b5c0d2f0a --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1250.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1250 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0083\u201e\u2026\u2020\u2021\u0088\u2030\u0160\u2039\u015a\u0164\u017d\u0179\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u0161\u203a\u015b\u0165\u017e\u017a\u00a0\u02c7\u02d8\u0141\u00a4\u0104\u00a6\u00a7\u00a8\u00a9\u015e\u00ab\u00ac\u00ad\u00ae\u017b\u00b0\u00b1\u02db\u0142\u00b4\u00b5\u00b6\u00b7\u00b8\u0105\u015f\u00bb\u013d\u02dd\u013e\u017c\u0154\u00c1\u00c2\u0102\u00c4\u0139\u0106\u00c7\u010c\u00c9\u0118\u00cb\u011a\u00cd\u00ce\u010e\u0110\u0143\u0147\u00d3\u00d4\u0150\u00d6\u00d7\u0158\u016e\u00da\u0170\u00dc\u00dd\u0162\u00df\u0155\u00e1\u00e2\u0103\u00e4\u013a\u0107\u00e7\u010d\u00e9\u0119\u00eb\u011b\u00ed\u00ee\u010f\u0111\u0144\u0148\u00f3\u00f4\u0151\u00f6\u00f7\u0159\u016f\u00fa\u0171\u00fc\u00fd\u0163\u02d9"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1250", "x-cp1250", "cp1250"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1251.js b/intl/uconv/tests/unit/test_encode_CP1251.js new file mode 100644 index 0000000000..52d15d8731 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1251.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1251 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0402\u0403\u201a\u0453\u201e\u2026\u2020\u2021\u20ac\u2030\u0409\u2039\u040a\u040c\u040b\u040f\u0452\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u0459\u203a\u045a\u045c\u045b\u045f\u00a0\u040e\u045e\u0408\u00a4\u0490\u00a6\u00a7\u0401\u00a9\u0404\u00ab\u00ac\u00ad\u00ae\u0407\u00b0\u00b1\u0406\u0456\u0491\u00b5\u00b6\u00b7\u0451\u2116\u0454\u00bb\u0458\u0405\u0455\u0457\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1251", "x-cp1251", "cp1251"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1252.js b/intl/uconv/tests/unit/test_encode_CP1252.js new file mode 100644 index 0000000000..2f99791408 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1252.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1252 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u008d\u017d\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u009d\u017e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u00d0\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u00dd\u00de\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f0\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u00fd\u00fe\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1252", "x-cp1252", "cp1252"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1253.js b/intl/uconv/tests/unit/test_encode_CP1253.js new file mode 100644 index 0000000000..a7ba34cb9f --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1253.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1253 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u0088\u2030\u008a\u2039\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u009a\u203a\u009c\u009d\u009e\u009f\u00a0\u0385\u0386\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00ab\u00ac\u00ad\u00ae\u2015\u00b0\u00b1\u00b2\u00b3\u0384\u00b5\u00b6\u00b7\u0388\u0389\u038a\u00bb\u038c\u00bd\u038e\u038f\u0390\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039a\u039b\u039c\u039d\u039e\u039f\u03a0\u03a1\u03a3\u03a4\u03a5\u03a6\u03a7\u03a8\u03a9\u03aa\u03ab\u03ac\u03ad\u03ae\u03af\u03b0\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c2\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03ca\u03cb\u03cc\u03cd\u03ce"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe"; + +const aliases = ["windows-1253", "x-cp1253", "cp1253"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1254.js b/intl/uconv/tests/unit/test_encode_CP1254.js new file mode 100644 index 0000000000..593a33841e --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1254.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1254 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u009d\u009e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u00c3\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u00cc\u00cd\u00ce\u00cf\u011e\u00d1\u00d2\u00d3\u00d4\u00d5\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u0130\u015e\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u011f\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u0131\u015f\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1254", "x-cp1254", "cp1254"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1255.js b/intl/uconv/tests/unit/test_encode_CP1255.js new file mode 100644 index 0000000000..6da4cd53a2 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1255.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1255 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u008a\u2039\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u009a\u203a\u009c\u009d\u009e\u009f\u00a0\u00a1\u00a2\u00a3\u20aa\u00a5\u00a6\u00a7\u00a8\u00a9\u00d7\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00f7\u00bb\u00bc\u00bd\u00be\u00bf\u05b0\u05b1\u05b2\u05b3\u05b4\u05b5\u05b6\u05b7\u05b8\u05b9\u05ba\u05bb\u05bc\u05bd\u05be\u05bf\u05c0\u05c1\u05c2\u05c3\u05f0\u05f1\u05f2\u05f3\u05f4\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05da\u05db\u05dc\u05dd\u05de\u05df\u05e0\u05e1\u05e2\u05e3\u05e4\u05e5\u05e6\u05e7\u05e8\u05e9\u05ea\u200e\u200f"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfd\xfe"; + +const aliases = ["windows-1255", "x-cp1255", "cp1255"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1256.js b/intl/uconv/tests/unit/test_encode_CP1256.js new file mode 100644 index 0000000000..c8fbbb6192 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1256.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1256 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u067e\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0679\u2039\u0152\u0686\u0698\u0688\u06af\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u06a9\u2122\u0691\u203a\u0153\u200c\u200d\u06ba\u00a0\u060c\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u06be\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u061b\u00bb\u00bc\u00bd\u00be\u061f\u06c1\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u00d7\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u00e0\u0644\u00e2\u0645\u0646\u0647\u0648\u00e7\u00e8\u00e9\u00ea\u00eb\u0649\u064a\u00ee\u00ef\u064b\u064c\u064d\u064e\u00f4\u064f\u0650\u00f7\u0651\u00f9\u0652\u00fb\u00fc\u200e\u200f\u06d2"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1256", "x-cp1256", "cp1256"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1257.js b/intl/uconv/tests/unit/test_encode_CP1257.js new file mode 100644 index 0000000000..d56241ef88 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1257.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1257 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0083\u201e\u2026\u2020\u2021\u0088\u2030\u008a\u2039\u008c\u00a8\u02c7\u00b8\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u2122\u009a\u203a\u009c\u00af\u02db\u009f\u00a0\u00a2\u00a3\u00a4\u00a6\u00a7\u00d8\u00a9\u0156\u00ab\u00ac\u00ad\u00ae\u00c6\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00f8\u00b9\u0157\u00bb\u00bc\u00bd\u00be\u00e6\u0104\u012e\u0100\u0106\u00c4\u00c5\u0118\u0112\u010c\u00c9\u0179\u0116\u0122\u0136\u012a\u013b\u0160\u0143\u0145\u00d3\u014c\u00d5\u00d6\u00d7\u0172\u0141\u015a\u016a\u00dc\u017b\u017d\u00df\u0105\u012f\u0101\u0107\u00e4\u00e5\u0119\u0113\u010d\u00e9\u017a\u0117\u0123\u0137\u012b\u013c\u0161\u0144\u0146\u00f3\u014d\u00f5\u00f6\u00f7\u0173\u0142\u015b\u016b\u00fc\u017c\u017e\u02d9"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa2\xa3\xa4\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1257", "x-cp1257", "cp1257"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP1258.js b/intl/uconv/tests/unit/test_encode_CP1258.js new file mode 100644 index 0000000000..e60a2f79ba --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP1258.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-1258 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u008a\u2039\u0152\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u009a\u203a\u0153\u009d\u009e\u0178\u00a0\u00a1\u00a2\u00a3\u00a4\u00a5\u00a6\u00a7\u00a8\u00a9\u00aa\u00ab\u00ac\u00ad\u00ae\u00af\u00b0\u00b1\u00b2\u00b3\u00b4\u00b5\u00b6\u00b7\u00b8\u00b9\u00ba\u00bb\u00bc\u00bd\u00be\u00bf\u00c0\u00c1\u00c2\u0102\u00c4\u00c5\u00c6\u00c7\u00c8\u00c9\u00ca\u00cb\u0300\u00cd\u00ce\u00cf\u0110\u00d1\u0309\u00d3\u00d4\u01a0\u00d6\u00d7\u00d8\u00d9\u00da\u00db\u00dc\u01af\u0303\u00df\u00e0\u00e1\u00e2\u0103\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u0301\u00ed\u00ee\u00ef\u0111\u00f1\u0323\u00f3\u00f4\u01a1\u00f6\u00f7\u00f8\u00f9\u00fa\u00fb\u00fc\u01b0\u20ab\u00ff"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["windows-1258", "x-cp1258", "cp1258"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_CP874.js b/intl/uconv/tests/unit/test_encode_CP874.js new file mode 100644 index 0000000000..18158ef7e1 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_CP874.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to windows-874 + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20ac\u0081\u0082\u0083\u0084\u2026\u0086\u0087\u0088\u0089\u008a\u008b\u008c\u008d\u008e\u008f\u0090\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u0098\u0099\u009a\u009b\u009c\u009d\u009e\u009f\u00a0\u0e01\u0e02\u0e03\u0e04\u0e05\u0e06\u0e07\u0e08\u0e09\u0e0a\u0e0b\u0e0c\u0e0d\u0e0e\u0e0f\u0e10\u0e11\u0e12\u0e13\u0e14\u0e15\u0e16\u0e17\u0e18\u0e19\u0e1a\u0e1b\u0e1c\u0e1d\u0e1e\u0e1f\u0e20\u0e21\u0e22\u0e23\u0e24\u0e25\u0e26\u0e27\u0e28\u0e29\u0e2a\u0e2b\u0e2c\u0e2d\u0e2e\u0e2f\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37\u0e38\u0e39\u0e3a\u0e3f\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e46\u0e47\u0e48\u0e49\u0e4a\u0e4b\u0e4c\u0e4d\u0e4e\u0e4f\u0e50\u0e51\u0e52\u0e53\u0e54\u0e55\u0e56\u0e57\u0e58\u0e59\u0e5a\u0e5b"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb"; + +const aliases = ["windows-874", "dos-874"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_gb18030.js b/intl/uconv/tests/unit/test_encode_gb18030.js new file mode 100644 index 0000000000..c080e67535 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_gb18030.js @@ -0,0 +1,15 @@ +// Tests conversion from Unicode to gb18030 +// This is a sniff test which doesn't cover the full gbk range: the test string +// includes only the ASCII range and the first 63 double byte characters + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20AC\u4E02\u4E04\u4E05\u4E06\u4E0F\u4E12\u4E17\u4E1F\u4E20\u4E21\u4E23\u4E26\u4E29\u4E2E\u4E2F\u4E31\u4E33\u4E35\u4E37\u4E3C\u4E40\u4E41\u4E42\u4E44\u4E46\u4E4A\u4E51\u4E55\u4E57\u4E5A\u4E5B\u4E62\u4E63\u4E64\u4E65\u4E67\u4E68\u4E6A\u4E6B\u4E6C\u4E6D\u4E6E\u4E6F\u4E72\u4E74\u4E75\u4E76\u4E77\u4E78\u4E79\u4E7A\u4E7B\u4E7C\u4E7D\u4E7F\u4E80\u4E81\u4E82\u4E83\u4E84\u4E85\u4E87\u4E8A\uFFFD\uE7C6\u1E3F\u01F9\uE7C9\u1E3E\uE7C7\u1E40"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\xa2\xe3\x81@\x81A\x81B\x81C\x81D\x81E\x81F\x81G\x81H\x81I\x81J\x81K\x81L\x81M\x81N\x81O\x81P\x81Q\x81R\x81S\x81T\x81U\x81V\x81W\x81X\x81Y\x81Z\x81[\x81\\\x81]\x81^\x81_\x81`\x81a\x81b\x81c\x81d\x81e\x81f\x81g\x81h\x81i\x81j\x81k\x81l\x81m\x81n\x81o\x81p\x81q\x81r\x81s\x81t\x81u\x81v\x81w\x81x\x81y\x81z\x81{\x81|\x81}\x81~\x84\x31\xa4\x37\xa8\xa0\xa8\xbc\xa8\xbf\xa8\xc1\x815\xf46\x815\xf47\x815\xf48"; + +const aliases = ["gb18030"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_gbk.js b/intl/uconv/tests/unit/test_encode_gbk.js new file mode 100644 index 0000000000..50763b9dab --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_gbk.js @@ -0,0 +1,15 @@ +// Tests conversion from Unicode to gbk +// This is a sniff test which doesn't cover the full gbk range: the test string +// includes only the ASCII range and the first 63 double byte characters + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u20AC\u4E02\u4E04\u4E05\u4E06\u4E0F\u4E12\u4E17\u4E1F\u4E20\u4E21\u4E23\u4E26\u4E29\u4E2E\u4E2F\u4E31\u4E33\u4E35\u4E37\u4E3C\u4E40\u4E41\u4E42\u4E44\u4E46\u4E4A\u4E51\u4E55\u4E57\u4E5A\u4E5B\u4E62\u4E63\u4E64\u4E65\u4E67\u4E68\u4E6A\u4E6B\u4E6C\u4E6D\u4E6E\u4E6F\u4E72\u4E74\u4E75\u4E76\u4E77\u4E78\u4E79\u4E7A\u4E7B\u4E7C\u4E7D\u4E7F\u4E80\u4E81\u4E82\u4E83\u4E84\u4E85\u4E87\u4E8A\uFFFD"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81@\x81A\x81B\x81C\x81D\x81E\x81F\x81G\x81H\x81I\x81J\x81K\x81L\x81M\x81N\x81O\x81P\x81Q\x81R\x81S\x81T\x81U\x81V\x81W\x81X\x81Y\x81Z\x81[\x81\\\x81]\x81^\x81_\x81`\x81a\x81b\x81c\x81d\x81e\x81f\x81g\x81h\x81i\x81j\x81k\x81l\x81m\x81n\x81o\x81p\x81q\x81r\x81s\x81t\x81u\x81v\x81w\x81x\x81y\x81z\x81{\x81|\x81}\x81~?"; + +const aliases = ["gbk", "x-gbk"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_macintosh.js b/intl/uconv/tests/unit/test_encode_macintosh.js new file mode 100644 index 0000000000..949d0aaf7c --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_macintosh.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to x-mac-roman + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u00c4\u00c5\u00c7\u00c9\u00d1\u00d6\u00dc\u00e1\u00e0\u00e2\u00e4\u00e3\u00e5\u00e7\u00e9\u00e8\u00ea\u00eb\u00ed\u00ec\u00ee\u00ef\u00f1\u00f3\u00f2\u00f4\u00f6\u00f5\u00fa\u00f9\u00fb\u00fc\u2020\u00b0\u00a2\u00a3\u00a7\u2022\u00b6\u00df\u00ae\u00a9\u2122\u00b4\u00a8\u2260\u00c6\u00d8\u221e\u00b1\u2264\u2265\u00a5\u00b5\u2202\u2211\u220f\u03c0\u222b\u00aa\u00ba\u03a9\u00e6\u00f8\u00bf\u00a1\u00ac\u221a\u0192\u2248\u2206\u00ab\u00bb\u2026\u00a0\u00c0\u00c3\u00d5\u0152\u0153\u2013\u2014\u201c\u201d\u2018\u2019\u00f7\u25ca\u00ff\u0178\u2044\u20ac\u2039\u203a\ufb01\ufb02\u2021\u00b7\u201a\u201e\u2030\u00c2\u00ca\u00c1\u00cb\u00c8\u00cd\u00ce\u00cf\u00cc\u00d3\u00d4\uf8ff\u00d2\u00da\u00db\u00d9\u0131\u02c6\u02dc\u00af\u02d8\u02d9\u02da\u00b8\u02dd\u02db\u02c7"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["csMacintosh", "mac", "macintosh", "x-mac-roman"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_encode_x_mac_cyrillic.js b/intl/uconv/tests/unit/test_encode_x_mac_cyrillic.js new file mode 100644 index 0000000000..ac27c57cc4 --- /dev/null +++ b/intl/uconv/tests/unit/test_encode_x_mac_cyrillic.js @@ -0,0 +1,13 @@ +// Tests conversion from Unicode to x-mac-cyrillic + +const inString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u2020\u00b0\u0490\u00a3\u00a7\u2022\u00b6\u0406\u00ae\u00a9\u2122\u0402\u0452\u2260\u0403\u0453\u221e\u00b1\u2264\u2265\u0456\u00b5\u0491\u0408\u0404\u0454\u0407\u0457\u0409\u0459\u040a\u045a\u0458\u0405\u00ac\u221a\u0192\u2248\u2206\u00ab\u00bb\u2026\u00a0\u040b\u045b\u040c\u045c\u0455\u2013\u2014\u201c\u201d\u2018\u2019\u00f7\u201e\u040e\u045e\u040f\u045f\u2116\u0401\u0451\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u20ac"; + +const expectedString = + " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; + +const aliases = ["x-mac-cyrillic", "x-mac-ukrainian"]; + +function run_test() { + testEncodeAliases(aliases, inString, expectedString); +} diff --git a/intl/uconv/tests/unit/test_input_stream.js b/intl/uconv/tests/unit/test_input_stream.js new file mode 100644 index 0000000000..b33fb98356 --- /dev/null +++ b/intl/uconv/tests/unit/test_input_stream.js @@ -0,0 +1,41 @@ +var CC = Components.Constructor; +var converter = Cc[ + "@mozilla.org/intl/scriptableunicodeconverter" +].createInstance(Ci.nsIScriptableUnicodeConverter); +converter.charset = "UTF-8"; + +var SIS = CC( + "@mozilla.org/scriptableinputstream;1", + "nsIScriptableInputStream", + "init" +); + +function test_char(code) { + dump("test_char(0x" + code.toString(16) + ")\n"); + var original = String.fromCharCode(code); + var nativeStream = Cc["@mozilla.org/io/string-input-stream;1"].createInstance( + Ci.nsIStringInputStream + ); + nativeStream.setUTF8Data(original); + var stream = new SIS(nativeStream); + var utf8Result = stream.read(stream.available()); + stream.close(); + var result = converter.ConvertToUnicode(utf8Result); + Assert.equal(escape(original), escape(result)); +} + +function run_test() { + // This is not a very comprehensive test. + for (var i = 0x007f - 2; i <= 0x007f; i++) { + test_char(i); + } + for (i = 0x07ff - 2; i <= 0x07ff; i++) { + test_char(i); + } + for (i = 0x1000 - 2; i <= 0x1000 + 2; i++) { + test_char(i); + } + for (i = 0xe000; i <= 0xe000 + 2; i++) { + test_char(i); + } +} diff --git a/intl/uconv/tests/unit/test_unEscapeNonAsciiURI.js b/intl/uconv/tests/unit/test_unEscapeNonAsciiURI.js new file mode 100644 index 0000000000..f447959244 --- /dev/null +++ b/intl/uconv/tests/unit/test_unEscapeNonAsciiURI.js @@ -0,0 +1,58 @@ +// Tests for nsITextToSubURI.unEscapeNonAsciiURI +function run_test() { + // Tests whether nsTextToSubURI does UTF-16 unescaping (it shouldn't) + const testURI = "data:text/html,%FE%FF"; + Assert.equal( + Services.textToSubURI.unEscapeNonAsciiURI("UTF-16", testURI), + testURI + ); + + // Tests whether incomplete multibyte sequences throw. + const tests = [ + { + input: "http://example.com/?p=%E9", + throws: Cr.NS_ERROR_ILLEGAL_INPUT, + }, + { + input: "http://example.com/?p=%E9%80", + throws: Cr.NS_ERROR_ILLEGAL_INPUT, + }, + { + input: "http://example.com/?p=%E9%80%80", + expected: "http://example.com/?p=\u9000", + }, + { + input: "http://example.com/?p=%E9e", + throws: Cr.NS_ERROR_ILLEGAL_INPUT, + }, + { + input: "http://example.com/?p=%E9%E9", + throws: Cr.NS_ERROR_ILLEGAL_INPUT, + }, + { + input: "http://example.com/?name=M%FCller/", + throws: Cr.NS_ERROR_ILLEGAL_INPUT, + }, + { + input: "http://example.com/?name=M%C3%BCller/", + expected: "http://example.com/?name=Müller/", + }, + ]; + + for (const t of tests) { + if (t.throws !== undefined) { + let thrown = undefined; + try { + Services.textToSubURI.unEscapeNonAsciiURI("UTF-8", t.input); + } catch (e) { + thrown = e.result; + } + Assert.equal(thrown, t.throws); + } else { + Assert.equal( + Services.textToSubURI.unEscapeNonAsciiURI("UTF-8", t.input), + t.expected + ); + } + } +} diff --git a/intl/uconv/tests/unit/test_unEscapeURIForUI.js b/intl/uconv/tests/unit/test_unEscapeURIForUI.js new file mode 100644 index 0000000000..7f2fb167cc --- /dev/null +++ b/intl/uconv/tests/unit/test_unEscapeURIForUI.js @@ -0,0 +1,23 @@ +// Tests for nsITextToSubURI.unEscapeURIForUI +function run_test() { + // Tests whether incomplete multibyte sequences throw. + const tests = [ + { + input: "http://example.com/?p=%E3%80%82", + //TODO: should be the same as input, bug 1248812 + expected: "http://example.com/?p=%u3002", + }, + { + input: "http://example.com/?name=%E3%80%82", + dontEscape: true, + expected: "http://example.com/?name=\u3002", + }, + ]; + + for (const t of tests) { + Assert.equal( + Services.textToSubURI.unEscapeURIForUI(t.input, t.dontEscape), + t.expected + ); + } +} diff --git a/intl/uconv/tests/unit/test_unmapped.js b/intl/uconv/tests/unit/test_unmapped.js new file mode 100644 index 0000000000..13ee13c20e --- /dev/null +++ b/intl/uconv/tests/unit/test_unmapped.js @@ -0,0 +1,86 @@ +// Tests encoding of unmapped characters +const inString = "\uE5E5"; +const expectedString = "?"; + +function run_test() { + var failures = false; + var encodingConverter = CreateScriptableConverter(); + + // this list excludes codepages that can represent all Unicode + var encoders = [ + "Big5", + "EUC-JP", + "EUC-KR", + "GBK", + "gb18030", + "IBM866", + "ISO-2022-JP", + "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", + "ISO-8859-2", + "KOI8-R", + "KOI8-U", + "Shift_JIS", + "windows-1250", + "windows-1251", + "windows-1252", + "windows-1253", + "windows-1254", + "windows-1255", + "windows-1256", + "windows-1257", + "windows-1258", + "windows-874", + "x-mac-cyrillic", + ]; + + var counter = 0; + while (counter < encoders.length) { + var charset = encoders[counter++]; + + dump("testing " + counter + " " + charset + "\n"); + encodingConverter.charset = charset; + var codepageString = + encodingConverter.ConvertFromUnicode(inString) + + encodingConverter.Finish(); + if (codepageString != expectedString) { + dump(charset + " encoding failed\n"); + for (var i = 0; i < expectedString.length; ++i) { + if (i >= codepageString.length) { + dump( + "output length " + + codepageString.length + + " less than expected length " + + expectedString.length + + "\n" + ); + break; + } + if (codepageString.charAt(i) != expectedString.charAt(i)) { + dump( + i.toString(16) + + ": 0x" + + codepageString.charCodeAt(i).toString(16) + + " != " + + expectedString.charCodeAt(i).toString(16) + + "\n" + ); + } + } + failures = true; + } + } + if (failures) { + do_throw("test failed\n"); + } +} diff --git a/intl/uconv/tests/unit/test_utf8_illegals.js b/intl/uconv/tests/unit/test_utf8_illegals.js new file mode 100644 index 0000000000..55aec6ab8c --- /dev/null +++ b/intl/uconv/tests/unit/test_utf8_illegals.js @@ -0,0 +1,164 @@ +// Tests illegal UTF-8 sequences + +var Cc = Components.Constructor; + +const { NetUtil } = ChromeUtils.importESModule( + "resource://gre/modules/NetUtil.sys.mjs" +); + +const tests = [ + { + inStrings: [ + "%80", // Illegal or incomplete sequences + "%8f", + "%90", + "%9f", + "%a0", + "%bf", + "%c0", + "%c1", + "%c2", + "%df", + "%e0", + "%e0%a0", + "%e0%bf", + "%ed%80", + "%ed%9f", + "%ef", + "%ef%bf", + "%f0", + "%f0%90", + "%f0%90%80", + "%f0%90%bf", + "%f0%bf", + "%f0%bf%80", + "%f0%bf%bf", + "%f4", + "%f4%80", + "%f4%80%80", + "%f4%80%bf", + "%f4%8f", + "%f4%8f%80", + "%f4%8f%bf", + "%f5", + "%f7", + "%f8", + "%fb", + "%fc", + "%fd", + ], + expected: "ABC\ufffdXYZ", + }, + + { + inStrings: [ + "%c0%af", // Illegal bytes in 2-octet + "%c1%af", + ], // sequences + expected: "ABC\ufffd\ufffdXYZ", + }, + + { + inStrings: [ + "%e0%80%80", // Illegal bytes in 3-octet + "%e0%80%af", // sequences + "%e0%9f%bf", + // long surrogates + "%ed%a0%80", // D800 + "%ed%ad%bf", // DB7F + "%ed%ae%80", // DB80 + "%ed%af%bf", // DBFF + "%ed%b0%80", // DC00 + "%ed%be%80", // DF80 + "%ed%bf%bf", + ], // DFFF + expected: "ABC\ufffd\ufffd\ufffdXYZ", + }, + + { + inStrings: [ + "%f0%80%80%80", // Illegal bytes in 4-octet + "%f0%80%80%af", // sequences + "%f0%8f%bf%bf", + "%f4%90%80%80", + "%f4%bf%bf%bf", + "%f5%80%80%80", + "%f7%bf%bf%bf", + ], + expected: "ABC\ufffd\ufffd\ufffd\ufffdXYZ", + }, + + { + inStrings: [ + "%f8%80%80%80%80", // Illegal bytes in 5-octet + "%f8%80%80%80%af", // sequences + "%fb%bf%bf%bf%bf", + ], + expected: "ABC\ufffd\ufffd\ufffd\ufffd\ufffdXYZ", + }, + + // Surrogate pairs + { + inStrings: [ + "%ed%a0%80%ed%b0%80", // D800 DC00 + "%ed%a0%80%ed%bf%bf", // D800 DFFF + "%ed%ad%bf%ed%b0%80", // DB7F DC00 + "%ed%ad%bf%ed%bf%bf", // DB7F DFFF + "%ed%ae%80%ed%b0%80", // DB80 DC00 + "%ed%ae%80%ed%bf%bf", // DB80 DFFF + "%ed%af%bf%ed%b0%80", // DBFF DC00 + "%ed%ad%bf%ed%bf%bf", // DBFF DFFF + "%fc%80%80%80%80%80", // Illegal bytes in 6-octet + "%fc%80%80%80%80%af", // sequences + "%fd%bf%bf%bf%bf%bf", + ], + expected: "ABC\ufffd\ufffd\ufffd\ufffd\ufffd\ufffdXYZ", + }, +]; + +function testCaseInputStream(inStr, expected) { + var dataURI = "data:text/plain; charset=UTF-8,ABC" + inStr + "XYZ"; + dump(inStr + "==>"); + + var ConverterInputStream = Cc( + "@mozilla.org/intl/converter-input-stream;1", + "nsIConverterInputStream", + "init" + ); + var channel = NetUtil.newChannel({ + uri: dataURI, + loadUsingSystemPrincipal: true, + }); + var testInputStream = channel.open(); + var testConverter = new ConverterInputStream( + testInputStream, + "UTF-8", + 16, + 0xfffd + ); + + if (!(testConverter instanceof Ci.nsIUnicharLineInputStream)) { + throw new Error("not line input stream"); + } + + var outStr = ""; + var more; + do { + // read the line and check for eof + var line = {}; + more = testConverter.readLine(line); + outStr += line.value; + } while (more); + + dump(outStr + "; expected=" + expected + "\n"); + Assert.equal(outStr, expected); + Assert.equal(outStr.length, expected.length); +} + +function run_test() { + for (var t of tests) { + for (var inStr of t.inStrings) { + testCaseInputStream(inStr, t.expected); + } + } +} diff --git a/intl/uconv/tests/unit/xpcshell.toml b/intl/uconv/tests/unit/xpcshell.toml new file mode 100644 index 0000000000..47362902ba --- /dev/null +++ b/intl/uconv/tests/unit/xpcshell.toml @@ -0,0 +1,175 @@ +[DEFAULT] +head = "head_charsetConversionTests.js" +support-files = [ + "data/unicode-conversion.utf16.txt", + "data/unicode-conversion.utf16be.txt", + "data/unicode-conversion.utf16le.txt", + "data/unicode-conversion.utf8.txt", +] + +["test_bug116882.js"] + +["test_bug317216.js"] + +["test_bug321379.js"] + +["test_bug340714.js"] + +["test_bug381412.Big5-HKSCS.js"] + +["test_bug381412.Big5.js"] + +["test_bug381412.euc-kr.js"] + +["test_bug381412.euc_jp.js"] + +["test_bug381412.gb2312.js"] + +["test_bug381412.js"] + +["test_bug396637.js"] + +["test_bug399257.js"] + +["test_bug457886.js"] + +["test_bug522931.js"] + +["test_bug563283.js"] + +["test_bug563618.js"] + +["test_bug601429.js"] + +["test_bug715319.dbcs.js"] + +["test_bug715319.euc_jp.js"] + +["test_bug715319.gb2312.js"] + +["test_charset_conversion.js"] + +["test_decode_8859-1.js"] + +["test_decode_8859-10.js"] + +["test_decode_8859-11.js"] + +["test_decode_8859-13.js"] + +["test_decode_8859-14.js"] + +["test_decode_8859-15.js"] + +["test_decode_8859-2.js"] + +["test_decode_8859-3.js"] + +["test_decode_8859-4.js"] + +["test_decode_8859-5.js"] + +["test_decode_8859-6.js"] + +["test_decode_8859-7.js"] + +["test_decode_8859-8.js"] + +["test_decode_8859-9.js"] + +["test_decode_CP1250.js"] + +["test_decode_CP1251.js"] + +["test_decode_CP1252.js"] + +["test_decode_CP1253.js"] + +["test_decode_CP1254.js"] + +["test_decode_CP1255.js"] + +["test_decode_CP1256.js"] + +["test_decode_CP1257.js"] + +["test_decode_CP1258.js"] + +["test_decode_CP874.js"] + +["test_decode_gb18030.js"] + +["test_decode_gbk.js"] + +["test_decode_macintosh.js"] + +["test_decode_x_mac_cyrillic.js"] + +["test_decode_x_mac_ukrainian.js"] + +["test_encode_8859-1.js"] + +["test_encode_8859-10.js"] + +["test_encode_8859-11.js"] + +["test_encode_8859-13.js"] + +["test_encode_8859-14.js"] + +["test_encode_8859-15.js"] + +["test_encode_8859-2.js"] + +["test_encode_8859-3.js"] + +["test_encode_8859-4.js"] + +["test_encode_8859-5.js"] + +["test_encode_8859-6.js"] + +["test_encode_8859-7.js"] + +["test_encode_8859-8.js"] + +["test_encode_8859-9.js"] + +["test_encode_CP1250.js"] + +["test_encode_CP1251.js"] + +["test_encode_CP1252.js"] + +["test_encode_CP1253.js"] + +["test_encode_CP1254.js"] + +["test_encode_CP1255.js"] + +["test_encode_CP1256.js"] + +["test_encode_CP1257.js"] + +["test_encode_CP1258.js"] + +["test_encode_CP874.js"] + +["test_encode_gb18030.js"] + +["test_encode_gbk.js"] + +["test_encode_macintosh.js"] + +["test_encode_x_mac_cyrillic.js"] + +["test_input_stream.js"] + +["test_unEscapeNonAsciiURI.js"] + +["test_unEscapeURIForUI.js"] + +["test_unmapped.js"] + +["test_utf8_illegals.js"] + |