diff --git a/src/Umbraco.Core/Strings/DefaultShortStringHelper.cs b/src/Umbraco.Core/Strings/DefaultShortStringHelper.cs index 581cd168a3..6d26a1a888 100644 --- a/src/Umbraco.Core/Strings/DefaultShortStringHelper.cs +++ b/src/Umbraco.Core/Strings/DefaultShortStringHelper.cs @@ -278,11 +278,11 @@ namespace Umbraco.Cms.Core.Strings switch (codeType) { case CleanStringType.Ascii: - text = Utf8ToAsciiConverter.ToAsciiString(text); + text = Utf8ToAsciiConverterStatic.ToAsciiString(text); break; case CleanStringType.TryAscii: const char ESC = (char) 27; - var ctext = Utf8ToAsciiConverter.ToAsciiString(text, ESC); + var ctext = Utf8ToAsciiConverterStatic.ToAsciiString(text, ESC); if (ctext.Contains(ESC) == false) { text = ctext; diff --git a/src/Umbraco.Core/Strings/Utf8ToAsciiConverter.cs b/src/Umbraco.Core/Strings/Utf8ToAsciiConverter.cs index f997328aff..f8463f7e01 100644 --- a/src/Umbraco.Core/Strings/Utf8ToAsciiConverter.cs +++ b/src/Umbraco.Core/Strings/Utf8ToAsciiConverter.cs @@ -1,3631 +1,209 @@ +using System.Buffers; +using System.Collections.Frozen; +using System.Globalization; +using System.Text; + namespace Umbraco.Cms.Core.Strings; /// -/// Provides methods to convert Utf8 text to Ascii. +/// SIMD-optimized UTF-8 to ASCII converter with extensible character mappings. /// /// -/// Tries to match characters such as accented eg "é" to Ascii equivalent eg "e". -/// Converts all "whitespace" characters to a single whitespace. -/// Removes all non-Utf8 (unicode) characters, so in fact it can sort-of "convert" Unicode to Ascii. -/// Replaces symbols with '?'. +/// +/// This converter uses a multi-step fallback strategy: +/// 1. Dictionary lookup for special cases (ligatures, Cyrillic, special Latin) +/// 2. Unicode normalization (FormD) for accented Latin characters +/// 3. Control character stripping +/// 4. Whitespace normalization +/// 5. Fallback character for unmapped characters +/// +/// +/// Most accented Latin characters (À, é, ñ, etc.) are handled automatically via +/// Unicode normalization. Dictionary mappings are only needed for characters that +/// don't decompose correctly (ligatures like Æ→AE, Cyrillic, special Latin like Ø→O). +/// /// -public static class Utf8ToAsciiConverter +public sealed class Utf8ToAsciiConverter : IUtf8ToAsciiConverter { /// - /// Converts an Utf8 string into an Ascii string. + /// Maximum expansion ratio for output buffer sizing. + /// Worst case: single char becomes 4 chars (e.g., Щ→Shch in standard transliteration). /// - /// The text to convert. - /// The character to use to replace characters that cannot properly be converted. - /// The converted text. - public static string ToAsciiString(string text, char fail = '?') => ToAsciiString(text.AsSpan(), fail); + private const int MaxExpansionRatio = 4; - /// - /// Converts an Utf8 string into an Ascii string. - /// - /// The text to convert. - /// The character to use to replace characters that cannot properly be converted. - /// The converted text. - public static string ToAsciiString(ReadOnlySpan text, char fail = '?') + // SIMD-optimized ASCII detection (uses AVX-512 when available) + private static readonly SearchValues AsciiPrintable = + SearchValues.Create(" !\"#$%&'()*+,-./0123456789:;<=>?@" + + "ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + + "abcdefghijklmnopqrstuvwxyz{|}~"); + + private readonly FrozenDictionary _mappings; + + public Utf8ToAsciiConverter(ICharacterMappingLoader mappingLoader) { - // this is faster although it uses more memory - // but... we should be filtering short strings only... - - var totalSize = text.Length * 3; - Span output = totalSize <= 1024 ? stackalloc char[totalSize] : new char[totalSize]; // *3 because of things such as OE - var len = ToAscii(text, output, fail); - return new string(output[..len]); - - // var output = new StringBuilder(input.Length + 16); // default is 16, start with at least input length + little extra - // ToAscii(input, output); - // return output.ToString(); + _mappings = mappingLoader.LoadMappings(); } - /// - /// Converts an Utf8 string into an array of Ascii characters. - /// - /// The text to convert. - /// The character to use to replace characters that cannot properly be converted. - /// The converted text. - public static char[] ToAsciiCharArray(string text, char fail = '?') + /// + public string Convert(string? text, char fallback = '?') { - var input = text.ToCharArray(); - - // this is faster although it uses more memory - // but... we should be filtering short strings only... - int outputLength = input.Length * 3; // *3 because of things such as OE - Span output = outputLength <= 1024 ? stackalloc char[outputLength] : new char[outputLength]; - var len = ToAscii(input, output, fail); - return output[..len].ToArray(); - - // var temp = new StringBuilder(input.Length + 16); // default is 16, start with at least input length + little extra - // ToAscii(input, temp); - // var output = new char[temp.Length]; - // temp.CopyTo(0, output, 0, temp.Length); - // return output; - } - - /// - /// Converts an array of Utf8 characters into an array of Ascii characters. - /// - /// The input array. - /// The output array. - /// The character to use to replace characters that cannot properly be converted. - /// The number of characters in the output array. - /// The caller must ensure that the output array is big enough. - /// The output array is not big enough. - private static int ToAscii(ReadOnlySpan input, Span output, char fail = '?') - { - var opos = 0; - - for (var ipos = 0; ipos < input.Length; ipos++) + if (string.IsNullOrEmpty(text)) { - // ignore high surrogate - if (char.IsSurrogate(input[ipos])) + return string.Empty; + } + + var input = text.AsSpan(); + + // Fast path: all ASCII - no conversion needed + if (input.IndexOfAnyExcept(AsciiPrintable) == -1) + { + return text; + } + + // Allocate output buffer for worst-case expansion + var maxLen = text.Length * MaxExpansionRatio; + char[] arrayBuffer = ArrayPool.Shared.Rent(maxLen); + try + { + var written = Convert(input, arrayBuffer.AsSpan(), fallback); + return new string(arrayBuffer, 0, written); + } + finally + { + ArrayPool.Shared.Return(arrayBuffer); + } + } + + /// + public int Convert(ReadOnlySpan input, Span output, char fallback = '?') + { + if (input.IsEmpty) + { + return 0; + } + + var opos = 0; + var ipos = 0; + + while (ipos < input.Length) + { + // Find next non-ASCII character using SIMD + var remaining = input[ipos..]; + var asciiLen = remaining.IndexOfAnyExcept(AsciiPrintable); + + if (asciiLen == -1) { - ipos++; // and skip low surrogate - output[opos++] = fail; + // Rest is all ASCII - bulk copy + remaining.CopyTo(output[opos..]); + return opos + remaining.Length; } - else + + if (asciiLen > 0) { - ToAscii(input, ipos, output, ref opos, fail); + // Copy ASCII prefix + remaining[..asciiLen].CopyTo(output[opos..]); + opos += asciiLen; + ipos += asciiLen; } + + // Process non-ASCII character + var c = input[ipos]; + + // Handle surrogate pairs (emoji, etc.) + if (char.IsSurrogate(c)) + { + output[opos++] = fallback; + ipos++; + if (ipos < input.Length && char.IsLowSurrogate(input[ipos])) + { + ipos++; // Skip low surrogate + } + continue; + } + + opos += ProcessNonAscii(c, output[opos..], fallback); + ipos++; } return opos; } - // private static void ToAscii(char[] input, StringBuilder output) - // { - // var chars = new char[5]; - - // for (var ipos = 0; ipos < input.Length; ipos++) - // { - // var opos = 0; - // if (char.IsSurrogate(input[ipos])) - // ipos++; - // else - // { - // ToAscii(input, ipos, chars, ref opos); - // output.Append(chars, 0, opos); - // } - // } - // } - - /// - /// Converts the character at position in input array of Utf8 characters - /// - /// and writes the converted value to output array of Ascii characters at position - /// , - /// and increments that position accordingly. - /// - /// The input array. - /// The input position. - /// The output array. - /// The output position. - /// The character to use to replace characters that cannot properly be converted. - /// - /// Adapted from various sources on the 'net including Lucene.Net.Analysis.ASCIIFoldingFilter. - /// Input should contain Utf8 characters exclusively and NOT Unicode. - /// Removes controls, normalizes whitespaces, replaces symbols by '?'. - /// - private static void ToAscii(ReadOnlySpan input, int ipos, Span output, ref int opos, char fail = '?') + private int ProcessNonAscii(char c, Span output, char fallback) { - var c = input[ipos]; + // 1. Check special cases dictionary (ligatures, Cyrillic, etc.) + if (_mappings.TryGetValue(c, out var mapped)) + { + if (mapped.Length == 0) + { + return 0; // Empty mapping = strip character + } + mapped.AsSpan().CopyTo(output); + return mapped.Length; + } + // 2. Try Unicode normalization (handles most accented chars) + var normLen = TryNormalize(c, output); + if (normLen > 0) + { + return normLen; + } + + // 3. Control character handling if (char.IsControl(c)) { - // Control characters are non-printing and formatting characters, such as ACK, BEL, CR, FF, LF, and VT. - // The Unicode standard assigns the following code points to control characters: from \U0000 to \U001F, - // \U007F, and from \U0080 to \U009F. According to the Unicode standard, these values are to be - // interpreted as control characters unless their use is otherwise defined by an application. Valid - // control characters are members of the UnicodeCategory.Control category. - - // we don't want them + return 0; // Strip control characters } - // else if (char.IsSeparator(c)) - // { - // // The Unicode standard recognizes three subcategories of separators: - // // - Space separators (the UnicodeCategory.SpaceSeparator category), which includes characters such as \u0020. - // // - Line separators (the UnicodeCategory.LineSeparator category), which includes \u2028. - // // - Paragraph separators (the UnicodeCategory.ParagraphSeparator category), which includes \u2029. - // // - // // Note: The Unicode standard classifies the characters \u000A (LF), \u000C (FF), and \u000A (CR) as control - // // characters (members of the UnicodeCategory.Control category), not as separator characters. - - // // better do it via WhiteSpace - // } - else if (char.IsWhiteSpace(c)) + // 4. Whitespace normalization + if (char.IsWhiteSpace(c)) { - // White space characters are the following Unicode characters: - // - Members of the SpaceSeparator category, which includes the characters SPACE (U+0020), - // OGHAM SPACE MARK (U+1680), MONGOLIAN VOWEL SEPARATOR (U+180E), EN QUAD (U+2000), EM QUAD (U+2001), - // EN SPACE (U+2002), EM SPACE (U+2003), THREE-PER-EM SPACE (U+2004), FOUR-PER-EM SPACE (U+2005), - // SIX-PER-EM SPACE (U+2006), FIGURE SPACE (U+2007), PUNCTUATION SPACE (U+2008), THIN SPACE (U+2009), - // HAIR SPACE (U+200A), NARROW NO-BREAK SPACE (U+202F), MEDIUM MATHEMATICAL SPACE (U+205F), - // and IDEOGRAPHIC SPACE (U+3000). - // - Members of the LineSeparator category, which consists solely of the LINE SEPARATOR character (U+2028). - // - Members of the ParagraphSeparator category, which consists solely of the PARAGRAPH SEPARATOR character (U+2029). - // - The characters CHARACTER TABULATION (U+0009), LINE FEED (U+000A), LINE TABULATION (U+000B), - // FORM FEED (U+000C), CARRIAGE RETURN (U+000D), NEXT LINE (U+0085), and NO-BREAK SPACE (U+00A0). - - // make it a whitespace - output[opos++] = ' '; + output[0] = ' '; + return 1; } - else if (c < '\u0080') - { - // safe - output[opos++] = c; - } - else - { - switch (c) - { - case '\u00C0': - // À [LATIN CAPITAL LETTER A WITH GRAVE] - case '\u00C1': - // � [LATIN CAPITAL LETTER A WITH ACUTE] - case '\u00C2': - //  [LATIN CAPITAL LETTER A WITH CIRCUMFLEX] - case '\u00C3': - // à [LATIN CAPITAL LETTER A WITH TILDE] - case '\u00C4': - // Ä [LATIN CAPITAL LETTER A WITH DIAERESIS] - case '\u00C5': - // Ã… [LATIN CAPITAL LETTER A WITH RING ABOVE] - case '\u0100': - // Ä€ [LATIN CAPITAL LETTER A WITH MACRON] - case '\u0102': - // Ä‚ [LATIN CAPITAL LETTER A WITH BREVE] - case '\u0104': - // Ä„ [LATIN CAPITAL LETTER A WITH OGONEK] - case '\u018F': - // � http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA] - case '\u01CD': - // � [LATIN CAPITAL LETTER A WITH CARON] - case '\u01DE': - // Çž [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON] - case '\u01E0': - // Ç  [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON] - case '\u01FA': - // Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE] - case '\u0200': - // È€ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE] - case '\u0202': - // È‚ [LATIN CAPITAL LETTER A WITH INVERTED BREVE] - case '\u0226': - // Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE] - case '\u023A': - // Ⱥ [LATIN CAPITAL LETTER A WITH STROKE] - case '\u1D00': - // á´€ [LATIN LETTER SMALL CAPITAL A] - case '\u1E00': - // Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW] - case '\u1EA0': - // Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW] - case '\u1EA2': - // Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE] - case '\u1EA4': - // Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE] - case '\u1EA6': - // Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE] - case '\u1EA8': - // Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1EAA': - // Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE] - case '\u1EAC': - // Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW] - case '\u1EAE': - // Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE] - case '\u1EB0': - // Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE] - case '\u1EB2': - // Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE] - case '\u1EB4': - // Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE] - case '\u1EB6': - // Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW] - case '\u24B6': - // â’¶ [CIRCLED LATIN CAPITAL LETTER A] - case '\uFF21': // Ａ [FULLWIDTH LATIN CAPITAL LETTER A] - output[opos++] = 'A'; - break; - case '\u00E0': - // à [LATIN SMALL LETTER A WITH GRAVE] - case '\u00E1': - // á [LATIN SMALL LETTER A WITH ACUTE] - case '\u00E2': - // â [LATIN SMALL LETTER A WITH CIRCUMFLEX] - case '\u00E3': - // ã [LATIN SMALL LETTER A WITH TILDE] - case '\u00E4': - // ä [LATIN SMALL LETTER A WITH DIAERESIS] - case '\u00E5': - // Ã¥ [LATIN SMALL LETTER A WITH RING ABOVE] - case '\u0101': - // � [LATIN SMALL LETTER A WITH MACRON] - case '\u0103': - // ă [LATIN SMALL LETTER A WITH BREVE] - case '\u0105': - // Ä… [LATIN SMALL LETTER A WITH OGONEK] - case '\u01CE': - // ÇŽ [LATIN SMALL LETTER A WITH CARON] - case '\u01DF': - // ÇŸ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON] - case '\u01E1': - // Ç¡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON] - case '\u01FB': - // Ç» [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE] - case '\u0201': - // � [LATIN SMALL LETTER A WITH DOUBLE GRAVE] - case '\u0203': - // ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE] - case '\u0227': - // ȧ [LATIN SMALL LETTER A WITH DOT ABOVE] - case '\u0250': - // � [LATIN SMALL LETTER TURNED A] - case '\u0259': - // É™ [LATIN SMALL LETTER SCHWA] - case '\u025A': - // Éš [LATIN SMALL LETTER SCHWA WITH HOOK] - case '\u1D8F': - // � [LATIN SMALL LETTER A WITH RETROFLEX HOOK] - case '\u1D95': - // ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK] - case '\u1E01': - // ạ [LATIN SMALL LETTER A WITH RING BELOW] - case '\u1E9A': - // ả [LATIN SMALL LETTER A WITH RIGHT HALF RING] - case '\u1EA1': - // ạ [LATIN SMALL LETTER A WITH DOT BELOW] - case '\u1EA3': - // ả [LATIN SMALL LETTER A WITH HOOK ABOVE] - case '\u1EA5': - // ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE] - case '\u1EA7': - // ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE] - case '\u1EA9': - // ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1EAB': - // ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE] - case '\u1EAD': - // ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW] - case '\u1EAF': - // ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE] - case '\u1EB1': - // ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE] - case '\u1EB3': - // ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE] - case '\u1EB5': - // ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE] - case '\u1EB7': - // ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW] - case '\u2090': - // � [LATIN SUBSCRIPT SMALL LETTER A] - case '\u2094': - // �? [LATIN SUBSCRIPT SMALL LETTER SCHWA] - case '\u24D0': - // � [CIRCLED LATIN SMALL LETTER A] - case '\u2C65': - // â±¥ [LATIN SMALL LETTER A WITH STROKE] - case '\u2C6F': - // Ɐ [LATIN CAPITAL LETTER TURNED A] - case '\uFF41': // � [FULLWIDTH LATIN SMALL LETTER A] - output[opos++] = 'a'; - break; - - case '\uA732': // Ꜳ [LATIN CAPITAL LETTER AA] - output[opos++] = 'A'; - output[opos++] = 'A'; - break; - - case '\u00C6': - // Æ [LATIN CAPITAL LETTER AE] - case '\u01E2': - // Ç¢ [LATIN CAPITAL LETTER AE WITH MACRON] - case '\u01FC': - // Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE] - case '\u1D01': // á´� [LATIN LETTER SMALL CAPITAL AE] - output[opos++] = 'A'; - output[opos++] = 'E'; - break; - - case '\uA734': // Ꜵ [LATIN CAPITAL LETTER AO] - output[opos++] = 'A'; - output[opos++] = 'O'; - break; - - case '\uA736': // Ꜷ [LATIN CAPITAL LETTER AU] - output[opos++] = 'A'; - output[opos++] = 'U'; - break; - - case '\uA738': - // Ꜹ [LATIN CAPITAL LETTER AV] - case '\uA73A': // Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR] - output[opos++] = 'A'; - output[opos++] = 'V'; - break; - - case '\uA73C': // Ꜽ [LATIN CAPITAL LETTER AY] - output[opos++] = 'A'; - output[opos++] = 'Y'; - break; - - case '\u249C': // â’œ [PARENTHESIZED LATIN SMALL LETTER A] - output[opos++] = '('; - output[opos++] = 'a'; - output[opos++] = ')'; - break; - - case '\uA733': // ꜳ [LATIN SMALL LETTER AA] - output[opos++] = 'a'; - output[opos++] = 'a'; - break; - - case '\u00E6': - // æ [LATIN SMALL LETTER AE] - case '\u01E3': - // Ç£ [LATIN SMALL LETTER AE WITH MACRON] - case '\u01FD': - // ǽ [LATIN SMALL LETTER AE WITH ACUTE] - case '\u1D02': // á´‚ [LATIN SMALL LETTER TURNED AE] - output[opos++] = 'a'; - output[opos++] = 'e'; - break; - - case '\uA735': // ꜵ [LATIN SMALL LETTER AO] - output[opos++] = 'a'; - output[opos++] = 'o'; - break; - - case '\uA737': // ꜷ [LATIN SMALL LETTER AU] - output[opos++] = 'a'; - output[opos++] = 'u'; - break; - - case '\uA739': - // ꜹ [LATIN SMALL LETTER AV] - case '\uA73B': // ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR] - output[opos++] = 'a'; - output[opos++] = 'v'; - break; - - case '\uA73D': // ꜽ [LATIN SMALL LETTER AY] - output[opos++] = 'a'; - output[opos++] = 'y'; - break; - - case '\u0181': - // � [LATIN CAPITAL LETTER B WITH HOOK] - case '\u0182': - // Æ‚ [LATIN CAPITAL LETTER B WITH TOPBAR] - case '\u0243': - // Ƀ [LATIN CAPITAL LETTER B WITH STROKE] - case '\u0299': - // Ê™ [LATIN LETTER SMALL CAPITAL B] - case '\u1D03': - // á´ƒ [LATIN LETTER SMALL CAPITAL BARRED B] - case '\u1E02': - // Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE] - case '\u1E04': - // Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW] - case '\u1E06': - // Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW] - case '\u24B7': - // â’· [CIRCLED LATIN CAPITAL LETTER B] - case '\uFF22': // ï¼¢ [FULLWIDTH LATIN CAPITAL LETTER B] - output[opos++] = 'B'; - break; - - case '\u0180': - // Æ€ [LATIN SMALL LETTER B WITH STROKE] - case '\u0183': - // ƃ [LATIN SMALL LETTER B WITH TOPBAR] - case '\u0253': - // É“ [LATIN SMALL LETTER B WITH HOOK] - case '\u1D6C': - // ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE] - case '\u1D80': - // ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK] - case '\u1E03': - // ḃ [LATIN SMALL LETTER B WITH DOT ABOVE] - case '\u1E05': - // ḅ [LATIN SMALL LETTER B WITH DOT BELOW] - case '\u1E07': - // ḇ [LATIN SMALL LETTER B WITH LINE BELOW] - case '\u24D1': - // â“‘ [CIRCLED LATIN SMALL LETTER B] - case '\uFF42': // ｂ [FULLWIDTH LATIN SMALL LETTER B] - output[opos++] = 'b'; - break; - - case '\u249D': // â’� [PARENTHESIZED LATIN SMALL LETTER B] - output[opos++] = '('; - output[opos++] = 'b'; - output[opos++] = ')'; - break; - - case '\u00C7': - // Ç [LATIN CAPITAL LETTER C WITH CEDILLA] - case '\u0106': - // Ć [LATIN CAPITAL LETTER C WITH ACUTE] - case '\u0108': - // Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX] - case '\u010A': - // ÄŠ [LATIN CAPITAL LETTER C WITH DOT ABOVE] - case '\u010C': - // ÄŒ [LATIN CAPITAL LETTER C WITH CARON] - case '\u0187': - // Ƈ [LATIN CAPITAL LETTER C WITH HOOK] - case '\u023B': - // È» [LATIN CAPITAL LETTER C WITH STROKE] - case '\u0297': - // Ê— [LATIN LETTER STRETCHED C] - case '\u1D04': - // á´„ [LATIN LETTER SMALL CAPITAL C] - case '\u1E08': - // Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE] - case '\u24B8': - // â’¸ [CIRCLED LATIN CAPITAL LETTER C] - case '\uFF23': // ï¼£ [FULLWIDTH LATIN CAPITAL LETTER C] - output[opos++] = 'C'; - break; - - case '\u00E7': - // ç [LATIN SMALL LETTER C WITH CEDILLA] - case '\u0107': - // ć [LATIN SMALL LETTER C WITH ACUTE] - case '\u0109': - // ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX] - case '\u010B': - // Ä‹ [LATIN SMALL LETTER C WITH DOT ABOVE] - case '\u010D': - // � [LATIN SMALL LETTER C WITH CARON] - case '\u0188': - // ƈ [LATIN SMALL LETTER C WITH HOOK] - case '\u023C': - // ȼ [LATIN SMALL LETTER C WITH STROKE] - case '\u0255': - // É• [LATIN SMALL LETTER C WITH CURL] - case '\u1E09': - // ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE] - case '\u2184': - // ↄ [LATIN SMALL LETTER REVERSED C] - case '\u24D2': - // â“’ [CIRCLED LATIN SMALL LETTER C] - case '\uA73E': - // Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT] - case '\uA73F': - // ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT] - case '\uFF43': // ｃ [FULLWIDTH LATIN SMALL LETTER C] - output[opos++] = 'c'; - break; - - case '\u249E': // â’ž [PARENTHESIZED LATIN SMALL LETTER C] - output[opos++] = '('; - output[opos++] = 'c'; - output[opos++] = ')'; - break; - - case '\u00D0': - // � [LATIN CAPITAL LETTER ETH] - case '\u010E': - // ÄŽ [LATIN CAPITAL LETTER D WITH CARON] - case '\u0110': - // � [LATIN CAPITAL LETTER D WITH STROKE] - case '\u0189': - // Ɖ [LATIN CAPITAL LETTER AFRICAN D] - case '\u018A': - // ÆŠ [LATIN CAPITAL LETTER D WITH HOOK] - case '\u018B': - // Æ‹ [LATIN CAPITAL LETTER D WITH TOPBAR] - case '\u1D05': - // á´… [LATIN LETTER SMALL CAPITAL D] - case '\u1D06': - // á´† [LATIN LETTER SMALL CAPITAL ETH] - case '\u1E0A': - // Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE] - case '\u1E0C': - // Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW] - case '\u1E0E': - // Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW] - case '\u1E10': - // � [LATIN CAPITAL LETTER D WITH CEDILLA] - case '\u1E12': - // Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW] - case '\u24B9': - // â’¹ [CIRCLED LATIN CAPITAL LETTER D] - case '\uA779': - // � [LATIN CAPITAL LETTER INSULAR D] - case '\uFF24': // Ｄ [FULLWIDTH LATIN CAPITAL LETTER D] - output[opos++] = 'D'; - break; - - case '\u00F0': - // ð [LATIN SMALL LETTER ETH] - case '\u010F': - // � [LATIN SMALL LETTER D WITH CARON] - case '\u0111': - // Ä‘ [LATIN SMALL LETTER D WITH STROKE] - case '\u018C': - // ÆŒ [LATIN SMALL LETTER D WITH TOPBAR] - case '\u0221': - // È¡ [LATIN SMALL LETTER D WITH CURL] - case '\u0256': - // É– [LATIN SMALL LETTER D WITH TAIL] - case '\u0257': - // É— [LATIN SMALL LETTER D WITH HOOK] - case '\u1D6D': - // áµ­ [LATIN SMALL LETTER D WITH MIDDLE TILDE] - case '\u1D81': - // � [LATIN SMALL LETTER D WITH PALATAL HOOK] - case '\u1D91': - // ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL] - case '\u1E0B': - // ḋ [LATIN SMALL LETTER D WITH DOT ABOVE] - case '\u1E0D': - // � [LATIN SMALL LETTER D WITH DOT BELOW] - case '\u1E0F': - // � [LATIN SMALL LETTER D WITH LINE BELOW] - case '\u1E11': - // ḑ [LATIN SMALL LETTER D WITH CEDILLA] - case '\u1E13': - // ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW] - case '\u24D3': - // â““ [CIRCLED LATIN SMALL LETTER D] - case '\uA77A': - // � [LATIN SMALL LETTER INSULAR D] - case '\uFF44': // ｄ [FULLWIDTH LATIN SMALL LETTER D] - output[opos++] = 'd'; - break; - - case '\u01C4': - // Ç„ [LATIN CAPITAL LETTER DZ WITH CARON] - case '\u01F1': // DZ [LATIN CAPITAL LETTER DZ] - output[opos++] = 'D'; - output[opos++] = 'Z'; - break; - - case '\u01C5': - // Ç… [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON] - case '\u01F2': // Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z] - output[opos++] = 'D'; - output[opos++] = 'z'; - break; - - case '\u249F': // â’Ÿ [PARENTHESIZED LATIN SMALL LETTER D] - output[opos++] = '('; - output[opos++] = 'd'; - output[opos++] = ')'; - break; - - case '\u0238': // ȸ [LATIN SMALL LETTER DB DIGRAPH] - output[opos++] = 'd'; - output[opos++] = 'b'; - break; - - case '\u01C6': - // dž [LATIN SMALL LETTER DZ WITH CARON] - case '\u01F3': - // dz [LATIN SMALL LETTER DZ] - case '\u02A3': - // Ê£ [LATIN SMALL LETTER DZ DIGRAPH] - case '\u02A5': // Ê¥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL] - output[opos++] = 'd'; - output[opos++] = 'z'; - break; - - case '\u00C8': - // È [LATIN CAPITAL LETTER E WITH GRAVE] - case '\u00C9': - // É [LATIN CAPITAL LETTER E WITH ACUTE] - case '\u00CA': - // Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX] - case '\u00CB': - // Ë [LATIN CAPITAL LETTER E WITH DIAERESIS] - case '\u0112': - // Ä’ [LATIN CAPITAL LETTER E WITH MACRON] - case '\u0114': - // �? [LATIN CAPITAL LETTER E WITH BREVE] - case '\u0116': - // Ä– [LATIN CAPITAL LETTER E WITH DOT ABOVE] - case '\u0118': - // Ę [LATIN CAPITAL LETTER E WITH OGONEK] - case '\u011A': - // Äš [LATIN CAPITAL LETTER E WITH CARON] - case '\u018E': - // ÆŽ [LATIN CAPITAL LETTER REVERSED E] - case '\u0190': - // � [LATIN CAPITAL LETTER OPEN E] - case '\u0204': - // È„ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE] - case '\u0206': - // Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE] - case '\u0228': - // Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA] - case '\u0246': - // Ɇ [LATIN CAPITAL LETTER E WITH STROKE] - case '\u1D07': - // á´‡ [LATIN LETTER SMALL CAPITAL E] - case '\u1E14': - // �? [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE] - case '\u1E16': - // Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE] - case '\u1E18': - // Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW] - case '\u1E1A': - // Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW] - case '\u1E1C': - // Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE] - case '\u1EB8': - // Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW] - case '\u1EBA': - // Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE] - case '\u1EBC': - // Ẽ [LATIN CAPITAL LETTER E WITH TILDE] - case '\u1EBE': - // Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE] - case '\u1EC0': - // Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE] - case '\u1EC2': - // Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1EC4': - // Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE] - case '\u1EC6': - // Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW] - case '\u24BA': - // â’º [CIRCLED LATIN CAPITAL LETTER E] - case '\u2C7B': - // â±» [LATIN LETTER SMALL CAPITAL TURNED E] - case '\uFF25': // ï¼¥ [FULLWIDTH LATIN CAPITAL LETTER E] - output[opos++] = 'E'; - break; - - case '\u00E8': - // è [LATIN SMALL LETTER E WITH GRAVE] - case '\u00E9': - // é [LATIN SMALL LETTER E WITH ACUTE] - case '\u00EA': - // ê [LATIN SMALL LETTER E WITH CIRCUMFLEX] - case '\u00EB': - // ë [LATIN SMALL LETTER E WITH DIAERESIS] - case '\u0113': - // Ä“ [LATIN SMALL LETTER E WITH MACRON] - case '\u0115': - // Ä• [LATIN SMALL LETTER E WITH BREVE] - case '\u0117': - // Ä— [LATIN SMALL LETTER E WITH DOT ABOVE] - case '\u0119': - // Ä™ [LATIN SMALL LETTER E WITH OGONEK] - case '\u011B': - // Ä› [LATIN SMALL LETTER E WITH CARON] - case '\u01DD': - // � [LATIN SMALL LETTER TURNED E] - case '\u0205': - // È… [LATIN SMALL LETTER E WITH DOUBLE GRAVE] - case '\u0207': - // ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE] - case '\u0229': - // È© [LATIN SMALL LETTER E WITH CEDILLA] - case '\u0247': - // ɇ [LATIN SMALL LETTER E WITH STROKE] - case '\u0258': - // ɘ [LATIN SMALL LETTER REVERSED E] - case '\u025B': - // É› [LATIN SMALL LETTER OPEN E] - case '\u025C': - // Éœ [LATIN SMALL LETTER REVERSED OPEN E] - case '\u025D': - // � [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK] - case '\u025E': - // Éž [LATIN SMALL LETTER CLOSED REVERSED OPEN E] - case '\u029A': - // Êš [LATIN SMALL LETTER CLOSED OPEN E] - case '\u1D08': - // á´ˆ [LATIN SMALL LETTER TURNED OPEN E] - case '\u1D92': - // ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK] - case '\u1D93': - // ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK] - case '\u1D94': - // �? [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK] - case '\u1E15': - // ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE] - case '\u1E17': - // ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE] - case '\u1E19': - // ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW] - case '\u1E1B': - // ḛ [LATIN SMALL LETTER E WITH TILDE BELOW] - case '\u1E1D': - // � [LATIN SMALL LETTER E WITH CEDILLA AND BREVE] - case '\u1EB9': - // ẹ [LATIN SMALL LETTER E WITH DOT BELOW] - case '\u1EBB': - // ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE] - case '\u1EBD': - // ẽ [LATIN SMALL LETTER E WITH TILDE] - case '\u1EBF': - // ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE] - case '\u1EC1': - // � [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE] - case '\u1EC3': - // ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1EC5': - // á»… [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE] - case '\u1EC7': - // ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW] - case '\u2091': - // â‚‘ [LATIN SUBSCRIPT SMALL LETTER E] - case '\u24D4': - // �? [CIRCLED LATIN SMALL LETTER E] - case '\u2C78': - // ⱸ [LATIN SMALL LETTER E WITH NOTCH] - case '\uFF45': // ï½… [FULLWIDTH LATIN SMALL LETTER E] - output[opos++] = 'e'; - break; - - case '\u24A0': // â’  [PARENTHESIZED LATIN SMALL LETTER E] - output[opos++] = '('; - output[opos++] = 'e'; - output[opos++] = ')'; - break; - - case '\u0191': - // Æ‘ [LATIN CAPITAL LETTER F WITH HOOK] - case '\u1E1E': - // Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE] - case '\u24BB': - // â’» [CIRCLED LATIN CAPITAL LETTER F] - case '\uA730': - // ꜰ [LATIN LETTER SMALL CAPITAL F] - case '\uA77B': - // � [LATIN CAPITAL LETTER INSULAR F] - case '\uA7FB': - // ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F] - case '\uFF26': // Ｆ [FULLWIDTH LATIN CAPITAL LETTER F] - output[opos++] = 'F'; - break; - - case '\u0192': - // Æ’ [LATIN SMALL LETTER F WITH HOOK] - case '\u1D6E': - // áµ® [LATIN SMALL LETTER F WITH MIDDLE TILDE] - case '\u1D82': - // ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK] - case '\u1E1F': - // ḟ [LATIN SMALL LETTER F WITH DOT ABOVE] - case '\u1E9B': - // ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE] - case '\u24D5': - // â“• [CIRCLED LATIN SMALL LETTER F] - case '\uA77C': - // � [LATIN SMALL LETTER INSULAR F] - case '\uFF46': // ｆ [FULLWIDTH LATIN SMALL LETTER F] - output[opos++] = 'f'; - break; - - case '\u24A1': // â’¡ [PARENTHESIZED LATIN SMALL LETTER F] - output[opos++] = '('; - output[opos++] = 'f'; - output[opos++] = ')'; - break; - - case '\uFB00': // ff [LATIN SMALL LIGATURE FF] - output[opos++] = 'f'; - output[opos++] = 'f'; - break; - - case '\uFB03': // ffi [LATIN SMALL LIGATURE FFI] - output[opos++] = 'f'; - output[opos++] = 'f'; - output[opos++] = 'i'; - break; - - case '\uFB04': // ffl [LATIN SMALL LIGATURE FFL] - output[opos++] = 'f'; - output[opos++] = 'f'; - output[opos++] = 'l'; - break; - - case '\uFB01': // � [LATIN SMALL LIGATURE FI] - output[opos++] = 'f'; - output[opos++] = 'i'; - break; - - case '\uFB02': // fl [LATIN SMALL LIGATURE FL] - output[opos++] = 'f'; - output[opos++] = 'l'; - break; - - case '\u011C': - // Äœ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX] - case '\u011E': - // Äž [LATIN CAPITAL LETTER G WITH BREVE] - case '\u0120': - // Ä  [LATIN CAPITAL LETTER G WITH DOT ABOVE] - case '\u0122': - // Ä¢ [LATIN CAPITAL LETTER G WITH CEDILLA] - case '\u0193': - // Æ“ [LATIN CAPITAL LETTER G WITH HOOK] - case '\u01E4': - // Ǥ [LATIN CAPITAL LETTER G WITH STROKE] - case '\u01E5': - // Ç¥ [LATIN SMALL LETTER G WITH STROKE] - case '\u01E6': - // Ǧ [LATIN CAPITAL LETTER G WITH CARON] - case '\u01E7': - // ǧ [LATIN SMALL LETTER G WITH CARON] - case '\u01F4': - // Ç´ [LATIN CAPITAL LETTER G WITH ACUTE] - case '\u0262': - // É¢ [LATIN LETTER SMALL CAPITAL G] - case '\u029B': - // Ê› [LATIN LETTER SMALL CAPITAL G WITH HOOK] - case '\u1E20': - // Ḡ [LATIN CAPITAL LETTER G WITH MACRON] - case '\u24BC': - // â’¼ [CIRCLED LATIN CAPITAL LETTER G] - case '\uA77D': - // � [LATIN CAPITAL LETTER INSULAR G] - case '\uA77E': - // � [LATIN CAPITAL LETTER TURNED INSULAR G] - case '\uFF27': // Ｇ [FULLWIDTH LATIN CAPITAL LETTER G] - output[opos++] = 'G'; - break; - - case '\u011D': - // � [LATIN SMALL LETTER G WITH CIRCUMFLEX] - case '\u011F': - // ÄŸ [LATIN SMALL LETTER G WITH BREVE] - case '\u0121': - // Ä¡ [LATIN SMALL LETTER G WITH DOT ABOVE] - case '\u0123': - // Ä£ [LATIN SMALL LETTER G WITH CEDILLA] - case '\u01F5': - // ǵ [LATIN SMALL LETTER G WITH ACUTE] - case '\u0260': - // É  [LATIN SMALL LETTER G WITH HOOK] - case '\u0261': - // É¡ [LATIN SMALL LETTER SCRIPT G] - case '\u1D77': - // áµ· [LATIN SMALL LETTER TURNED G] - case '\u1D79': - // áµ¹ [LATIN SMALL LETTER INSULAR G] - case '\u1D83': - // ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK] - case '\u1E21': - // ḡ [LATIN SMALL LETTER G WITH MACRON] - case '\u24D6': - // â“– [CIRCLED LATIN SMALL LETTER G] - case '\uA77F': - // � [LATIN SMALL LETTER TURNED INSULAR G] - case '\uFF47': // ｇ [FULLWIDTH LATIN SMALL LETTER G] - output[opos++] = 'g'; - break; - - case '\u24A2': // â’¢ [PARENTHESIZED LATIN SMALL LETTER G] - output[opos++] = '('; - output[opos++] = 'g'; - output[opos++] = ')'; - break; - - case '\u0124': - // Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX] - case '\u0126': - // Ħ [LATIN CAPITAL LETTER H WITH STROKE] - case '\u021E': - // Èž [LATIN CAPITAL LETTER H WITH CARON] - case '\u029C': - // Êœ [LATIN LETTER SMALL CAPITAL H] - case '\u1E22': - // Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE] - case '\u1E24': - // Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW] - case '\u1E26': - // Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS] - case '\u1E28': - // Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA] - case '\u1E2A': - // Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW] - case '\u24BD': - // â’½ [CIRCLED LATIN CAPITAL LETTER H] - case '\u2C67': - // Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER] - case '\u2C75': - // â±µ [LATIN CAPITAL LETTER HALF H] - case '\uFF28': // Ｈ [FULLWIDTH LATIN CAPITAL LETTER H] - output[opos++] = 'H'; - break; - - case '\u0125': - // Ä¥ [LATIN SMALL LETTER H WITH CIRCUMFLEX] - case '\u0127': - // ħ [LATIN SMALL LETTER H WITH STROKE] - case '\u021F': - // ÈŸ [LATIN SMALL LETTER H WITH CARON] - case '\u0265': - // É¥ [LATIN SMALL LETTER TURNED H] - case '\u0266': - // ɦ [LATIN SMALL LETTER H WITH HOOK] - case '\u02AE': - // Ê® [LATIN SMALL LETTER TURNED H WITH FISHHOOK] - case '\u02AF': - // ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL] - case '\u1E23': - // ḣ [LATIN SMALL LETTER H WITH DOT ABOVE] - case '\u1E25': - // ḥ [LATIN SMALL LETTER H WITH DOT BELOW] - case '\u1E27': - // ḧ [LATIN SMALL LETTER H WITH DIAERESIS] - case '\u1E29': - // ḩ [LATIN SMALL LETTER H WITH CEDILLA] - case '\u1E2B': - // ḫ [LATIN SMALL LETTER H WITH BREVE BELOW] - case '\u1E96': - // ẖ [LATIN SMALL LETTER H WITH LINE BELOW] - case '\u24D7': - // â“— [CIRCLED LATIN SMALL LETTER H] - case '\u2C68': - // ⱨ [LATIN SMALL LETTER H WITH DESCENDER] - case '\u2C76': - // ⱶ [LATIN SMALL LETTER HALF H] - case '\uFF48': // ｈ [FULLWIDTH LATIN SMALL LETTER H] - output[opos++] = 'h'; - break; - - case '\u01F6': // Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR] - output[opos++] = 'H'; - output[opos++] = 'V'; - break; - - case '\u24A3': // â’£ [PARENTHESIZED LATIN SMALL LETTER H] - output[opos++] = '('; - output[opos++] = 'h'; - output[opos++] = ')'; - break; - - case '\u0195': // Æ• [LATIN SMALL LETTER HV] - output[opos++] = 'h'; - output[opos++] = 'v'; - break; - - case '\u00CC': - // ÃŒ [LATIN CAPITAL LETTER I WITH GRAVE] - case '\u00CD': - // � [LATIN CAPITAL LETTER I WITH ACUTE] - case '\u00CE': - // ÃŽ [LATIN CAPITAL LETTER I WITH CIRCUMFLEX] - case '\u00CF': - // � [LATIN CAPITAL LETTER I WITH DIAERESIS] - case '\u0128': - // Ĩ [LATIN CAPITAL LETTER I WITH TILDE] - case '\u012A': - // Ī [LATIN CAPITAL LETTER I WITH MACRON] - case '\u012C': - // Ĭ [LATIN CAPITAL LETTER I WITH BREVE] - case '\u012E': - // Ä® [LATIN CAPITAL LETTER I WITH OGONEK] - case '\u0130': - // Ä° [LATIN CAPITAL LETTER I WITH DOT ABOVE] - case '\u0196': - // Æ– [LATIN CAPITAL LETTER IOTA] - case '\u0197': - // Æ— [LATIN CAPITAL LETTER I WITH STROKE] - case '\u01CF': - // � [LATIN CAPITAL LETTER I WITH CARON] - case '\u0208': - // Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE] - case '\u020A': - // ÈŠ [LATIN CAPITAL LETTER I WITH INVERTED BREVE] - case '\u026A': - // ɪ [LATIN LETTER SMALL CAPITAL I] - case '\u1D7B': - // áµ» [LATIN SMALL CAPITAL LETTER I WITH STROKE] - case '\u1E2C': - // Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW] - case '\u1E2E': - // Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE] - case '\u1EC8': - // Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE] - case '\u1ECA': - // Ị [LATIN CAPITAL LETTER I WITH DOT BELOW] - case '\u24BE': - // â’¾ [CIRCLED LATIN CAPITAL LETTER I] - case '\uA7FE': - // ꟾ [LATIN EPIGRAPHIC LETTER I LONGA] - case '\uFF29': // Ｉ [FULLWIDTH LATIN CAPITAL LETTER I] - output[opos++] = 'I'; - break; - - case '\u00EC': - // ì [LATIN SMALL LETTER I WITH GRAVE] - case '\u00ED': - // í [LATIN SMALL LETTER I WITH ACUTE] - case '\u00EE': - // î [LATIN SMALL LETTER I WITH CIRCUMFLEX] - case '\u00EF': - // ï [LATIN SMALL LETTER I WITH DIAERESIS] - case '\u0129': - // Ä© [LATIN SMALL LETTER I WITH TILDE] - case '\u012B': - // Ä« [LATIN SMALL LETTER I WITH MACRON] - case '\u012D': - // Ä­ [LATIN SMALL LETTER I WITH BREVE] - case '\u012F': - // į [LATIN SMALL LETTER I WITH OGONEK] - case '\u0131': - // ı [LATIN SMALL LETTER DOTLESS I] - case '\u01D0': - // � [LATIN SMALL LETTER I WITH CARON] - case '\u0209': - // ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE] - case '\u020B': - // È‹ [LATIN SMALL LETTER I WITH INVERTED BREVE] - case '\u0268': - // ɨ [LATIN SMALL LETTER I WITH STROKE] - case '\u1D09': - // á´‰ [LATIN SMALL LETTER TURNED I] - case '\u1D62': - // áµ¢ [LATIN SUBSCRIPT SMALL LETTER I] - case '\u1D7C': - // áµ¼ [LATIN SMALL LETTER IOTA WITH STROKE] - case '\u1D96': - // ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK] - case '\u1E2D': - // ḭ [LATIN SMALL LETTER I WITH TILDE BELOW] - case '\u1E2F': - // ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE] - case '\u1EC9': - // ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE] - case '\u1ECB': - // ị [LATIN SMALL LETTER I WITH DOT BELOW] - case '\u2071': - // � [SUPERSCRIPT LATIN SMALL LETTER I] - case '\u24D8': - // ⓘ [CIRCLED LATIN SMALL LETTER I] - case '\uFF49': // ｉ [FULLWIDTH LATIN SMALL LETTER I] - output[opos++] = 'i'; - break; - - case '\u0132': // IJ [LATIN CAPITAL LIGATURE IJ] - output[opos++] = 'I'; - output[opos++] = 'J'; - break; - - case '\u24A4': // â’¤ [PARENTHESIZED LATIN SMALL LETTER I] - output[opos++] = '('; - output[opos++] = 'i'; - output[opos++] = ')'; - break; - - case '\u0133': // ij [LATIN SMALL LIGATURE IJ] - output[opos++] = 'i'; - output[opos++] = 'j'; - break; - - case '\u0134': - // Ä´ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX] - case '\u0248': - // Ɉ [LATIN CAPITAL LETTER J WITH STROKE] - case '\u1D0A': - // á´Š [LATIN LETTER SMALL CAPITAL J] - case '\u24BF': - // â’¿ [CIRCLED LATIN CAPITAL LETTER J] - case '\uFF2A': // Ｊ [FULLWIDTH LATIN CAPITAL LETTER J] - output[opos++] = 'J'; - break; - - case '\u0135': - // ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX] - case '\u01F0': - // Ç° [LATIN SMALL LETTER J WITH CARON] - case '\u0237': - // È· [LATIN SMALL LETTER DOTLESS J] - case '\u0249': - // ɉ [LATIN SMALL LETTER J WITH STROKE] - case '\u025F': - // ÉŸ [LATIN SMALL LETTER DOTLESS J WITH STROKE] - case '\u0284': - // Ê„ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK] - case '\u029D': - // � [LATIN SMALL LETTER J WITH CROSSED-TAIL] - case '\u24D9': - // â“™ [CIRCLED LATIN SMALL LETTER J] - case '\u2C7C': - // â±¼ [LATIN SUBSCRIPT SMALL LETTER J] - case '\uFF4A': // ｊ [FULLWIDTH LATIN SMALL LETTER J] - output[opos++] = 'j'; - break; - - case '\u24A5': // â’¥ [PARENTHESIZED LATIN SMALL LETTER J] - output[opos++] = '('; - output[opos++] = 'j'; - output[opos++] = ')'; - break; - - case '\u0136': - // Ķ [LATIN CAPITAL LETTER K WITH CEDILLA] - case '\u0198': - // Ƙ [LATIN CAPITAL LETTER K WITH HOOK] - case '\u01E8': - // Ǩ [LATIN CAPITAL LETTER K WITH CARON] - case '\u1D0B': - // á´‹ [LATIN LETTER SMALL CAPITAL K] - case '\u1E30': - // Ḱ [LATIN CAPITAL LETTER K WITH ACUTE] - case '\u1E32': - // Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW] - case '\u1E34': - // Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW] - case '\u24C0': - // â“€ [CIRCLED LATIN CAPITAL LETTER K] - case '\u2C69': - // Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER] - case '\uA740': - // � [LATIN CAPITAL LETTER K WITH STROKE] - case '\uA742': - // � [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE] - case '\uA744': - // � [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE] - case '\uFF2B': // Ｋ [FULLWIDTH LATIN CAPITAL LETTER K] - output[opos++] = 'K'; - break; - - case '\u0137': - // Ä· [LATIN SMALL LETTER K WITH CEDILLA] - case '\u0199': - // Æ™ [LATIN SMALL LETTER K WITH HOOK] - case '\u01E9': - // Ç© [LATIN SMALL LETTER K WITH CARON] - case '\u029E': - // Êž [LATIN SMALL LETTER TURNED K] - case '\u1D84': - // ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK] - case '\u1E31': - // ḱ [LATIN SMALL LETTER K WITH ACUTE] - case '\u1E33': - // ḳ [LATIN SMALL LETTER K WITH DOT BELOW] - case '\u1E35': - // ḵ [LATIN SMALL LETTER K WITH LINE BELOW] - case '\u24DA': - // â“š [CIRCLED LATIN SMALL LETTER K] - case '\u2C6A': - // ⱪ [LATIN SMALL LETTER K WITH DESCENDER] - case '\uA741': - // � [LATIN SMALL LETTER K WITH STROKE] - case '\uA743': - // � [LATIN SMALL LETTER K WITH DIAGONAL STROKE] - case '\uA745': - // � [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE] - case '\uFF4B': // ｋ [FULLWIDTH LATIN SMALL LETTER K] - output[opos++] = 'k'; - break; - - case '\u24A6': // â’¦ [PARENTHESIZED LATIN SMALL LETTER K] - output[opos++] = '('; - output[opos++] = 'k'; - output[opos++] = ')'; - break; - - case '\u0139': - // Ĺ [LATIN CAPITAL LETTER L WITH ACUTE] - case '\u013B': - // Ä» [LATIN CAPITAL LETTER L WITH CEDILLA] - case '\u013D': - // Ľ [LATIN CAPITAL LETTER L WITH CARON] - case '\u013F': - // Ä¿ [LATIN CAPITAL LETTER L WITH MIDDLE DOT] - case '\u0141': - // � [LATIN CAPITAL LETTER L WITH STROKE] - case '\u023D': - // Ƚ [LATIN CAPITAL LETTER L WITH BAR] - case '\u029F': - // ÊŸ [LATIN LETTER SMALL CAPITAL L] - case '\u1D0C': - // á´Œ [LATIN LETTER SMALL CAPITAL L WITH STROKE] - case '\u1E36': - // Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW] - case '\u1E38': - // Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON] - case '\u1E3A': - // Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW] - case '\u1E3C': - // Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW] - case '\u24C1': - // � [CIRCLED LATIN CAPITAL LETTER L] - case '\u2C60': - // â±  [LATIN CAPITAL LETTER L WITH DOUBLE BAR] - case '\u2C62': - // â±¢ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE] - case '\uA746': - // � [LATIN CAPITAL LETTER BROKEN L] - case '\uA748': - // � [LATIN CAPITAL LETTER L WITH HIGH STROKE] - case '\uA780': - // Ꞁ [LATIN CAPITAL LETTER TURNED L] - case '\uFF2C': // Ｌ [FULLWIDTH LATIN CAPITAL LETTER L] - output[opos++] = 'L'; - break; - - case '\u013A': - // ĺ [LATIN SMALL LETTER L WITH ACUTE] - case '\u013C': - // ļ [LATIN SMALL LETTER L WITH CEDILLA] - case '\u013E': - // ľ [LATIN SMALL LETTER L WITH CARON] - case '\u0140': - // Å€ [LATIN SMALL LETTER L WITH MIDDLE DOT] - case '\u0142': - // Å‚ [LATIN SMALL LETTER L WITH STROKE] - case '\u019A': - // Æš [LATIN SMALL LETTER L WITH BAR] - case '\u0234': - // È´ [LATIN SMALL LETTER L WITH CURL] - case '\u026B': - // É« [LATIN SMALL LETTER L WITH MIDDLE TILDE] - case '\u026C': - // ɬ [LATIN SMALL LETTER L WITH BELT] - case '\u026D': - // É­ [LATIN SMALL LETTER L WITH RETROFLEX HOOK] - case '\u1D85': - // ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK] - case '\u1E37': - // ḷ [LATIN SMALL LETTER L WITH DOT BELOW] - case '\u1E39': - // ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON] - case '\u1E3B': - // ḻ [LATIN SMALL LETTER L WITH LINE BELOW] - case '\u1E3D': - // ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW] - case '\u24DB': - // â“› [CIRCLED LATIN SMALL LETTER L] - case '\u2C61': - // ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR] - case '\uA747': - // � [LATIN SMALL LETTER BROKEN L] - case '\uA749': - // � [LATIN SMALL LETTER L WITH HIGH STROKE] - case '\uA781': - // � [LATIN SMALL LETTER TURNED L] - case '\uFF4C': // ｌ [FULLWIDTH LATIN SMALL LETTER L] - output[opos++] = 'l'; - break; - - case '\u01C7': // LJ [LATIN CAPITAL LETTER LJ] - output[opos++] = 'L'; - output[opos++] = 'J'; - break; - - case '\u1EFA': // Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL] - output[opos++] = 'L'; - output[opos++] = 'L'; - break; - - case '\u01C8': // Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J] - output[opos++] = 'L'; - output[opos++] = 'j'; - break; - - case '\u24A7': // â’§ [PARENTHESIZED LATIN SMALL LETTER L] - output[opos++] = '('; - output[opos++] = 'l'; - output[opos++] = ')'; - break; - - case '\u01C9': // lj [LATIN SMALL LETTER LJ] - output[opos++] = 'l'; - output[opos++] = 'j'; - break; - - case '\u1EFB': // á»» [LATIN SMALL LETTER MIDDLE-WELSH LL] - output[opos++] = 'l'; - output[opos++] = 'l'; - break; - - case '\u02AA': // ʪ [LATIN SMALL LETTER LS DIGRAPH] - output[opos++] = 'l'; - output[opos++] = 's'; - break; - - case '\u02AB': // Ê« [LATIN SMALL LETTER LZ DIGRAPH] - output[opos++] = 'l'; - output[opos++] = 'z'; - break; - - case '\u019C': - // Æœ [LATIN CAPITAL LETTER TURNED M] - case '\u1D0D': - // á´� [LATIN LETTER SMALL CAPITAL M] - case '\u1E3E': - // Ḿ [LATIN CAPITAL LETTER M WITH ACUTE] - case '\u1E40': - // á¹€ [LATIN CAPITAL LETTER M WITH DOT ABOVE] - case '\u1E42': - // Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW] - case '\u24C2': - // â“‚ [CIRCLED LATIN CAPITAL LETTER M] - case '\u2C6E': - // â±® [LATIN CAPITAL LETTER M WITH HOOK] - case '\uA7FD': - // ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M] - case '\uA7FF': - // ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M] - case '\uFF2D': // ï¼­ [FULLWIDTH LATIN CAPITAL LETTER M] - output[opos++] = 'M'; - break; - - case '\u026F': - // ɯ [LATIN SMALL LETTER TURNED M] - case '\u0270': - // É° [LATIN SMALL LETTER TURNED M WITH LONG LEG] - case '\u0271': - // ɱ [LATIN SMALL LETTER M WITH HOOK] - case '\u1D6F': - // ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE] - case '\u1D86': - // ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK] - case '\u1E3F': - // ḿ [LATIN SMALL LETTER M WITH ACUTE] - case '\u1E41': - // � [LATIN SMALL LETTER M WITH DOT ABOVE] - case '\u1E43': - // ṃ [LATIN SMALL LETTER M WITH DOT BELOW] - case '\u24DC': - // â“œ [CIRCLED LATIN SMALL LETTER M] - case '\uFF4D': // � [FULLWIDTH LATIN SMALL LETTER M] - output[opos++] = 'm'; - break; - - case '\u24A8': // â’¨ [PARENTHESIZED LATIN SMALL LETTER M] - output[opos++] = '('; - output[opos++] = 'm'; - output[opos++] = ')'; - break; - - case '\u00D1': - // Ñ [LATIN CAPITAL LETTER N WITH TILDE] - case '\u0143': - // Ã…Æ’ [LATIN CAPITAL LETTER N WITH ACUTE] - case '\u0145': - // Å… [LATIN CAPITAL LETTER N WITH CEDILLA] - case '\u0147': - // Ň [LATIN CAPITAL LETTER N WITH CARON] - case '\u014A': - // Ã…Å  http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG] - case '\u019D': - // � [LATIN CAPITAL LETTER N WITH LEFT HOOK] - case '\u01F8': - // Ǹ [LATIN CAPITAL LETTER N WITH GRAVE] - case '\u0220': - // È  [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG] - case '\u0274': - // É´ [LATIN LETTER SMALL CAPITAL N] - case '\u1D0E': - // á´Ž [LATIN LETTER SMALL CAPITAL REVERSED N] - case '\u1E44': - // Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE] - case '\u1E46': - // Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW] - case '\u1E48': - // Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW] - case '\u1E4A': - // Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW] - case '\u24C3': - // Ⓝ [CIRCLED LATIN CAPITAL LETTER N] - case '\uFF2E': // ï¼® [FULLWIDTH LATIN CAPITAL LETTER N] - output[opos++] = 'N'; - break; - - case '\u00F1': - // ñ [LATIN SMALL LETTER N WITH TILDE] - case '\u0144': - // Å„ [LATIN SMALL LETTER N WITH ACUTE] - case '\u0146': - // ņ [LATIN SMALL LETTER N WITH CEDILLA] - case '\u0148': - // ň [LATIN SMALL LETTER N WITH CARON] - case '\u0149': - // ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE] - case '\u014B': - // Å‹ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG] - case '\u019E': - // Æž [LATIN SMALL LETTER N WITH LONG RIGHT LEG] - case '\u01F9': - // ǹ [LATIN SMALL LETTER N WITH GRAVE] - case '\u0235': - // ȵ [LATIN SMALL LETTER N WITH CURL] - case '\u0272': - // ɲ [LATIN SMALL LETTER N WITH LEFT HOOK] - case '\u0273': - // ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK] - case '\u1D70': - // áµ° [LATIN SMALL LETTER N WITH MIDDLE TILDE] - case '\u1D87': - // ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK] - case '\u1E45': - // á¹… [LATIN SMALL LETTER N WITH DOT ABOVE] - case '\u1E47': - // ṇ [LATIN SMALL LETTER N WITH DOT BELOW] - case '\u1E49': - // ṉ [LATIN SMALL LETTER N WITH LINE BELOW] - case '\u1E4B': - // ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW] - case '\u207F': - // � [SUPERSCRIPT LATIN SMALL LETTER N] - case '\u24DD': - // � [CIRCLED LATIN SMALL LETTER N] - case '\uFF4E': // ｎ [FULLWIDTH LATIN SMALL LETTER N] - output[opos++] = 'n'; - break; - - case '\u01CA': // ÇŠ [LATIN CAPITAL LETTER NJ] - output[opos++] = 'N'; - output[opos++] = 'J'; - break; - - case '\u01CB': // Ç‹ [LATIN CAPITAL LETTER N WITH SMALL LETTER J] - output[opos++] = 'N'; - output[opos++] = 'j'; - break; - - case '\u24A9': // â’© [PARENTHESIZED LATIN SMALL LETTER N] - output[opos++] = '('; - output[opos++] = 'n'; - output[opos++] = ')'; - break; - - case '\u01CC': // ÇŒ [LATIN SMALL LETTER NJ] - output[opos++] = 'n'; - output[opos++] = 'j'; - break; - - case '\u00D2': - // Ã’ [LATIN CAPITAL LETTER O WITH GRAVE] - case '\u00D3': - // Ó [LATIN CAPITAL LETTER O WITH ACUTE] - case '\u00D4': - // �? [LATIN CAPITAL LETTER O WITH CIRCUMFLEX] - case '\u00D5': - // Õ [LATIN CAPITAL LETTER O WITH TILDE] - case '\u00D6': - // Ö [LATIN CAPITAL LETTER O WITH DIAERESIS] - case '\u00D8': - // Ø [LATIN CAPITAL LETTER O WITH STROKE] - case '\u014C': - // Ã…Å’ [LATIN CAPITAL LETTER O WITH MACRON] - case '\u014E': - // ÅŽ [LATIN CAPITAL LETTER O WITH BREVE] - case '\u0150': - // � [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE] - case '\u0186': - // Ɔ [LATIN CAPITAL LETTER OPEN O] - case '\u019F': - // ÆŸ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE] - case '\u01A0': - // Æ  [LATIN CAPITAL LETTER O WITH HORN] - case '\u01D1': - // Ç‘ [LATIN CAPITAL LETTER O WITH CARON] - case '\u01EA': - // Ǫ [LATIN CAPITAL LETTER O WITH OGONEK] - case '\u01EC': - // Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON] - case '\u01FE': - // Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE] - case '\u020C': - // ÈŒ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE] - case '\u020E': - // ÈŽ [LATIN CAPITAL LETTER O WITH INVERTED BREVE] - case '\u022A': - // Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON] - case '\u022C': - // Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON] - case '\u022E': - // È® [LATIN CAPITAL LETTER O WITH DOT ABOVE] - case '\u0230': - // È° [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON] - case '\u1D0F': - // á´� [LATIN LETTER SMALL CAPITAL O] - case '\u1D10': - // á´� [LATIN LETTER SMALL CAPITAL OPEN O] - case '\u1E4C': - // Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE] - case '\u1E4E': - // Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS] - case '\u1E50': - // � [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE] - case '\u1E52': - // á¹’ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE] - case '\u1ECC': - // Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW] - case '\u1ECE': - // Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE] - case '\u1ED0': - // � [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE] - case '\u1ED2': - // á»’ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE] - case '\u1ED4': - // �? [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1ED6': - // á»– [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE] - case '\u1ED8': - // Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW] - case '\u1EDA': - // Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE] - case '\u1EDC': - // Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE] - case '\u1EDE': - // Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE] - case '\u1EE0': - // á»  [LATIN CAPITAL LETTER O WITH HORN AND TILDE] - case '\u1EE2': - // Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW] - case '\u24C4': - // â“„ [CIRCLED LATIN CAPITAL LETTER O] - case '\uA74A': - // � [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY] - case '\uA74C': - // � [LATIN CAPITAL LETTER O WITH LOOP] - case '\uFF2F': // Ｏ [FULLWIDTH LATIN CAPITAL LETTER O] - output[opos++] = 'O'; - break; - - case '\u00F2': - // ò [LATIN SMALL LETTER O WITH GRAVE] - case '\u00F3': - // ó [LATIN SMALL LETTER O WITH ACUTE] - case '\u00F4': - // ô [LATIN SMALL LETTER O WITH CIRCUMFLEX] - case '\u00F5': - // õ [LATIN SMALL LETTER O WITH TILDE] - case '\u00F6': - // ö [LATIN SMALL LETTER O WITH DIAERESIS] - case '\u00F8': - // ø [LATIN SMALL LETTER O WITH STROKE] - case '\u014D': - // � [LATIN SMALL LETTER O WITH MACRON] - case '\u014F': - // � [LATIN SMALL LETTER O WITH BREVE] - case '\u0151': - // Å‘ [LATIN SMALL LETTER O WITH DOUBLE ACUTE] - case '\u01A1': - // Æ¡ [LATIN SMALL LETTER O WITH HORN] - case '\u01D2': - // Ç’ [LATIN SMALL LETTER O WITH CARON] - case '\u01EB': - // Ç« [LATIN SMALL LETTER O WITH OGONEK] - case '\u01ED': - // Ç­ [LATIN SMALL LETTER O WITH OGONEK AND MACRON] - case '\u01FF': - // Ç¿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE] - case '\u020D': - // � [LATIN SMALL LETTER O WITH DOUBLE GRAVE] - case '\u020F': - // � [LATIN SMALL LETTER O WITH INVERTED BREVE] - case '\u022B': - // È« [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON] - case '\u022D': - // È­ [LATIN SMALL LETTER O WITH TILDE AND MACRON] - case '\u022F': - // ȯ [LATIN SMALL LETTER O WITH DOT ABOVE] - case '\u0231': - // ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON] - case '\u0254': - // �? [LATIN SMALL LETTER OPEN O] - case '\u0275': - // ɵ [LATIN SMALL LETTER BARRED O] - case '\u1D16': - // á´– [LATIN SMALL LETTER TOP HALF O] - case '\u1D17': - // á´— [LATIN SMALL LETTER BOTTOM HALF O] - case '\u1D97': - // ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK] - case '\u1E4D': - // � [LATIN SMALL LETTER O WITH TILDE AND ACUTE] - case '\u1E4F': - // � [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS] - case '\u1E51': - // ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE] - case '\u1E53': - // ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE] - case '\u1ECD': - // � [LATIN SMALL LETTER O WITH DOT BELOW] - case '\u1ECF': - // � [LATIN SMALL LETTER O WITH HOOK ABOVE] - case '\u1ED1': - // ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE] - case '\u1ED3': - // ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE] - case '\u1ED5': - // ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] - case '\u1ED7': - // á»— [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE] - case '\u1ED9': - // á»™ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW] - case '\u1EDB': - // á»› [LATIN SMALL LETTER O WITH HORN AND ACUTE] - case '\u1EDD': - // � [LATIN SMALL LETTER O WITH HORN AND GRAVE] - case '\u1EDF': - // ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE] - case '\u1EE1': - // ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE] - case '\u1EE3': - // ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW] - case '\u2092': - // â‚’ [LATIN SUBSCRIPT SMALL LETTER O] - case '\u24DE': - // â“ž [CIRCLED LATIN SMALL LETTER O] - case '\u2C7A': - // ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE] - case '\uA74B': - // � [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY] - case '\uA74D': - // � [LATIN SMALL LETTER O WITH LOOP] - case '\uFF4F': // � [FULLWIDTH LATIN SMALL LETTER O] - output[opos++] = 'o'; - break; - - case '\u0152': - // Å’ [LATIN CAPITAL LIGATURE OE] - case '\u0276': // ɶ [LATIN LETTER SMALL CAPITAL OE] - output[opos++] = 'O'; - output[opos++] = 'E'; - break; - - case '\uA74E': // � [LATIN CAPITAL LETTER OO] - output[opos++] = 'O'; - output[opos++] = 'O'; - break; - - case '\u0222': - // È¢ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU] - case '\u1D15': // á´• [LATIN LETTER SMALL CAPITAL OU] - output[opos++] = 'O'; - output[opos++] = 'U'; - break; - - case '\u24AA': // â’ª [PARENTHESIZED LATIN SMALL LETTER O] - output[opos++] = '('; - output[opos++] = 'o'; - output[opos++] = ')'; - break; - - case '\u0153': - // Å“ [LATIN SMALL LIGATURE OE] - case '\u1D14': // á´�? [LATIN SMALL LETTER TURNED OE] - output[opos++] = 'o'; - output[opos++] = 'e'; - break; - - case '\uA74F': // � [LATIN SMALL LETTER OO] - output[opos++] = 'o'; - output[opos++] = 'o'; - break; - - case '\u0223': // È£ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU] - output[opos++] = 'o'; - output[opos++] = 'u'; - break; - - case '\u01A4': - // Ƥ [LATIN CAPITAL LETTER P WITH HOOK] - case '\u1D18': - // á´˜ [LATIN LETTER SMALL CAPITAL P] - case '\u1E54': - // �? [LATIN CAPITAL LETTER P WITH ACUTE] - case '\u1E56': - // á¹– [LATIN CAPITAL LETTER P WITH DOT ABOVE] - case '\u24C5': - // â“… [CIRCLED LATIN CAPITAL LETTER P] - case '\u2C63': - // â±£ [LATIN CAPITAL LETTER P WITH STROKE] - case '\uA750': - // � [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER] - case '\uA752': - // � [LATIN CAPITAL LETTER P WITH FLOURISH] - case '\uA754': - // �? [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL] - case '\uFF30': // ï¼° [FULLWIDTH LATIN CAPITAL LETTER P] - output[opos++] = 'P'; - break; - - case '\u01A5': - // Æ¥ [LATIN SMALL LETTER P WITH HOOK] - case '\u1D71': - // áµ± [LATIN SMALL LETTER P WITH MIDDLE TILDE] - case '\u1D7D': - // áµ½ [LATIN SMALL LETTER P WITH STROKE] - case '\u1D88': - // ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK] - case '\u1E55': - // ṕ [LATIN SMALL LETTER P WITH ACUTE] - case '\u1E57': - // á¹— [LATIN SMALL LETTER P WITH DOT ABOVE] - case '\u24DF': - // â“Ÿ [CIRCLED LATIN SMALL LETTER P] - case '\uA751': - // � [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER] - case '\uA753': - // � [LATIN SMALL LETTER P WITH FLOURISH] - case '\uA755': - // � [LATIN SMALL LETTER P WITH SQUIRREL TAIL] - case '\uA7FC': - // ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P] - case '\uFF50': // � [FULLWIDTH LATIN SMALL LETTER P] - output[opos++] = 'p'; - break; - - case '\u24AB': // â’« [PARENTHESIZED LATIN SMALL LETTER P] - output[opos++] = '('; - output[opos++] = 'p'; - output[opos++] = ')'; - break; - - case '\u024A': - // ÉŠ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL] - case '\u24C6': - // Ⓠ [CIRCLED LATIN CAPITAL LETTER Q] - case '\uA756': - // � [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER] - case '\uA758': - // � [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE] - case '\uFF31': // ï¼± [FULLWIDTH LATIN CAPITAL LETTER Q] - output[opos++] = 'Q'; - break; - - case '\u0138': - // ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA] - case '\u024B': - // É‹ [LATIN SMALL LETTER Q WITH HOOK TAIL] - case '\u02A0': - // Ê  [LATIN SMALL LETTER Q WITH HOOK] - case '\u24E0': - // â“  [CIRCLED LATIN SMALL LETTER Q] - case '\uA757': - // � [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER] - case '\uA759': - // � [LATIN SMALL LETTER Q WITH DIAGONAL STROKE] - case '\uFF51': // ｑ [FULLWIDTH LATIN SMALL LETTER Q] - output[opos++] = 'q'; - break; - - case '\u24AC': // â’¬ [PARENTHESIZED LATIN SMALL LETTER Q] - output[opos++] = '('; - output[opos++] = 'q'; - output[opos++] = ')'; - break; - - case '\u0239': // ȹ [LATIN SMALL LETTER QP DIGRAPH] - output[opos++] = 'q'; - output[opos++] = 'p'; - break; - - case '\u0154': - // �? [LATIN CAPITAL LETTER R WITH ACUTE] - case '\u0156': - // Å– [LATIN CAPITAL LETTER R WITH CEDILLA] - case '\u0158': - // Ã…Ëœ [LATIN CAPITAL LETTER R WITH CARON] - case '\u0210': - // È’ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE] - case '\u0212': - // È’ [LATIN CAPITAL LETTER R WITH INVERTED BREVE] - case '\u024C': - // ÉŒ [LATIN CAPITAL LETTER R WITH STROKE] - case '\u0280': - // Ê€ [LATIN LETTER SMALL CAPITAL R] - case '\u0281': - // � [LATIN LETTER SMALL CAPITAL INVERTED R] - case '\u1D19': - // á´™ [LATIN LETTER SMALL CAPITAL REVERSED R] - case '\u1D1A': - // á´š [LATIN LETTER SMALL CAPITAL TURNED R] - case '\u1E58': - // Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE] - case '\u1E5A': - // Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW] - case '\u1E5C': - // Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON] - case '\u1E5E': - // Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW] - case '\u24C7': - // Ⓡ [CIRCLED LATIN CAPITAL LETTER R] - case '\u2C64': - // Ɽ [LATIN CAPITAL LETTER R WITH TAIL] - case '\uA75A': - // � [LATIN CAPITAL LETTER R ROTUNDA] - case '\uA782': - // êž‚ [LATIN CAPITAL LETTER INSULAR R] - case '\uFF32': // ï¼² [FULLWIDTH LATIN CAPITAL LETTER R] - output[opos++] = 'R'; - break; - - case '\u0155': - // Å• [LATIN SMALL LETTER R WITH ACUTE] - case '\u0157': - // Å— [LATIN SMALL LETTER R WITH CEDILLA] - case '\u0159': - // Ã…â„¢ [LATIN SMALL LETTER R WITH CARON] - case '\u0211': - // È‘ [LATIN SMALL LETTER R WITH DOUBLE GRAVE] - case '\u0213': - // È“ [LATIN SMALL LETTER R WITH INVERTED BREVE] - case '\u024D': - // � [LATIN SMALL LETTER R WITH STROKE] - case '\u027C': - // ɼ [LATIN SMALL LETTER R WITH LONG LEG] - case '\u027D': - // ɽ [LATIN SMALL LETTER R WITH TAIL] - case '\u027E': - // ɾ [LATIN SMALL LETTER R WITH FISHHOOK] - case '\u027F': - // É¿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK] - case '\u1D63': - // áµ£ [LATIN SUBSCRIPT SMALL LETTER R] - case '\u1D72': - // áµ² [LATIN SMALL LETTER R WITH MIDDLE TILDE] - case '\u1D73': - // áµ³ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE] - case '\u1D89': - // ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK] - case '\u1E59': - // á¹™ [LATIN SMALL LETTER R WITH DOT ABOVE] - case '\u1E5B': - // á¹› [LATIN SMALL LETTER R WITH DOT BELOW] - case '\u1E5D': - // � [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON] - case '\u1E5F': - // ṟ [LATIN SMALL LETTER R WITH LINE BELOW] - case '\u24E1': - // â“¡ [CIRCLED LATIN SMALL LETTER R] - case '\uA75B': - // � [LATIN SMALL LETTER R ROTUNDA] - case '\uA783': - // ꞃ [LATIN SMALL LETTER INSULAR R] - case '\uFF52': // ï½’ [FULLWIDTH LATIN SMALL LETTER R] - output[opos++] = 'r'; - break; - - case '\u24AD': // â’­ [PARENTHESIZED LATIN SMALL LETTER R] - output[opos++] = '('; - output[opos++] = 'r'; - output[opos++] = ')'; - break; - - case '\u015A': - // Ã…Å¡ [LATIN CAPITAL LETTER S WITH ACUTE] - case '\u015C': - // Ã…Å“ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX] - case '\u015E': - // Åž [LATIN CAPITAL LETTER S WITH CEDILLA] - case '\u0160': - // Å  [LATIN CAPITAL LETTER S WITH CARON] - case '\u0218': - // Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW] - case '\u1E60': - // á¹  [LATIN CAPITAL LETTER S WITH DOT ABOVE] - case '\u1E62': - // á¹¢ [LATIN CAPITAL LETTER S WITH DOT BELOW] - case '\u1E64': - // Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE] - case '\u1E66': - // Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE] - case '\u1E68': - // Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE] - case '\u24C8': - // Ⓢ [CIRCLED LATIN CAPITAL LETTER S] - case '\uA731': - // ꜱ [LATIN LETTER SMALL CAPITAL S] - case '\uA785': - // êž… [LATIN SMALL LETTER INSULAR S] - case '\uFF33': // ï¼³ [FULLWIDTH LATIN CAPITAL LETTER S] - output[opos++] = 'S'; - break; - - case '\u015B': - // Å› [LATIN SMALL LETTER S WITH ACUTE] - case '\u015D': - // � [LATIN SMALL LETTER S WITH CIRCUMFLEX] - case '\u015F': - // ÅŸ [LATIN SMALL LETTER S WITH CEDILLA] - case '\u0161': - // Å¡ [LATIN SMALL LETTER S WITH CARON] - case '\u017F': - // Å¿ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S] - case '\u0219': - // È™ [LATIN SMALL LETTER S WITH COMMA BELOW] - case '\u023F': - // È¿ [LATIN SMALL LETTER S WITH SWASH TAIL] - case '\u0282': - // Ê‚ [LATIN SMALL LETTER S WITH HOOK] - case '\u1D74': - // áµ´ [LATIN SMALL LETTER S WITH MIDDLE TILDE] - case '\u1D8A': - // ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK] - case '\u1E61': - // ṡ [LATIN SMALL LETTER S WITH DOT ABOVE] - case '\u1E63': - // á¹£ [LATIN SMALL LETTER S WITH DOT BELOW] - case '\u1E65': - // á¹¥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE] - case '\u1E67': - // ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE] - case '\u1E69': - // ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE] - case '\u1E9C': - // ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE] - case '\u1E9D': - // � [LATIN SMALL LETTER LONG S WITH HIGH STROKE] - case '\u24E2': - // â“¢ [CIRCLED LATIN SMALL LETTER S] - case '\uA784': - // êž„ [LATIN CAPITAL LETTER INSULAR S] - case '\uFF53': // ｓ [FULLWIDTH LATIN SMALL LETTER S] - output[opos++] = 's'; - break; - - case '\u1E9E': // ẞ [LATIN CAPITAL LETTER SHARP S] - output[opos++] = 'S'; - output[opos++] = 'S'; - break; - - case '\u24AE': // â’® [PARENTHESIZED LATIN SMALL LETTER S] - output[opos++] = '('; - output[opos++] = 's'; - output[opos++] = ')'; - break; - - case '\u00DF': // ß [LATIN SMALL LETTER SHARP S] - output[opos++] = 's'; - output[opos++] = 's'; - break; - - case '\uFB06': // st [LATIN SMALL LIGATURE ST] - output[opos++] = 's'; - output[opos++] = 't'; - break; - - case '\u0162': - // Å¢ [LATIN CAPITAL LETTER T WITH CEDILLA] - case '\u0164': - // Ť [LATIN CAPITAL LETTER T WITH CARON] - case '\u0166': - // Ŧ [LATIN CAPITAL LETTER T WITH STROKE] - case '\u01AC': - // Ƭ [LATIN CAPITAL LETTER T WITH HOOK] - case '\u01AE': - // Æ® [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK] - case '\u021A': - // Èš [LATIN CAPITAL LETTER T WITH COMMA BELOW] - case '\u023E': - // Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE] - case '\u1D1B': - // á´› [LATIN LETTER SMALL CAPITAL T] - case '\u1E6A': - // Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE] - case '\u1E6C': - // Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW] - case '\u1E6E': - // á¹® [LATIN CAPITAL LETTER T WITH LINE BELOW] - case '\u1E70': - // á¹° [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW] - case '\u24C9': - // Ⓣ [CIRCLED LATIN CAPITAL LETTER T] - case '\uA786': - // Ꞇ [LATIN CAPITAL LETTER INSULAR T] - case '\uFF34': // ï¼´ [FULLWIDTH LATIN CAPITAL LETTER T] - output[opos++] = 'T'; - break; - - case '\u0163': - // Å£ [LATIN SMALL LETTER T WITH CEDILLA] - case '\u0165': - // Ã…Â¥ [LATIN SMALL LETTER T WITH CARON] - case '\u0167': - // ŧ [LATIN SMALL LETTER T WITH STROKE] - case '\u01AB': - // Æ« [LATIN SMALL LETTER T WITH PALATAL HOOK] - case '\u01AD': - // Æ­ [LATIN SMALL LETTER T WITH HOOK] - case '\u021B': - // È› [LATIN SMALL LETTER T WITH COMMA BELOW] - case '\u0236': - // ȶ [LATIN SMALL LETTER T WITH CURL] - case '\u0287': - // ʇ [LATIN SMALL LETTER TURNED T] - case '\u0288': - // ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK] - case '\u1D75': - // áµµ [LATIN SMALL LETTER T WITH MIDDLE TILDE] - case '\u1E6B': - // ṫ [LATIN SMALL LETTER T WITH DOT ABOVE] - case '\u1E6D': - // á¹­ [LATIN SMALL LETTER T WITH DOT BELOW] - case '\u1E6F': - // ṯ [LATIN SMALL LETTER T WITH LINE BELOW] - case '\u1E71': - // á¹± [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW] - case '\u1E97': - // ẗ [LATIN SMALL LETTER T WITH DIAERESIS] - case '\u24E3': - // â“£ [CIRCLED LATIN SMALL LETTER T] - case '\u2C66': - // ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE] - case '\uFF54': // �? [FULLWIDTH LATIN SMALL LETTER T] - output[opos++] = 't'; - break; - - case '\u00DE': - // Þ [LATIN CAPITAL LETTER THORN] - case '\uA766': // � [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER] - output[opos++] = 'T'; - output[opos++] = 'H'; - break; - - case '\uA728': // Ꜩ [LATIN CAPITAL LETTER TZ] - output[opos++] = 'T'; - output[opos++] = 'Z'; - break; - - case '\u24AF': // â’¯ [PARENTHESIZED LATIN SMALL LETTER T] - output[opos++] = '('; - output[opos++] = 't'; - output[opos++] = ')'; - break; - - case '\u02A8': // ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL] - output[opos++] = 't'; - output[opos++] = 'c'; - break; - - case '\u00FE': - // þ [LATIN SMALL LETTER THORN] - case '\u1D7A': - // ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH] - case '\uA767': // � [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER] - output[opos++] = 't'; - output[opos++] = 'h'; - break; - - case '\u02A6': // ʦ [LATIN SMALL LETTER TS DIGRAPH] - output[opos++] = 't'; - output[opos++] = 's'; - break; - - case '\uA729': // ꜩ [LATIN SMALL LETTER TZ] - output[opos++] = 't'; - output[opos++] = 'z'; - break; - - case '\u00D9': - // Ù [LATIN CAPITAL LETTER U WITH GRAVE] - case '\u00DA': - // Ú [LATIN CAPITAL LETTER U WITH ACUTE] - case '\u00DB': - // Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX] - case '\u00DC': - // Ãœ [LATIN CAPITAL LETTER U WITH DIAERESIS] - case '\u0168': - // Ũ [LATIN CAPITAL LETTER U WITH TILDE] - case '\u016A': - // Ū [LATIN CAPITAL LETTER U WITH MACRON] - case '\u016C': - // Ŭ [LATIN CAPITAL LETTER U WITH BREVE] - case '\u016E': - // Å® [LATIN CAPITAL LETTER U WITH RING ABOVE] - case '\u0170': - // Å° [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE] - case '\u0172': - // Ų [LATIN CAPITAL LETTER U WITH OGONEK] - case '\u01AF': - // Ư [LATIN CAPITAL LETTER U WITH HORN] - case '\u01D3': - // Ç“ [LATIN CAPITAL LETTER U WITH CARON] - case '\u01D5': - // Ç• [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON] - case '\u01D7': - // Ç— [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE] - case '\u01D9': - // Ç™ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON] - case '\u01DB': - // Ç› [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE] - case '\u0214': - // �? [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE] - case '\u0216': - // È– [LATIN CAPITAL LETTER U WITH INVERTED BREVE] - case '\u0244': - // É„ [LATIN CAPITAL LETTER U BAR] - case '\u1D1C': - // á´œ [LATIN LETTER SMALL CAPITAL U] - case '\u1D7E': - // áµ¾ [LATIN SMALL CAPITAL LETTER U WITH STROKE] - case '\u1E72': - // á¹² [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW] - case '\u1E74': - // á¹´ [LATIN CAPITAL LETTER U WITH TILDE BELOW] - case '\u1E76': - // Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW] - case '\u1E78': - // Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE] - case '\u1E7A': - // Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS] - case '\u1EE4': - // Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW] - case '\u1EE6': - // Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE] - case '\u1EE8': - // Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE] - case '\u1EEA': - // Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE] - case '\u1EEC': - // Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE] - case '\u1EEE': - // á»® [LATIN CAPITAL LETTER U WITH HORN AND TILDE] - case '\u1EF0': - // á»° [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW] - case '\u24CA': - // â“Š [CIRCLED LATIN CAPITAL LETTER U] - case '\uFF35': // ï¼µ [FULLWIDTH LATIN CAPITAL LETTER U] - output[opos++] = 'U'; - break; - - case '\u00F9': - // ù [LATIN SMALL LETTER U WITH GRAVE] - case '\u00FA': - // ú [LATIN SMALL LETTER U WITH ACUTE] - case '\u00FB': - // û [LATIN SMALL LETTER U WITH CIRCUMFLEX] - case '\u00FC': - // ü [LATIN SMALL LETTER U WITH DIAERESIS] - case '\u0169': - // Å© [LATIN SMALL LETTER U WITH TILDE] - case '\u016B': - // Å« [LATIN SMALL LETTER U WITH MACRON] - case '\u016D': - // Å­ [LATIN SMALL LETTER U WITH BREVE] - case '\u016F': - // ů [LATIN SMALL LETTER U WITH RING ABOVE] - case '\u0171': - // ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE] - case '\u0173': - // ų [LATIN SMALL LETTER U WITH OGONEK] - case '\u01B0': - // Æ° [LATIN SMALL LETTER U WITH HORN] - case '\u01D4': - // �? [LATIN SMALL LETTER U WITH CARON] - case '\u01D6': - // Ç– [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON] - case '\u01D8': - // ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE] - case '\u01DA': - // Çš [LATIN SMALL LETTER U WITH DIAERESIS AND CARON] - case '\u01DC': - // Çœ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE] - case '\u0215': - // È• [LATIN SMALL LETTER U WITH DOUBLE GRAVE] - case '\u0217': - // È— [LATIN SMALL LETTER U WITH INVERTED BREVE] - case '\u0289': - // ʉ [LATIN SMALL LETTER U BAR] - case '\u1D64': - // ᵤ [LATIN SUBSCRIPT SMALL LETTER U] - case '\u1D99': - // ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK] - case '\u1E73': - // á¹³ [LATIN SMALL LETTER U WITH DIAERESIS BELOW] - case '\u1E75': - // á¹µ [LATIN SMALL LETTER U WITH TILDE BELOW] - case '\u1E77': - // á¹· [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW] - case '\u1E79': - // á¹¹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE] - case '\u1E7B': - // á¹» [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS] - case '\u1EE5': - // ụ [LATIN SMALL LETTER U WITH DOT BELOW] - case '\u1EE7': - // ủ [LATIN SMALL LETTER U WITH HOOK ABOVE] - case '\u1EE9': - // ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE] - case '\u1EEB': - // ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE] - case '\u1EED': - // á»­ [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE] - case '\u1EEF': - // ữ [LATIN SMALL LETTER U WITH HORN AND TILDE] - case '\u1EF1': - // á»± [LATIN SMALL LETTER U WITH HORN AND DOT BELOW] - case '\u24E4': - // ⓤ [CIRCLED LATIN SMALL LETTER U] - case '\uFF55': // ｕ [FULLWIDTH LATIN SMALL LETTER U] - output[opos++] = 'u'; - break; - - case '\u24B0': // â’° [PARENTHESIZED LATIN SMALL LETTER U] - output[opos++] = '('; - output[opos++] = 'u'; - output[opos++] = ')'; - break; - - case '\u1D6B': // ᵫ [LATIN SMALL LETTER UE] - output[opos++] = 'u'; - output[opos++] = 'e'; - break; - - case '\u01B2': - // Ʋ [LATIN CAPITAL LETTER V WITH HOOK] - case '\u0245': - // É… [LATIN CAPITAL LETTER TURNED V] - case '\u1D20': - // á´  [LATIN LETTER SMALL CAPITAL V] - case '\u1E7C': - // á¹¼ [LATIN CAPITAL LETTER V WITH TILDE] - case '\u1E7E': - // á¹¾ [LATIN CAPITAL LETTER V WITH DOT BELOW] - case '\u1EFC': - // Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V] - case '\u24CB': - // â“‹ [CIRCLED LATIN CAPITAL LETTER V] - case '\uA75E': - // � [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE] - case '\uA768': - // � [LATIN CAPITAL LETTER VEND] - case '\uFF36': // Ｖ [FULLWIDTH LATIN CAPITAL LETTER V] - output[opos++] = 'V'; - break; - - case '\u028B': - // Ê‹ [LATIN SMALL LETTER V WITH HOOK] - case '\u028C': - // ÊŒ [LATIN SMALL LETTER TURNED V] - case '\u1D65': - // áµ¥ [LATIN SUBSCRIPT SMALL LETTER V] - case '\u1D8C': - // ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK] - case '\u1E7D': - // á¹½ [LATIN SMALL LETTER V WITH TILDE] - case '\u1E7F': - // ṿ [LATIN SMALL LETTER V WITH DOT BELOW] - case '\u24E5': - // â“¥ [CIRCLED LATIN SMALL LETTER V] - case '\u2C71': - // â±± [LATIN SMALL LETTER V WITH RIGHT HOOK] - case '\u2C74': - // â±´ [LATIN SMALL LETTER V WITH CURL] - case '\uA75F': - // � [LATIN SMALL LETTER V WITH DIAGONAL STROKE] - case '\uFF56': // ï½– [FULLWIDTH LATIN SMALL LETTER V] - output[opos++] = 'v'; - break; - - case '\uA760': // � [LATIN CAPITAL LETTER VY] - output[opos++] = 'V'; - output[opos++] = 'Y'; - break; - - case '\u24B1': // â’± [PARENTHESIZED LATIN SMALL LETTER V] - output[opos++] = '('; - output[opos++] = 'v'; - output[opos++] = ')'; - break; - - case '\uA761': // � [LATIN SMALL LETTER VY] - output[opos++] = 'v'; - output[opos++] = 'y'; - break; - - case '\u0174': - // Å´ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX] - case '\u01F7': - // Ç· http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN] - case '\u1D21': - // á´¡ [LATIN LETTER SMALL CAPITAL W] - case '\u1E80': - // Ẁ [LATIN CAPITAL LETTER W WITH GRAVE] - case '\u1E82': - // Ẃ [LATIN CAPITAL LETTER W WITH ACUTE] - case '\u1E84': - // Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS] - case '\u1E86': - // Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE] - case '\u1E88': - // Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW] - case '\u24CC': - // â“Œ [CIRCLED LATIN CAPITAL LETTER W] - case '\u2C72': - // â±² [LATIN CAPITAL LETTER W WITH HOOK] - case '\uFF37': // ï¼· [FULLWIDTH LATIN CAPITAL LETTER W] - output[opos++] = 'W'; - break; - - case '\u0175': - // ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX] - case '\u01BF': - // Æ¿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN] - case '\u028D': - // � [LATIN SMALL LETTER TURNED W] - case '\u1E81': - // � [LATIN SMALL LETTER W WITH GRAVE] - case '\u1E83': - // ẃ [LATIN SMALL LETTER W WITH ACUTE] - case '\u1E85': - // ẅ [LATIN SMALL LETTER W WITH DIAERESIS] - case '\u1E87': - // ẇ [LATIN SMALL LETTER W WITH DOT ABOVE] - case '\u1E89': - // ẉ [LATIN SMALL LETTER W WITH DOT BELOW] - case '\u1E98': - // ẘ [LATIN SMALL LETTER W WITH RING ABOVE] - case '\u24E6': - // ⓦ [CIRCLED LATIN SMALL LETTER W] - case '\u2C73': - // â±³ [LATIN SMALL LETTER W WITH HOOK] - case '\uFF57': // ï½— [FULLWIDTH LATIN SMALL LETTER W] - output[opos++] = 'w'; - break; - - case '\u24B2': // â’² [PARENTHESIZED LATIN SMALL LETTER W] - output[opos++] = '('; - output[opos++] = 'w'; - output[opos++] = ')'; - break; - - case '\u1E8A': - // Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE] - case '\u1E8C': - // Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS] - case '\u24CD': - // � [CIRCLED LATIN CAPITAL LETTER X] - case '\uFF38': // Ｘ [FULLWIDTH LATIN CAPITAL LETTER X] - output[opos++] = 'X'; - break; - - case '\u1D8D': - // � [LATIN SMALL LETTER X WITH PALATAL HOOK] - case '\u1E8B': - // ẋ [LATIN SMALL LETTER X WITH DOT ABOVE] - case '\u1E8D': - // � [LATIN SMALL LETTER X WITH DIAERESIS] - case '\u2093': - // â‚“ [LATIN SUBSCRIPT SMALL LETTER X] - case '\u24E7': - // ⓧ [CIRCLED LATIN SMALL LETTER X] - case '\uFF58': // ｘ [FULLWIDTH LATIN SMALL LETTER X] - output[opos++] = 'x'; - break; - - case '\u24B3': // â’³ [PARENTHESIZED LATIN SMALL LETTER X] - output[opos++] = '('; - output[opos++] = 'x'; - output[opos++] = ')'; - break; - - case '\u00DD': - // � [LATIN CAPITAL LETTER Y WITH ACUTE] - case '\u0176': - // Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX] - case '\u0178': - // Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS] - case '\u01B3': - // Ƴ [LATIN CAPITAL LETTER Y WITH HOOK] - case '\u0232': - // Ȳ [LATIN CAPITAL LETTER Y WITH MACRON] - case '\u024E': - // ÉŽ [LATIN CAPITAL LETTER Y WITH STROKE] - case '\u028F': - // � [LATIN LETTER SMALL CAPITAL Y] - case '\u1E8E': - // Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE] - case '\u1EF2': - // Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE] - case '\u1EF4': - // á»´ [LATIN CAPITAL LETTER Y WITH DOT BELOW] - case '\u1EF6': - // Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE] - case '\u1EF8': - // Ỹ [LATIN CAPITAL LETTER Y WITH TILDE] - case '\u1EFE': - // Ỿ [LATIN CAPITAL LETTER Y WITH LOOP] - case '\u24CE': - // â“Ž [CIRCLED LATIN CAPITAL LETTER Y] - case '\uFF39': // ï¼¹ [FULLWIDTH LATIN CAPITAL LETTER Y] - output[opos++] = 'Y'; - break; - - case '\u00FD': - // ý [LATIN SMALL LETTER Y WITH ACUTE] - case '\u00FF': - // ÿ [LATIN SMALL LETTER Y WITH DIAERESIS] - case '\u0177': - // Å· [LATIN SMALL LETTER Y WITH CIRCUMFLEX] - case '\u01B4': - // Æ´ [LATIN SMALL LETTER Y WITH HOOK] - case '\u0233': - // ȳ [LATIN SMALL LETTER Y WITH MACRON] - case '\u024F': - // � [LATIN SMALL LETTER Y WITH STROKE] - case '\u028E': - // ÊŽ [LATIN SMALL LETTER TURNED Y] - case '\u1E8F': - // � [LATIN SMALL LETTER Y WITH DOT ABOVE] - case '\u1E99': - // ẙ [LATIN SMALL LETTER Y WITH RING ABOVE] - case '\u1EF3': - // ỳ [LATIN SMALL LETTER Y WITH GRAVE] - case '\u1EF5': - // ỵ [LATIN SMALL LETTER Y WITH DOT BELOW] - case '\u1EF7': - // á»· [LATIN SMALL LETTER Y WITH HOOK ABOVE] - case '\u1EF9': - // ỹ [LATIN SMALL LETTER Y WITH TILDE] - case '\u1EFF': - // ỿ [LATIN SMALL LETTER Y WITH LOOP] - case '\u24E8': - // ⓨ [CIRCLED LATIN SMALL LETTER Y] - case '\uFF59': // ï½™ [FULLWIDTH LATIN SMALL LETTER Y] - output[opos++] = 'y'; - break; - - case '\u24B4': // â’´ [PARENTHESIZED LATIN SMALL LETTER Y] - output[opos++] = '('; - output[opos++] = 'y'; - output[opos++] = ')'; - break; - - case '\u0179': - // Ź [LATIN CAPITAL LETTER Z WITH ACUTE] - case '\u017B': - // Å» [LATIN CAPITAL LETTER Z WITH DOT ABOVE] - case '\u017D': - // Ž [LATIN CAPITAL LETTER Z WITH CARON] - case '\u01B5': - // Ƶ [LATIN CAPITAL LETTER Z WITH STROKE] - case '\u021C': - // Èœ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH] - case '\u0224': - // Ȥ [LATIN CAPITAL LETTER Z WITH HOOK] - case '\u1D22': - // á´¢ [LATIN LETTER SMALL CAPITAL Z] - case '\u1E90': - // � [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX] - case '\u1E92': - // Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW] - case '\u1E94': - // �? [LATIN CAPITAL LETTER Z WITH LINE BELOW] - case '\u24CF': - // � [CIRCLED LATIN CAPITAL LETTER Z] - case '\u2C6B': - // Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER] - case '\uA762': - // � [LATIN CAPITAL LETTER VISIGOTHIC Z] - case '\uFF3A': // Ｚ [FULLWIDTH LATIN CAPITAL LETTER Z] - output[opos++] = 'Z'; - break; - - case '\u017A': - // ź [LATIN SMALL LETTER Z WITH ACUTE] - case '\u017C': - // ż [LATIN SMALL LETTER Z WITH DOT ABOVE] - case '\u017E': - // ž [LATIN SMALL LETTER Z WITH CARON] - case '\u01B6': - // ƶ [LATIN SMALL LETTER Z WITH STROKE] - case '\u021D': - // � http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH] - case '\u0225': - // È¥ [LATIN SMALL LETTER Z WITH HOOK] - case '\u0240': - // É€ [LATIN SMALL LETTER Z WITH SWASH TAIL] - case '\u0290': - // � [LATIN SMALL LETTER Z WITH RETROFLEX HOOK] - case '\u0291': - // Ê‘ [LATIN SMALL LETTER Z WITH CURL] - case '\u1D76': - // ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE] - case '\u1D8E': - // ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK] - case '\u1E91': - // ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX] - case '\u1E93': - // ẓ [LATIN SMALL LETTER Z WITH DOT BELOW] - case '\u1E95': - // ẕ [LATIN SMALL LETTER Z WITH LINE BELOW] - case '\u24E9': - // â“© [CIRCLED LATIN SMALL LETTER Z] - case '\u2C6C': - // ⱬ [LATIN SMALL LETTER Z WITH DESCENDER] - case '\uA763': - // � [LATIN SMALL LETTER VISIGOTHIC Z] - case '\uFF5A': // ｚ [FULLWIDTH LATIN SMALL LETTER Z] - output[opos++] = 'z'; - break; - - case '\u24B5': // â’µ [PARENTHESIZED LATIN SMALL LETTER Z] - output[opos++] = '('; - output[opos++] = 'z'; - output[opos++] = ')'; - break; - - case '\u2070': - // � [SUPERSCRIPT ZERO] - case '\u2080': - // â‚€ [SUBSCRIPT ZERO] - case '\u24EA': - // ⓪ [CIRCLED DIGIT ZERO] - case '\u24FF': - // â“¿ [NEGATIVE CIRCLED DIGIT ZERO] - case '\uFF10': // � [FULLWIDTH DIGIT ZERO] - output[opos++] = '0'; - break; - - case '\u00B9': - // ¹ [SUPERSCRIPT ONE] - case '\u2081': - // � [SUBSCRIPT ONE] - case '\u2460': - // â‘  [CIRCLED DIGIT ONE] - case '\u24F5': - // ⓵ [DOUBLE CIRCLED DIGIT ONE] - case '\u2776': - // � [DINGBAT NEGATIVE CIRCLED DIGIT ONE] - case '\u2780': - // ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE] - case '\u278A': - // ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE] - case '\uFF11': // １ [FULLWIDTH DIGIT ONE] - output[opos++] = '1'; - break; - - case '\u2488': // â’ˆ [DIGIT ONE FULL STOP] - output[opos++] = '1'; - output[opos++] = '.'; - break; - - case '\u2474': // â‘´ [PARENTHESIZED DIGIT ONE] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = ')'; - break; - - case '\u00B2': - // ² [SUPERSCRIPT TWO] - case '\u2082': - // â‚‚ [SUBSCRIPT TWO] - case '\u2461': - // â‘¡ [CIRCLED DIGIT TWO] - case '\u24F6': - // ⓶ [DOUBLE CIRCLED DIGIT TWO] - case '\u2777': - // � [DINGBAT NEGATIVE CIRCLED DIGIT TWO] - case '\u2781': - // � [DINGBAT CIRCLED SANS-SERIF DIGIT TWO] - case '\u278B': - // âž‹ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO] - case '\uFF12': // ï¼’ [FULLWIDTH DIGIT TWO] - output[opos++] = '2'; - break; - - case '\u2489': // â’‰ [DIGIT TWO FULL STOP] - output[opos++] = '2'; - output[opos++] = '.'; - break; - - case '\u2475': // ⑵ [PARENTHESIZED DIGIT TWO] - output[opos++] = '('; - output[opos++] = '2'; - output[opos++] = ')'; - break; - - case '\u00B3': - // ³ [SUPERSCRIPT THREE] - case '\u2083': - // ₃ [SUBSCRIPT THREE] - case '\u2462': - // â‘¢ [CIRCLED DIGIT THREE] - case '\u24F7': - // â“· [DOUBLE CIRCLED DIGIT THREE] - case '\u2778': - // � [DINGBAT NEGATIVE CIRCLED DIGIT THREE] - case '\u2782': - // âž‚ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE] - case '\u278C': - // ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE] - case '\uFF13': // ３ [FULLWIDTH DIGIT THREE] - output[opos++] = '3'; - break; - - case '\u248A': // â’Š [DIGIT THREE FULL STOP] - output[opos++] = '3'; - output[opos++] = '.'; - break; - - case '\u2476': // ⑶ [PARENTHESIZED DIGIT THREE] - output[opos++] = '('; - output[opos++] = '3'; - output[opos++] = ')'; - break; - - case '\u2074': - // � [SUPERSCRIPT FOUR] - case '\u2084': - // â‚„ [SUBSCRIPT FOUR] - case '\u2463': - // â‘£ [CIRCLED DIGIT FOUR] - case '\u24F8': - // ⓸ [DOUBLE CIRCLED DIGIT FOUR] - case '\u2779': - // � [DINGBAT NEGATIVE CIRCLED DIGIT FOUR] - case '\u2783': - // ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR] - case '\u278D': - // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR] - case '\uFF14': // �? [FULLWIDTH DIGIT FOUR] - output[opos++] = '4'; - break; - - case '\u248B': // â’‹ [DIGIT FOUR FULL STOP] - output[opos++] = '4'; - output[opos++] = '.'; - break; - - case '\u2477': // â‘· [PARENTHESIZED DIGIT FOUR] - output[opos++] = '('; - output[opos++] = '4'; - output[opos++] = ')'; - break; - - case '\u2075': - // � [SUPERSCRIPT FIVE] - case '\u2085': - // â‚… [SUBSCRIPT FIVE] - case '\u2464': - // ⑤ [CIRCLED DIGIT FIVE] - case '\u24F9': - // ⓹ [DOUBLE CIRCLED DIGIT FIVE] - case '\u277A': - // � [DINGBAT NEGATIVE CIRCLED DIGIT FIVE] - case '\u2784': - // âž„ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE] - case '\u278E': - // ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE] - case '\uFF15': // ５ [FULLWIDTH DIGIT FIVE] - output[opos++] = '5'; - break; - - case '\u248C': // â’Œ [DIGIT FIVE FULL STOP] - output[opos++] = '5'; - output[opos++] = '.'; - break; - - case '\u2478': // ⑸ [PARENTHESIZED DIGIT FIVE] - output[opos++] = '('; - output[opos++] = '5'; - output[opos++] = ')'; - break; - - case '\u2076': - // � [SUPERSCRIPT SIX] - case '\u2086': - // ₆ [SUBSCRIPT SIX] - case '\u2465': - // â‘¥ [CIRCLED DIGIT SIX] - case '\u24FA': - // ⓺ [DOUBLE CIRCLED DIGIT SIX] - case '\u277B': - // � [DINGBAT NEGATIVE CIRCLED DIGIT SIX] - case '\u2785': - // âž… [DINGBAT CIRCLED SANS-SERIF DIGIT SIX] - case '\u278F': - // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX] - case '\uFF16': // ï¼– [FULLWIDTH DIGIT SIX] - output[opos++] = '6'; - break; - - case '\u248D': // â’� [DIGIT SIX FULL STOP] - output[opos++] = '6'; - output[opos++] = '.'; - break; - - case '\u2479': // ⑹ [PARENTHESIZED DIGIT SIX] - output[opos++] = '('; - output[opos++] = '6'; - output[opos++] = ')'; - break; - - case '\u2077': - // � [SUPERSCRIPT SEVEN] - case '\u2087': - // ₇ [SUBSCRIPT SEVEN] - case '\u2466': - // ⑦ [CIRCLED DIGIT SEVEN] - case '\u24FB': - // â“» [DOUBLE CIRCLED DIGIT SEVEN] - case '\u277C': - // � [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN] - case '\u2786': - // ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN] - case '\u2790': - // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN] - case '\uFF17': // ï¼— [FULLWIDTH DIGIT SEVEN] - output[opos++] = '7'; - break; - - case '\u248E': // â’Ž [DIGIT SEVEN FULL STOP] - output[opos++] = '7'; - output[opos++] = '.'; - break; - - case '\u247A': // ⑺ [PARENTHESIZED DIGIT SEVEN] - output[opos++] = '('; - output[opos++] = '7'; - output[opos++] = ')'; - break; - - case '\u2078': - // � [SUPERSCRIPT EIGHT] - case '\u2088': - // ₈ [SUBSCRIPT EIGHT] - case '\u2467': - // ⑧ [CIRCLED DIGIT EIGHT] - case '\u24FC': - // ⓼ [DOUBLE CIRCLED DIGIT EIGHT] - case '\u277D': - // � [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT] - case '\u2787': - // ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT] - case '\u2791': - // âž‘ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT] - case '\uFF18': // ８ [FULLWIDTH DIGIT EIGHT] - output[opos++] = '8'; - break; - - case '\u248F': // â’� [DIGIT EIGHT FULL STOP] - output[opos++] = '8'; - output[opos++] = '.'; - break; - - case '\u247B': // â‘» [PARENTHESIZED DIGIT EIGHT] - output[opos++] = '('; - output[opos++] = '8'; - output[opos++] = ')'; - break; - - case '\u2079': - // � [SUPERSCRIPT NINE] - case '\u2089': - // ₉ [SUBSCRIPT NINE] - case '\u2468': - // ⑨ [CIRCLED DIGIT NINE] - case '\u24FD': - // ⓽ [DOUBLE CIRCLED DIGIT NINE] - case '\u277E': - // � [DINGBAT NEGATIVE CIRCLED DIGIT NINE] - case '\u2788': - // ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE] - case '\u2792': - // âž’ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE] - case '\uFF19': // ï¼™ [FULLWIDTH DIGIT NINE] - output[opos++] = '9'; - break; - - case '\u2490': // â’� [DIGIT NINE FULL STOP] - output[opos++] = '9'; - output[opos++] = '.'; - break; - - case '\u247C': // ⑼ [PARENTHESIZED DIGIT NINE] - output[opos++] = '('; - output[opos++] = '9'; - output[opos++] = ')'; - break; - - case '\u2469': - // â‘© [CIRCLED NUMBER TEN] - case '\u24FE': - // ⓾ [DOUBLE CIRCLED NUMBER TEN] - case '\u277F': - // � [DINGBAT NEGATIVE CIRCLED NUMBER TEN] - case '\u2789': - // ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN] - case '\u2793': // âž“ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN] - output[opos++] = '1'; - output[opos++] = '0'; - break; - - case '\u2491': // â’‘ [NUMBER TEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '0'; - output[opos++] = '.'; - break; - - case '\u247D': // ⑽ [PARENTHESIZED NUMBER TEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '0'; - output[opos++] = ')'; - break; - - case '\u246A': - // ⑪ [CIRCLED NUMBER ELEVEN] - case '\u24EB': // â“« [NEGATIVE CIRCLED NUMBER ELEVEN] - output[opos++] = '1'; - output[opos++] = '1'; - break; - - case '\u2492': // â’’ [NUMBER ELEVEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '1'; - output[opos++] = '.'; - break; - - case '\u247E': // ⑾ [PARENTHESIZED NUMBER ELEVEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '1'; - output[opos++] = ')'; - break; - - case '\u246B': - // â‘« [CIRCLED NUMBER TWELVE] - case '\u24EC': // ⓬ [NEGATIVE CIRCLED NUMBER TWELVE] - output[opos++] = '1'; - output[opos++] = '2'; - break; - - case '\u2493': // â’“ [NUMBER TWELVE FULL STOP] - output[opos++] = '1'; - output[opos++] = '2'; - output[opos++] = '.'; - break; - - case '\u247F': // â‘¿ [PARENTHESIZED NUMBER TWELVE] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '2'; - output[opos++] = ')'; - break; - - case '\u246C': - // ⑬ [CIRCLED NUMBER THIRTEEN] - case '\u24ED': // â“­ [NEGATIVE CIRCLED NUMBER THIRTEEN] - output[opos++] = '1'; - output[opos++] = '3'; - break; - - case '\u2494': // â’�? [NUMBER THIRTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '3'; - output[opos++] = '.'; - break; - - case '\u2480': // â’€ [PARENTHESIZED NUMBER THIRTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '3'; - output[opos++] = ')'; - break; - - case '\u246D': - // â‘­ [CIRCLED NUMBER FOURTEEN] - case '\u24EE': // â“® [NEGATIVE CIRCLED NUMBER FOURTEEN] - output[opos++] = '1'; - output[opos++] = '4'; - break; - - case '\u2495': // â’• [NUMBER FOURTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '4'; - output[opos++] = '.'; - break; - - case '\u2481': // â’� [PARENTHESIZED NUMBER FOURTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '4'; - output[opos++] = ')'; - break; - - case '\u246E': - // â‘® [CIRCLED NUMBER FIFTEEN] - case '\u24EF': // ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN] - output[opos++] = '1'; - output[opos++] = '5'; - break; - - case '\u2496': // â’– [NUMBER FIFTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '5'; - output[opos++] = '.'; - break; - - case '\u2482': // â’‚ [PARENTHESIZED NUMBER FIFTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '5'; - output[opos++] = ')'; - break; - - case '\u246F': - // ⑯ [CIRCLED NUMBER SIXTEEN] - case '\u24F0': // â“° [NEGATIVE CIRCLED NUMBER SIXTEEN] - output[opos++] = '1'; - output[opos++] = '6'; - break; - - case '\u2497': // â’— [NUMBER SIXTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '6'; - output[opos++] = '.'; - break; - - case '\u2483': // â’ƒ [PARENTHESIZED NUMBER SIXTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '6'; - output[opos++] = ')'; - break; - - case '\u2470': - // â‘° [CIRCLED NUMBER SEVENTEEN] - case '\u24F1': // ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN] - output[opos++] = '1'; - output[opos++] = '7'; - break; - - case '\u2498': // â’˜ [NUMBER SEVENTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '7'; - output[opos++] = '.'; - break; - - case '\u2484': // â’„ [PARENTHESIZED NUMBER SEVENTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '7'; - output[opos++] = ')'; - break; - - case '\u2471': - // ⑱ [CIRCLED NUMBER EIGHTEEN] - case '\u24F2': // ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN] - output[opos++] = '1'; - output[opos++] = '8'; - break; - - case '\u2499': // â’™ [NUMBER EIGHTEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '8'; - output[opos++] = '.'; - break; - - case '\u2485': // â’… [PARENTHESIZED NUMBER EIGHTEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '8'; - output[opos++] = ')'; - break; - - case '\u2472': - // ⑲ [CIRCLED NUMBER NINETEEN] - case '\u24F3': // ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN] - output[opos++] = '1'; - output[opos++] = '9'; - break; - - case '\u249A': // â’š [NUMBER NINETEEN FULL STOP] - output[opos++] = '1'; - output[opos++] = '9'; - output[opos++] = '.'; - break; - - case '\u2486': // â’† [PARENTHESIZED NUMBER NINETEEN] - output[opos++] = '('; - output[opos++] = '1'; - output[opos++] = '9'; - output[opos++] = ')'; - break; - - case '\u2473': - // ⑳ [CIRCLED NUMBER TWENTY] - case '\u24F4': // â“´ [NEGATIVE CIRCLED NUMBER TWENTY] - output[opos++] = '2'; - output[opos++] = '0'; - break; - - case '\u249B': // â’› [NUMBER TWENTY FULL STOP] - output[opos++] = '2'; - output[opos++] = '0'; - output[opos++] = '.'; - break; - - case '\u2487': // â’‡ [PARENTHESIZED NUMBER TWENTY] - output[opos++] = '('; - output[opos++] = '2'; - output[opos++] = '0'; - output[opos++] = ')'; - break; - - case '\u00AB': - // « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK] - case '\u00BB': - // » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK] - case '\u201C': - // “ [LEFT DOUBLE QUOTATION MARK] - case '\u201D': - // � [RIGHT DOUBLE QUOTATION MARK] - case '\u201E': - // „ [DOUBLE LOW-9 QUOTATION MARK] - case '\u2033': - // ″ [DOUBLE PRIME] - case '\u2036': - // ‶ [REVERSED DOUBLE PRIME] - case '\u275D': - // � [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT] - case '\u275E': - // � [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT] - case '\u276E': - // � [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT] - case '\u276F': - // � [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT] - case '\uFF02': // ＂ [FULLWIDTH QUOTATION MARK] - output[opos++] = '"'; - break; - - case '\u2018': - // ‘ [LEFT SINGLE QUOTATION MARK] - case '\u2019': - // ’ [RIGHT SINGLE QUOTATION MARK] - case '\u201A': - // ‚ [SINGLE LOW-9 QUOTATION MARK] - case '\u201B': - // ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK] - case '\u2032': - // ′ [PRIME] - case '\u2035': - // ‵ [REVERSED PRIME] - case '\u2039': - // ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK] - case '\u203A': - // › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK] - case '\u275B': - // � [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT] - case '\u275C': - // � [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT] - case '\uFF07': // ＇ [FULLWIDTH APOSTROPHE] - output[opos++] = '\''; - break; - - case '\u2010': - // � [HYPHEN] - case '\u2011': - // ‑ [NON-BREAKING HYPHEN] - case '\u2012': - // ‒ [FIGURE DASH] - case '\u2013': - // – [EN DASH] - case '\u2014': - // �? [EM DASH] - case '\u207B': - // � [SUPERSCRIPT MINUS] - case '\u208B': - // â‚‹ [SUBSCRIPT MINUS] - case '\uFF0D': // � [FULLWIDTH HYPHEN-MINUS] - output[opos++] = '-'; - break; - - case '\u2045': - // � [LEFT SQUARE BRACKET WITH QUILL] - case '\u2772': - // � [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT] - case '\uFF3B': // ï¼» [FULLWIDTH LEFT SQUARE BRACKET] - output[opos++] = '['; - break; - - case '\u2046': - // � [RIGHT SQUARE BRACKET WITH QUILL] - case '\u2773': - // � [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT] - case '\uFF3D': // ï¼½ [FULLWIDTH RIGHT SQUARE BRACKET] - output[opos++] = ']'; - break; - - case '\u207D': - // � [SUPERSCRIPT LEFT PARENTHESIS] - case '\u208D': - // � [SUBSCRIPT LEFT PARENTHESIS] - case '\u2768': - // � [MEDIUM LEFT PARENTHESIS ORNAMENT] - case '\u276A': - // � [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT] - case '\uFF08': // （ [FULLWIDTH LEFT PARENTHESIS] - output[opos++] = '('; - break; - - case '\u2E28': // ⸨ [LEFT DOUBLE PARENTHESIS] - output[opos++] = '('; - output[opos++] = '('; - break; - - case '\u207E': - // � [SUPERSCRIPT RIGHT PARENTHESIS] - case '\u208E': - // â‚Ž [SUBSCRIPT RIGHT PARENTHESIS] - case '\u2769': - // � [MEDIUM RIGHT PARENTHESIS ORNAMENT] - case '\u276B': - // � [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT] - case '\uFF09': // ） [FULLWIDTH RIGHT PARENTHESIS] - output[opos++] = ')'; - break; - - case '\u2E29': // ⸩ [RIGHT DOUBLE PARENTHESIS] - output[opos++] = ')'; - output[opos++] = ')'; - break; - - case '\u276C': - // � [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT] - case '\u2770': - // � [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT] - case '\uFF1C': // ＜ [FULLWIDTH LESS-THAN SIGN] - output[opos++] = '<'; - break; - - case '\u276D': - // � [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT] - case '\u2771': - // � [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT] - case '\uFF1E': // ＞ [FULLWIDTH GREATER-THAN SIGN] - output[opos++] = '>'; - break; - - case '\u2774': - // � [MEDIUM LEFT CURLY BRACKET ORNAMENT] - case '\uFF5B': // ï½› [FULLWIDTH LEFT CURLY BRACKET] - output[opos++] = '{'; - break; - - case '\u2775': - // � [MEDIUM RIGHT CURLY BRACKET ORNAMENT] - case '\uFF5D': // � [FULLWIDTH RIGHT CURLY BRACKET] - output[opos++] = '}'; - break; - - case '\u207A': - // � [SUPERSCRIPT PLUS SIGN] - case '\u208A': - // â‚Š [SUBSCRIPT PLUS SIGN] - case '\uFF0B': // ＋ [FULLWIDTH PLUS SIGN] - output[opos++] = '+'; - break; - - case '\u207C': - // � [SUPERSCRIPT EQUALS SIGN] - case '\u208C': - // â‚Œ [SUBSCRIPT EQUALS SIGN] - case '\uFF1D': // � [FULLWIDTH EQUALS SIGN] - output[opos++] = '='; - break; - - case '\uFF01': // � [FULLWIDTH EXCLAMATION MARK] - output[opos++] = '!'; - break; - - case '\u203C': // ‼ [DOUBLE EXCLAMATION MARK] - output[opos++] = '!'; - output[opos++] = '!'; - break; - - case '\u2049': // � [EXCLAMATION QUESTION MARK] - output[opos++] = '!'; - output[opos++] = '?'; - break; - - case '\uFF03': // ＃ [FULLWIDTH NUMBER SIGN] - output[opos++] = '#'; - break; - - case '\uFF04': // ＄ [FULLWIDTH DOLLAR SIGN] - output[opos++] = '$'; - break; - - case '\u2052': - // � [COMMERCIAL MINUS SIGN] - case '\uFF05': // ï¼… [FULLWIDTH PERCENT SIGN] - output[opos++] = '%'; - break; - - case '\uFF06': // ＆ [FULLWIDTH AMPERSAND] - output[opos++] = '&'; - break; - - case '\u204E': - // � [LOW ASTERISK] - case '\uFF0A': // ＊ [FULLWIDTH ASTERISK] - output[opos++] = '*'; - break; - - case '\uFF0C': // ， [FULLWIDTH COMMA] - output[opos++] = ','; - break; - - case '\uFF0E': // ． [FULLWIDTH FULL STOP] - output[opos++] = '.'; - break; - - case '\u2044': - // � [FRACTION SLASH] - case '\uFF0F': // � [FULLWIDTH SOLIDUS] - output[opos++] = '/'; - break; - - case '\uFF1A': // ： [FULLWIDTH COLON] - output[opos++] = ':'; - break; - - case '\u204F': - // � [REVERSED SEMICOLON] - case '\uFF1B': // ï¼› [FULLWIDTH SEMICOLON] - output[opos++] = ';'; - break; - - case '\uFF1F': // ？ [FULLWIDTH QUESTION MARK] - output[opos++] = '?'; - break; - - case '\u2047': // � [DOUBLE QUESTION MARK] - output[opos++] = '?'; - output[opos++] = '?'; - break; - - case '\u2048': // � [QUESTION EXCLAMATION MARK] - output[opos++] = '?'; - output[opos++] = '!'; - break; - - case '\uFF20': // ï¼  [FULLWIDTH COMMERCIAL AT] - output[opos++] = '@'; - break; - - case '\uFF3C': // ï¼¼ [FULLWIDTH REVERSE SOLIDUS] - output[opos++] = '\\'; - break; - - case '\u2038': - // ‸ [CARET] - case '\uFF3E': // ï¼¾ [FULLWIDTH CIRCUMFLEX ACCENT] - output[opos++] = '^'; - break; - - case '\uFF3F': // ＿ [FULLWIDTH LOW LINE] - output[opos++] = '_'; - break; - - case '\u2053': - // � [SWUNG DASH] - case '\uFF5E': // ～ [FULLWIDTH TILDE] - output[opos++] = '~'; - break; - - // BEGIN CUSTOM TRANSLITERATION OF CYRILIC CHARS - - // russian uppercase "А Б В Г Д Е Ё Ж З И Й К Л М Н О П Р С Т У Ф Х Ц Ч Ш Щ Ъ Ы Ь Э Ю Я" - // russian lowercase "а б в г д е ё ж з и й к л м н о п р с т у ф х ц ч ш щ ъ ы ь э ю я" - - // notes - // read http://www.vesic.org/english/blog/c-sharp/transliteration-easy-way-microsoft-transliteration-utility/ - // should we look into MS Transliteration Utility (http://msdn.microsoft.com/en-US/goglobal/bb688104.aspx) - // also UnicodeSharpFork https://bitbucket.org/DimaStefantsov/unidecodesharpfork - // also Transliterator http://transliterator.codeplex.com/ - // - // in any case it would be good to generate all those "case" statements instead of writing them by hand - // time for a T4 template? - // also we should support extensibility so ppl can register more cases in external code - - // TODO: transliterates Анастасия as Anastasiya, and not Anastasia - // Ольга --> Ol'ga, Татьяна --> Tat'yana -- that's bad (?) - // Note: should ä (German umlaut) become a or ae ? - case '\u0410': // А - output[opos++] = 'A'; - break; - case '\u0430': // а - output[opos++] = 'a'; - break; - case '\u0411': // Б - output[opos++] = 'B'; - break; - case '\u0431': // б - output[opos++] = 'b'; - break; - case '\u0412': // В - output[opos++] = 'V'; - break; - case '\u0432': // в - output[opos++] = 'v'; - break; - case '\u0413': // Г - output[opos++] = 'G'; - break; - case '\u0433': // г - output[opos++] = 'g'; - break; - case '\u0414': // Д - output[opos++] = 'D'; - break; - case '\u0434': // д - output[opos++] = 'd'; - break; - case '\u0415': // Е - output[opos++] = 'E'; - break; - case '\u0435': // е - output[opos++] = 'e'; - break; - case '\u0401': // Ё - output[opos++] = 'E'; // alt. Yo - break; - case '\u0451': // ё - output[opos++] = 'e'; // alt. yo - break; - case '\u0416': // Ж - output[opos++] = 'Z'; - output[opos++] = 'h'; - break; - case '\u0436': // ж - output[opos++] = 'z'; - output[opos++] = 'h'; - break; - case '\u0417': // З - output[opos++] = 'Z'; - break; - case '\u0437': // з - output[opos++] = 'z'; - break; - case '\u0418': // И - output[opos++] = 'I'; - break; - case '\u0438': // и - output[opos++] = 'i'; - break; - case '\u0419': // Й - output[opos++] = 'I'; // alt. Y, J - break; - case '\u0439': // й - output[opos++] = 'i'; // alt. y, j - break; - case '\u041A': // К - output[opos++] = 'K'; - break; - case '\u043A': // к - output[opos++] = 'k'; - break; - case '\u041B': // Л - output[opos++] = 'L'; - break; - case '\u043B': // л - output[opos++] = 'l'; - break; - case '\u041C': // М - output[opos++] = 'M'; - break; - case '\u043C': // м - output[opos++] = 'm'; - break; - case '\u041D': // Н - output[opos++] = 'N'; - break; - case '\u043D': // н - output[opos++] = 'n'; - break; - case '\u041E': // О - output[opos++] = 'O'; - break; - case '\u043E': // о - output[opos++] = 'o'; - break; - case '\u041F': // П - output[opos++] = 'P'; - break; - case '\u043F': // п - output[opos++] = 'p'; - break; - case '\u0420': // Р - output[opos++] = 'R'; - break; - case '\u0440': // р - output[opos++] = 'r'; - break; - case '\u0421': // С - output[opos++] = 'S'; - break; - case '\u0441': // с - output[opos++] = 's'; - break; - case '\u0422': // Т - output[opos++] = 'T'; - break; - case '\u0442': // т - output[opos++] = 't'; - break; - case '\u0423': // У - output[opos++] = 'U'; - break; - case '\u0443': // у - output[opos++] = 'u'; - break; - case '\u0424': // Ф - output[opos++] = 'F'; - break; - case '\u0444': // ф - output[opos++] = 'f'; - break; - case '\u0425': // Х - output[opos++] = 'K'; // alt. X - output[opos++] = 'h'; - break; - case '\u0445': // х - output[opos++] = 'k'; // alt. x - output[opos++] = 'h'; - break; - case '\u0426': // Ц - output[opos++] = 'F'; - break; - case '\u0446': // ц - output[opos++] = 'f'; - break; - case '\u0427': // Ч - output[opos++] = 'C'; // alt. Ts, C - output[opos++] = 'h'; - break; - case '\u0447': // ч - output[opos++] = 'c'; // alt. ts, c - output[opos++] = 'h'; - break; - case '\u0428': // Ш - output[opos++] = 'S'; // alt. Ch, S - output[opos++] = 'h'; - break; - case '\u0448': // ш - output[opos++] = 's'; // alt. ch, s - output[opos++] = 'h'; - break; - case '\u0429': // Щ - output[opos++] = 'S'; // alt. Shch, Sc - output[opos++] = 'h'; - break; - case '\u0449': // щ - output[opos++] = 's'; // alt. shch, sc - output[opos++] = 'h'; - break; - case '\u042A': // Ъ - output[opos++] = '"'; // " - break; - case '\u044A': // ъ - output[opos++] = '"'; // " - break; - case '\u042B': // Ы - output[opos++] = 'Y'; - break; - case '\u044B': // ы - output[opos++] = 'y'; - break; - case '\u042C': // Ь - output[opos++] = '\''; // ' - break; - case '\u044C': // ь - output[opos++] = '\''; // ' - break; - case '\u042D': // Э - output[opos++] = 'E'; - break; - case '\u044D': // э - output[opos++] = 'e'; - break; - case '\u042E': // Ю - output[opos++] = 'Y'; // alt. Ju - output[opos++] = 'u'; - break; - case '\u044E': // ю - output[opos++] = 'y'; // alt. ju - output[opos++] = 'u'; - break; - case '\u042F': // Я - output[opos++] = 'Y'; // alt. Ja - output[opos++] = 'a'; - break; - case '\u044F': // я - output[opos++] = 'y'; // alt. ja - output[opos++] = 'a'; - break; - - // BEGIN EXTRA - /* - case '£': - output[opos++] = 'G'; - output[opos++] = 'B'; - output[opos++] = 'P'; - break; - - case '€': - output[opos++] = 'E'; - output[opos++] = 'U'; - output[opos++] = 'R'; - break; - - case '©': - output[opos++] = '('; - output[opos++] = 'C'; - output[opos++] = ')'; - break; - */ - default: - // if (ToMoreAscii(input, ipos, output, ref opos)) - // break; - - // if (!char.IsLetterOrDigit(c)) // that would not catch eg 汉 unfortunately - // output[opos++] = '?'; - // else - // output[opos++] = c; - - // strict ASCII - output[opos++] = fail; - - break; - } - } + // 5. Fallback for unmapped characters + output[0] = fallback; + return 1; } - // private static bool ToMoreAscii(char[] input, int ipos, char[] output, ref int opos) - // { - // var c = input[ipos]; + private static int TryNormalize(char c, Span output) + { + // Skip characters that won't normalize to ASCII + if (c < '\u00C0') + { + return 0; + } - // switch (c) - // { - // case '£': - // output[opos++] = 'G'; - // output[opos++] = 'B'; - // output[opos++] = 'P'; - // break; + // Normalize to FormD (decomposed form) + ReadOnlySpan input = stackalloc char[] { c }; + var normalized = input.ToString().Normalize(NormalizationForm.FormD); - // case '€': - // output[opos++] = 'E'; - // output[opos++] = 'U'; - // output[opos++] = 'R'; - // break; + if (normalized.Length == 0) + { + return 0; + } - // case '©': - // output[opos++] = '('; - // output[opos++] = 'C'; - // output[opos++] = ')'; - // break; + // Copy only base characters (skip combining marks) + var len = 0; + foreach (var ch in normalized) + { + var category = CharUnicodeInfo.GetUnicodeCategory(ch); - // default: - // return false; - // } + // Skip combining marks (diacritics) + if (category == UnicodeCategory.NonSpacingMark || + category == UnicodeCategory.SpacingCombiningMark || + category == UnicodeCategory.EnclosingMark) + { + continue; + } - // return true; - // } + // Only keep if it's now ASCII + if (ch < '\u0080') + { + output[len++] = ch; + } + } + + return len; + } } diff --git a/src/Umbraco.Core/Strings/Utf8ToAsciiConverterNew.cs b/src/Umbraco.Core/Strings/Utf8ToAsciiConverterNew.cs deleted file mode 100644 index d1327bab6f..0000000000 --- a/src/Umbraco.Core/Strings/Utf8ToAsciiConverterNew.cs +++ /dev/null @@ -1,209 +0,0 @@ -using System.Buffers; -using System.Collections.Frozen; -using System.Globalization; -using System.Text; - -namespace Umbraco.Cms.Core.Strings; - -/// -/// SIMD-optimized UTF-8 to ASCII converter with extensible character mappings. -/// -/// -/// -/// This converter uses a multi-step fallback strategy: -/// 1. Dictionary lookup for special cases (ligatures, Cyrillic, special Latin) -/// 2. Unicode normalization (FormD) for accented Latin characters -/// 3. Control character stripping -/// 4. Whitespace normalization -/// 5. Fallback character for unmapped characters -/// -/// -/// Most accented Latin characters (À, é, ñ, etc.) are handled automatically via -/// Unicode normalization. Dictionary mappings are only needed for characters that -/// don't decompose correctly (ligatures like Æ→AE, Cyrillic, special Latin like Ø→O). -/// -/// -public sealed class Utf8ToAsciiConverterNew : IUtf8ToAsciiConverter -{ - /// - /// Maximum expansion ratio for output buffer sizing. - /// Worst case: single char becomes 4 chars (e.g., Щ→Shch in standard transliteration). - /// - private const int MaxExpansionRatio = 4; - - // SIMD-optimized ASCII detection (uses AVX-512 when available) - private static readonly SearchValues AsciiPrintable = - SearchValues.Create(" !\"#$%&'()*+,-./0123456789:;<=>?@" + - "ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`" + - "abcdefghijklmnopqrstuvwxyz{|}~"); - - private readonly FrozenDictionary _mappings; - - public Utf8ToAsciiConverterNew(ICharacterMappingLoader mappingLoader) - { - _mappings = mappingLoader.LoadMappings(); - } - - /// - public string Convert(string? text, char fallback = '?') - { - if (string.IsNullOrEmpty(text)) - { - return string.Empty; - } - - var input = text.AsSpan(); - - // Fast path: all ASCII - no conversion needed - if (input.IndexOfAnyExcept(AsciiPrintable) == -1) - { - return text; - } - - // Allocate output buffer for worst-case expansion - var maxLen = text.Length * MaxExpansionRatio; - char[] arrayBuffer = ArrayPool.Shared.Rent(maxLen); - try - { - var written = Convert(input, arrayBuffer.AsSpan(), fallback); - return new string(arrayBuffer, 0, written); - } - finally - { - ArrayPool.Shared.Return(arrayBuffer); - } - } - - /// - public int Convert(ReadOnlySpan input, Span output, char fallback = '?') - { - if (input.IsEmpty) - { - return 0; - } - - var opos = 0; - var ipos = 0; - - while (ipos < input.Length) - { - // Find next non-ASCII character using SIMD - var remaining = input[ipos..]; - var asciiLen = remaining.IndexOfAnyExcept(AsciiPrintable); - - if (asciiLen == -1) - { - // Rest is all ASCII - bulk copy - remaining.CopyTo(output[opos..]); - return opos + remaining.Length; - } - - if (asciiLen > 0) - { - // Copy ASCII prefix - remaining[..asciiLen].CopyTo(output[opos..]); - opos += asciiLen; - ipos += asciiLen; - } - - // Process non-ASCII character - var c = input[ipos]; - - // Handle surrogate pairs (emoji, etc.) - if (char.IsSurrogate(c)) - { - output[opos++] = fallback; - ipos++; - if (ipos < input.Length && char.IsLowSurrogate(input[ipos])) - { - ipos++; // Skip low surrogate - } - continue; - } - - opos += ProcessNonAscii(c, output[opos..], fallback); - ipos++; - } - - return opos; - } - - private int ProcessNonAscii(char c, Span output, char fallback) - { - // 1. Check special cases dictionary (ligatures, Cyrillic, etc.) - if (_mappings.TryGetValue(c, out var mapped)) - { - if (mapped.Length == 0) - { - return 0; // Empty mapping = strip character - } - mapped.AsSpan().CopyTo(output); - return mapped.Length; - } - - // 2. Try Unicode normalization (handles most accented chars) - var normLen = TryNormalize(c, output); - if (normLen > 0) - { - return normLen; - } - - // 3. Control character handling - if (char.IsControl(c)) - { - return 0; // Strip control characters - } - - // 4. Whitespace normalization - if (char.IsWhiteSpace(c)) - { - output[0] = ' '; - return 1; - } - - // 5. Fallback for unmapped characters - output[0] = fallback; - return 1; - } - - private static int TryNormalize(char c, Span output) - { - // Skip characters that won't normalize to ASCII - if (c < '\u00C0') - { - return 0; - } - - // Normalize to FormD (decomposed form) - ReadOnlySpan input = stackalloc char[] { c }; - var normalized = input.ToString().Normalize(NormalizationForm.FormD); - - if (normalized.Length == 0) - { - return 0; - } - - // Copy only base characters (skip combining marks) - var len = 0; - foreach (var ch in normalized) - { - var category = CharUnicodeInfo.GetUnicodeCategory(ch); - - // Skip combining marks (diacritics) - if (category == UnicodeCategory.NonSpacingMark || - category == UnicodeCategory.SpacingCombiningMark || - category == UnicodeCategory.EnclosingMark) - { - continue; - } - - // Only keep if it's now ASCII - if (ch < '\u0080') - { - output[len++] = ch; - } - } - - return len; - } -} diff --git a/src/Umbraco.Core/Strings/Utf8ToAsciiConverterOriginal.cs b/src/Umbraco.Core/Strings/Utf8ToAsciiConverterOriginal.cs new file mode 100644 index 0000000000..b6cb1e04b1 --- /dev/null +++ b/src/Umbraco.Core/Strings/Utf8ToAsciiConverterOriginal.cs @@ -0,0 +1,3633 @@ +#if false // Kept for historical reference only - not compiled +namespace Umbraco.Cms.Core.Strings; + +/// +/// Provides methods to convert Utf8 text to Ascii. +/// +/// +/// Tries to match characters such as accented eg "é" to Ascii equivalent eg "e". +/// Converts all "whitespace" characters to a single whitespace. +/// Removes all non-Utf8 (unicode) characters, so in fact it can sort-of "convert" Unicode to Ascii. +/// Replaces symbols with '?'. +/// +public static class Utf8ToAsciiConverter +{ + /// + /// Converts an Utf8 string into an Ascii string. + /// + /// The text to convert. + /// The character to use to replace characters that cannot properly be converted. + /// The converted text. + public static string ToAsciiString(string text, char fail = '?') => ToAsciiString(text.AsSpan(), fail); + + /// + /// Converts an Utf8 string into an Ascii string. + /// + /// The text to convert. + /// The character to use to replace characters that cannot properly be converted. + /// The converted text. + public static string ToAsciiString(ReadOnlySpan text, char fail = '?') + { + // this is faster although it uses more memory + // but... we should be filtering short strings only... + + var totalSize = text.Length * 3; + Span output = totalSize <= 1024 ? stackalloc char[totalSize] : new char[totalSize]; // *3 because of things such as OE + var len = ToAscii(text, output, fail); + return new string(output[..len]); + + // var output = new StringBuilder(input.Length + 16); // default is 16, start with at least input length + little extra + // ToAscii(input, output); + // return output.ToString(); + } + + /// + /// Converts an Utf8 string into an array of Ascii characters. + /// + /// The text to convert. + /// The character to use to replace characters that cannot properly be converted. + /// The converted text. + public static char[] ToAsciiCharArray(string text, char fail = '?') + { + var input = text.ToCharArray(); + + // this is faster although it uses more memory + // but... we should be filtering short strings only... + int outputLength = input.Length * 3; // *3 because of things such as OE + Span output = outputLength <= 1024 ? stackalloc char[outputLength] : new char[outputLength]; + var len = ToAscii(input, output, fail); + return output[..len].ToArray(); + + // var temp = new StringBuilder(input.Length + 16); // default is 16, start with at least input length + little extra + // ToAscii(input, temp); + // var output = new char[temp.Length]; + // temp.CopyTo(0, output, 0, temp.Length); + // return output; + } + + /// + /// Converts an array of Utf8 characters into an array of Ascii characters. + /// + /// The input array. + /// The output array. + /// The character to use to replace characters that cannot properly be converted. + /// The number of characters in the output array. + /// The caller must ensure that the output array is big enough. + /// The output array is not big enough. + private static int ToAscii(ReadOnlySpan input, Span output, char fail = '?') + { + var opos = 0; + + for (var ipos = 0; ipos < input.Length; ipos++) + { + // ignore high surrogate + if (char.IsSurrogate(input[ipos])) + { + ipos++; // and skip low surrogate + output[opos++] = fail; + } + else + { + ToAscii(input, ipos, output, ref opos, fail); + } + } + + return opos; + } + + // private static void ToAscii(char[] input, StringBuilder output) + // { + // var chars = new char[5]; + + // for (var ipos = 0; ipos < input.Length; ipos++) + // { + // var opos = 0; + // if (char.IsSurrogate(input[ipos])) + // ipos++; + // else + // { + // ToAscii(input, ipos, chars, ref opos); + // output.Append(chars, 0, opos); + // } + // } + // } + + /// + /// Converts the character at position in input array of Utf8 characters + /// + /// and writes the converted value to output array of Ascii characters at position + /// , + /// and increments that position accordingly. + /// + /// The input array. + /// The input position. + /// The output array. + /// The output position. + /// The character to use to replace characters that cannot properly be converted. + /// + /// Adapted from various sources on the 'net including Lucene.Net.Analysis.ASCIIFoldingFilter. + /// Input should contain Utf8 characters exclusively and NOT Unicode. + /// Removes controls, normalizes whitespaces, replaces symbols by '?'. + /// + private static void ToAscii(ReadOnlySpan input, int ipos, Span output, ref int opos, char fail = '?') + { + var c = input[ipos]; + + if (char.IsControl(c)) + { + // Control characters are non-printing and formatting characters, such as ACK, BEL, CR, FF, LF, and VT. + // The Unicode standard assigns the following code points to control characters: from \U0000 to \U001F, + // \U007F, and from \U0080 to \U009F. According to the Unicode standard, these values are to be + // interpreted as control characters unless their use is otherwise defined by an application. Valid + // control characters are members of the UnicodeCategory.Control category. + + // we don't want them + } + + // else if (char.IsSeparator(c)) + // { + // // The Unicode standard recognizes three subcategories of separators: + // // - Space separators (the UnicodeCategory.SpaceSeparator category), which includes characters such as \u0020. + // // - Line separators (the UnicodeCategory.LineSeparator category), which includes \u2028. + // // - Paragraph separators (the UnicodeCategory.ParagraphSeparator category), which includes \u2029. + // // + // // Note: The Unicode standard classifies the characters \u000A (LF), \u000C (FF), and \u000A (CR) as control + // // characters (members of the UnicodeCategory.Control category), not as separator characters. + + // // better do it via WhiteSpace + // } + else if (char.IsWhiteSpace(c)) + { + // White space characters are the following Unicode characters: + // - Members of the SpaceSeparator category, which includes the characters SPACE (U+0020), + // OGHAM SPACE MARK (U+1680), MONGOLIAN VOWEL SEPARATOR (U+180E), EN QUAD (U+2000), EM QUAD (U+2001), + // EN SPACE (U+2002), EM SPACE (U+2003), THREE-PER-EM SPACE (U+2004), FOUR-PER-EM SPACE (U+2005), + // SIX-PER-EM SPACE (U+2006), FIGURE SPACE (U+2007), PUNCTUATION SPACE (U+2008), THIN SPACE (U+2009), + // HAIR SPACE (U+200A), NARROW NO-BREAK SPACE (U+202F), MEDIUM MATHEMATICAL SPACE (U+205F), + // and IDEOGRAPHIC SPACE (U+3000). + // - Members of the LineSeparator category, which consists solely of the LINE SEPARATOR character (U+2028). + // - Members of the ParagraphSeparator category, which consists solely of the PARAGRAPH SEPARATOR character (U+2029). + // - The characters CHARACTER TABULATION (U+0009), LINE FEED (U+000A), LINE TABULATION (U+000B), + // FORM FEED (U+000C), CARRIAGE RETURN (U+000D), NEXT LINE (U+0085), and NO-BREAK SPACE (U+00A0). + + // make it a whitespace + output[opos++] = ' '; + } + else if (c < '\u0080') + { + // safe + output[opos++] = c; + } + else + { + switch (c) + { + case '\u00C0': + // À [LATIN CAPITAL LETTER A WITH GRAVE] + case '\u00C1': + // � [LATIN CAPITAL LETTER A WITH ACUTE] + case '\u00C2': + //  [LATIN CAPITAL LETTER A WITH CIRCUMFLEX] + case '\u00C3': + // à [LATIN CAPITAL LETTER A WITH TILDE] + case '\u00C4': + // Ä [LATIN CAPITAL LETTER A WITH DIAERESIS] + case '\u00C5': + // Ã… [LATIN CAPITAL LETTER A WITH RING ABOVE] + case '\u0100': + // Ä€ [LATIN CAPITAL LETTER A WITH MACRON] + case '\u0102': + // Ä‚ [LATIN CAPITAL LETTER A WITH BREVE] + case '\u0104': + // Ä„ [LATIN CAPITAL LETTER A WITH OGONEK] + case '\u018F': + // � http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA] + case '\u01CD': + // � [LATIN CAPITAL LETTER A WITH CARON] + case '\u01DE': + // Çž [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON] + case '\u01E0': + // Ç  [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON] + case '\u01FA': + // Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE] + case '\u0200': + // È€ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE] + case '\u0202': + // È‚ [LATIN CAPITAL LETTER A WITH INVERTED BREVE] + case '\u0226': + // Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE] + case '\u023A': + // Ⱥ [LATIN CAPITAL LETTER A WITH STROKE] + case '\u1D00': + // á´€ [LATIN LETTER SMALL CAPITAL A] + case '\u1E00': + // Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW] + case '\u1EA0': + // Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW] + case '\u1EA2': + // Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE] + case '\u1EA4': + // Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE] + case '\u1EA6': + // Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE] + case '\u1EA8': + // Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1EAA': + // Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE] + case '\u1EAC': + // Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW] + case '\u1EAE': + // Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE] + case '\u1EB0': + // Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE] + case '\u1EB2': + // Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE] + case '\u1EB4': + // Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE] + case '\u1EB6': + // Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW] + case '\u24B6': + // â’¶ [CIRCLED LATIN CAPITAL LETTER A] + case '\uFF21': // Ａ [FULLWIDTH LATIN CAPITAL LETTER A] + output[opos++] = 'A'; + break; + + case '\u00E0': + // à [LATIN SMALL LETTER A WITH GRAVE] + case '\u00E1': + // á [LATIN SMALL LETTER A WITH ACUTE] + case '\u00E2': + // â [LATIN SMALL LETTER A WITH CIRCUMFLEX] + case '\u00E3': + // ã [LATIN SMALL LETTER A WITH TILDE] + case '\u00E4': + // ä [LATIN SMALL LETTER A WITH DIAERESIS] + case '\u00E5': + // Ã¥ [LATIN SMALL LETTER A WITH RING ABOVE] + case '\u0101': + // � [LATIN SMALL LETTER A WITH MACRON] + case '\u0103': + // ă [LATIN SMALL LETTER A WITH BREVE] + case '\u0105': + // Ä… [LATIN SMALL LETTER A WITH OGONEK] + case '\u01CE': + // ÇŽ [LATIN SMALL LETTER A WITH CARON] + case '\u01DF': + // ÇŸ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON] + case '\u01E1': + // Ç¡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON] + case '\u01FB': + // Ç» [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE] + case '\u0201': + // � [LATIN SMALL LETTER A WITH DOUBLE GRAVE] + case '\u0203': + // ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE] + case '\u0227': + // ȧ [LATIN SMALL LETTER A WITH DOT ABOVE] + case '\u0250': + // � [LATIN SMALL LETTER TURNED A] + case '\u0259': + // É™ [LATIN SMALL LETTER SCHWA] + case '\u025A': + // Éš [LATIN SMALL LETTER SCHWA WITH HOOK] + case '\u1D8F': + // � [LATIN SMALL LETTER A WITH RETROFLEX HOOK] + case '\u1D95': + // ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK] + case '\u1E01': + // ạ [LATIN SMALL LETTER A WITH RING BELOW] + case '\u1E9A': + // ả [LATIN SMALL LETTER A WITH RIGHT HALF RING] + case '\u1EA1': + // ạ [LATIN SMALL LETTER A WITH DOT BELOW] + case '\u1EA3': + // ả [LATIN SMALL LETTER A WITH HOOK ABOVE] + case '\u1EA5': + // ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE] + case '\u1EA7': + // ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE] + case '\u1EA9': + // ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1EAB': + // ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE] + case '\u1EAD': + // ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW] + case '\u1EAF': + // ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE] + case '\u1EB1': + // ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE] + case '\u1EB3': + // ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE] + case '\u1EB5': + // ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE] + case '\u1EB7': + // ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW] + case '\u2090': + // � [LATIN SUBSCRIPT SMALL LETTER A] + case '\u2094': + // �? [LATIN SUBSCRIPT SMALL LETTER SCHWA] + case '\u24D0': + // � [CIRCLED LATIN SMALL LETTER A] + case '\u2C65': + // â±¥ [LATIN SMALL LETTER A WITH STROKE] + case '\u2C6F': + // Ɐ [LATIN CAPITAL LETTER TURNED A] + case '\uFF41': // � [FULLWIDTH LATIN SMALL LETTER A] + output[opos++] = 'a'; + break; + + case '\uA732': // Ꜳ [LATIN CAPITAL LETTER AA] + output[opos++] = 'A'; + output[opos++] = 'A'; + break; + + case '\u00C6': + // Æ [LATIN CAPITAL LETTER AE] + case '\u01E2': + // Ç¢ [LATIN CAPITAL LETTER AE WITH MACRON] + case '\u01FC': + // Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE] + case '\u1D01': // á´� [LATIN LETTER SMALL CAPITAL AE] + output[opos++] = 'A'; + output[opos++] = 'E'; + break; + + case '\uA734': // Ꜵ [LATIN CAPITAL LETTER AO] + output[opos++] = 'A'; + output[opos++] = 'O'; + break; + + case '\uA736': // Ꜷ [LATIN CAPITAL LETTER AU] + output[opos++] = 'A'; + output[opos++] = 'U'; + break; + + case '\uA738': + // Ꜹ [LATIN CAPITAL LETTER AV] + case '\uA73A': // Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR] + output[opos++] = 'A'; + output[opos++] = 'V'; + break; + + case '\uA73C': // Ꜽ [LATIN CAPITAL LETTER AY] + output[opos++] = 'A'; + output[opos++] = 'Y'; + break; + + case '\u249C': // â’œ [PARENTHESIZED LATIN SMALL LETTER A] + output[opos++] = '('; + output[opos++] = 'a'; + output[opos++] = ')'; + break; + + case '\uA733': // ꜳ [LATIN SMALL LETTER AA] + output[opos++] = 'a'; + output[opos++] = 'a'; + break; + + case '\u00E6': + // æ [LATIN SMALL LETTER AE] + case '\u01E3': + // Ç£ [LATIN SMALL LETTER AE WITH MACRON] + case '\u01FD': + // ǽ [LATIN SMALL LETTER AE WITH ACUTE] + case '\u1D02': // á´‚ [LATIN SMALL LETTER TURNED AE] + output[opos++] = 'a'; + output[opos++] = 'e'; + break; + + case '\uA735': // ꜵ [LATIN SMALL LETTER AO] + output[opos++] = 'a'; + output[opos++] = 'o'; + break; + + case '\uA737': // ꜷ [LATIN SMALL LETTER AU] + output[opos++] = 'a'; + output[opos++] = 'u'; + break; + + case '\uA739': + // ꜹ [LATIN SMALL LETTER AV] + case '\uA73B': // ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR] + output[opos++] = 'a'; + output[opos++] = 'v'; + break; + + case '\uA73D': // ꜽ [LATIN SMALL LETTER AY] + output[opos++] = 'a'; + output[opos++] = 'y'; + break; + + case '\u0181': + // � [LATIN CAPITAL LETTER B WITH HOOK] + case '\u0182': + // Æ‚ [LATIN CAPITAL LETTER B WITH TOPBAR] + case '\u0243': + // Ƀ [LATIN CAPITAL LETTER B WITH STROKE] + case '\u0299': + // Ê™ [LATIN LETTER SMALL CAPITAL B] + case '\u1D03': + // á´ƒ [LATIN LETTER SMALL CAPITAL BARRED B] + case '\u1E02': + // Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE] + case '\u1E04': + // Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW] + case '\u1E06': + // Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW] + case '\u24B7': + // â’· [CIRCLED LATIN CAPITAL LETTER B] + case '\uFF22': // ï¼¢ [FULLWIDTH LATIN CAPITAL LETTER B] + output[opos++] = 'B'; + break; + + case '\u0180': + // Æ€ [LATIN SMALL LETTER B WITH STROKE] + case '\u0183': + // ƃ [LATIN SMALL LETTER B WITH TOPBAR] + case '\u0253': + // É“ [LATIN SMALL LETTER B WITH HOOK] + case '\u1D6C': + // ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE] + case '\u1D80': + // ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK] + case '\u1E03': + // ḃ [LATIN SMALL LETTER B WITH DOT ABOVE] + case '\u1E05': + // ḅ [LATIN SMALL LETTER B WITH DOT BELOW] + case '\u1E07': + // ḇ [LATIN SMALL LETTER B WITH LINE BELOW] + case '\u24D1': + // â“‘ [CIRCLED LATIN SMALL LETTER B] + case '\uFF42': // ｂ [FULLWIDTH LATIN SMALL LETTER B] + output[opos++] = 'b'; + break; + + case '\u249D': // â’� [PARENTHESIZED LATIN SMALL LETTER B] + output[opos++] = '('; + output[opos++] = 'b'; + output[opos++] = ')'; + break; + + case '\u00C7': + // Ç [LATIN CAPITAL LETTER C WITH CEDILLA] + case '\u0106': + // Ć [LATIN CAPITAL LETTER C WITH ACUTE] + case '\u0108': + // Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX] + case '\u010A': + // ÄŠ [LATIN CAPITAL LETTER C WITH DOT ABOVE] + case '\u010C': + // ÄŒ [LATIN CAPITAL LETTER C WITH CARON] + case '\u0187': + // Ƈ [LATIN CAPITAL LETTER C WITH HOOK] + case '\u023B': + // È» [LATIN CAPITAL LETTER C WITH STROKE] + case '\u0297': + // Ê— [LATIN LETTER STRETCHED C] + case '\u1D04': + // á´„ [LATIN LETTER SMALL CAPITAL C] + case '\u1E08': + // Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE] + case '\u24B8': + // â’¸ [CIRCLED LATIN CAPITAL LETTER C] + case '\uFF23': // ï¼£ [FULLWIDTH LATIN CAPITAL LETTER C] + output[opos++] = 'C'; + break; + + case '\u00E7': + // ç [LATIN SMALL LETTER C WITH CEDILLA] + case '\u0107': + // ć [LATIN SMALL LETTER C WITH ACUTE] + case '\u0109': + // ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX] + case '\u010B': + // Ä‹ [LATIN SMALL LETTER C WITH DOT ABOVE] + case '\u010D': + // � [LATIN SMALL LETTER C WITH CARON] + case '\u0188': + // ƈ [LATIN SMALL LETTER C WITH HOOK] + case '\u023C': + // ȼ [LATIN SMALL LETTER C WITH STROKE] + case '\u0255': + // É• [LATIN SMALL LETTER C WITH CURL] + case '\u1E09': + // ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE] + case '\u2184': + // ↄ [LATIN SMALL LETTER REVERSED C] + case '\u24D2': + // â“’ [CIRCLED LATIN SMALL LETTER C] + case '\uA73E': + // Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT] + case '\uA73F': + // ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT] + case '\uFF43': // ｃ [FULLWIDTH LATIN SMALL LETTER C] + output[opos++] = 'c'; + break; + + case '\u249E': // â’ž [PARENTHESIZED LATIN SMALL LETTER C] + output[opos++] = '('; + output[opos++] = 'c'; + output[opos++] = ')'; + break; + + case '\u00D0': + // � [LATIN CAPITAL LETTER ETH] + case '\u010E': + // ÄŽ [LATIN CAPITAL LETTER D WITH CARON] + case '\u0110': + // � [LATIN CAPITAL LETTER D WITH STROKE] + case '\u0189': + // Ɖ [LATIN CAPITAL LETTER AFRICAN D] + case '\u018A': + // ÆŠ [LATIN CAPITAL LETTER D WITH HOOK] + case '\u018B': + // Æ‹ [LATIN CAPITAL LETTER D WITH TOPBAR] + case '\u1D05': + // á´… [LATIN LETTER SMALL CAPITAL D] + case '\u1D06': + // á´† [LATIN LETTER SMALL CAPITAL ETH] + case '\u1E0A': + // Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE] + case '\u1E0C': + // Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW] + case '\u1E0E': + // Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW] + case '\u1E10': + // � [LATIN CAPITAL LETTER D WITH CEDILLA] + case '\u1E12': + // Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW] + case '\u24B9': + // â’¹ [CIRCLED LATIN CAPITAL LETTER D] + case '\uA779': + // � [LATIN CAPITAL LETTER INSULAR D] + case '\uFF24': // Ｄ [FULLWIDTH LATIN CAPITAL LETTER D] + output[opos++] = 'D'; + break; + + case '\u00F0': + // ð [LATIN SMALL LETTER ETH] + case '\u010F': + // � [LATIN SMALL LETTER D WITH CARON] + case '\u0111': + // Ä‘ [LATIN SMALL LETTER D WITH STROKE] + case '\u018C': + // ÆŒ [LATIN SMALL LETTER D WITH TOPBAR] + case '\u0221': + // È¡ [LATIN SMALL LETTER D WITH CURL] + case '\u0256': + // É– [LATIN SMALL LETTER D WITH TAIL] + case '\u0257': + // É— [LATIN SMALL LETTER D WITH HOOK] + case '\u1D6D': + // áµ­ [LATIN SMALL LETTER D WITH MIDDLE TILDE] + case '\u1D81': + // � [LATIN SMALL LETTER D WITH PALATAL HOOK] + case '\u1D91': + // ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL] + case '\u1E0B': + // ḋ [LATIN SMALL LETTER D WITH DOT ABOVE] + case '\u1E0D': + // � [LATIN SMALL LETTER D WITH DOT BELOW] + case '\u1E0F': + // � [LATIN SMALL LETTER D WITH LINE BELOW] + case '\u1E11': + // ḑ [LATIN SMALL LETTER D WITH CEDILLA] + case '\u1E13': + // ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW] + case '\u24D3': + // â““ [CIRCLED LATIN SMALL LETTER D] + case '\uA77A': + // � [LATIN SMALL LETTER INSULAR D] + case '\uFF44': // ｄ [FULLWIDTH LATIN SMALL LETTER D] + output[opos++] = 'd'; + break; + + case '\u01C4': + // Ç„ [LATIN CAPITAL LETTER DZ WITH CARON] + case '\u01F1': // DZ [LATIN CAPITAL LETTER DZ] + output[opos++] = 'D'; + output[opos++] = 'Z'; + break; + + case '\u01C5': + // Ç… [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON] + case '\u01F2': // Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z] + output[opos++] = 'D'; + output[opos++] = 'z'; + break; + + case '\u249F': // â’Ÿ [PARENTHESIZED LATIN SMALL LETTER D] + output[opos++] = '('; + output[opos++] = 'd'; + output[opos++] = ')'; + break; + + case '\u0238': // ȸ [LATIN SMALL LETTER DB DIGRAPH] + output[opos++] = 'd'; + output[opos++] = 'b'; + break; + + case '\u01C6': + // dž [LATIN SMALL LETTER DZ WITH CARON] + case '\u01F3': + // dz [LATIN SMALL LETTER DZ] + case '\u02A3': + // Ê£ [LATIN SMALL LETTER DZ DIGRAPH] + case '\u02A5': // Ê¥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL] + output[opos++] = 'd'; + output[opos++] = 'z'; + break; + + case '\u00C8': + // È [LATIN CAPITAL LETTER E WITH GRAVE] + case '\u00C9': + // É [LATIN CAPITAL LETTER E WITH ACUTE] + case '\u00CA': + // Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX] + case '\u00CB': + // Ë [LATIN CAPITAL LETTER E WITH DIAERESIS] + case '\u0112': + // Ä’ [LATIN CAPITAL LETTER E WITH MACRON] + case '\u0114': + // �? [LATIN CAPITAL LETTER E WITH BREVE] + case '\u0116': + // Ä– [LATIN CAPITAL LETTER E WITH DOT ABOVE] + case '\u0118': + // Ę [LATIN CAPITAL LETTER E WITH OGONEK] + case '\u011A': + // Äš [LATIN CAPITAL LETTER E WITH CARON] + case '\u018E': + // ÆŽ [LATIN CAPITAL LETTER REVERSED E] + case '\u0190': + // � [LATIN CAPITAL LETTER OPEN E] + case '\u0204': + // È„ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE] + case '\u0206': + // Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE] + case '\u0228': + // Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA] + case '\u0246': + // Ɇ [LATIN CAPITAL LETTER E WITH STROKE] + case '\u1D07': + // á´‡ [LATIN LETTER SMALL CAPITAL E] + case '\u1E14': + // �? [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE] + case '\u1E16': + // Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE] + case '\u1E18': + // Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW] + case '\u1E1A': + // Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW] + case '\u1E1C': + // Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE] + case '\u1EB8': + // Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW] + case '\u1EBA': + // Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE] + case '\u1EBC': + // Ẽ [LATIN CAPITAL LETTER E WITH TILDE] + case '\u1EBE': + // Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE] + case '\u1EC0': + // Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE] + case '\u1EC2': + // Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1EC4': + // Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE] + case '\u1EC6': + // Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW] + case '\u24BA': + // â’º [CIRCLED LATIN CAPITAL LETTER E] + case '\u2C7B': + // â±» [LATIN LETTER SMALL CAPITAL TURNED E] + case '\uFF25': // ï¼¥ [FULLWIDTH LATIN CAPITAL LETTER E] + output[opos++] = 'E'; + break; + + case '\u00E8': + // è [LATIN SMALL LETTER E WITH GRAVE] + case '\u00E9': + // é [LATIN SMALL LETTER E WITH ACUTE] + case '\u00EA': + // ê [LATIN SMALL LETTER E WITH CIRCUMFLEX] + case '\u00EB': + // ë [LATIN SMALL LETTER E WITH DIAERESIS] + case '\u0113': + // Ä“ [LATIN SMALL LETTER E WITH MACRON] + case '\u0115': + // Ä• [LATIN SMALL LETTER E WITH BREVE] + case '\u0117': + // Ä— [LATIN SMALL LETTER E WITH DOT ABOVE] + case '\u0119': + // Ä™ [LATIN SMALL LETTER E WITH OGONEK] + case '\u011B': + // Ä› [LATIN SMALL LETTER E WITH CARON] + case '\u01DD': + // � [LATIN SMALL LETTER TURNED E] + case '\u0205': + // È… [LATIN SMALL LETTER E WITH DOUBLE GRAVE] + case '\u0207': + // ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE] + case '\u0229': + // È© [LATIN SMALL LETTER E WITH CEDILLA] + case '\u0247': + // ɇ [LATIN SMALL LETTER E WITH STROKE] + case '\u0258': + // ɘ [LATIN SMALL LETTER REVERSED E] + case '\u025B': + // É› [LATIN SMALL LETTER OPEN E] + case '\u025C': + // Éœ [LATIN SMALL LETTER REVERSED OPEN E] + case '\u025D': + // � [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK] + case '\u025E': + // Éž [LATIN SMALL LETTER CLOSED REVERSED OPEN E] + case '\u029A': + // Êš [LATIN SMALL LETTER CLOSED OPEN E] + case '\u1D08': + // á´ˆ [LATIN SMALL LETTER TURNED OPEN E] + case '\u1D92': + // ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK] + case '\u1D93': + // ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK] + case '\u1D94': + // �? [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK] + case '\u1E15': + // ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE] + case '\u1E17': + // ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE] + case '\u1E19': + // ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW] + case '\u1E1B': + // ḛ [LATIN SMALL LETTER E WITH TILDE BELOW] + case '\u1E1D': + // � [LATIN SMALL LETTER E WITH CEDILLA AND BREVE] + case '\u1EB9': + // ẹ [LATIN SMALL LETTER E WITH DOT BELOW] + case '\u1EBB': + // ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE] + case '\u1EBD': + // ẽ [LATIN SMALL LETTER E WITH TILDE] + case '\u1EBF': + // ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE] + case '\u1EC1': + // � [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE] + case '\u1EC3': + // ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1EC5': + // á»… [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE] + case '\u1EC7': + // ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW] + case '\u2091': + // â‚‘ [LATIN SUBSCRIPT SMALL LETTER E] + case '\u24D4': + // �? [CIRCLED LATIN SMALL LETTER E] + case '\u2C78': + // ⱸ [LATIN SMALL LETTER E WITH NOTCH] + case '\uFF45': // ï½… [FULLWIDTH LATIN SMALL LETTER E] + output[opos++] = 'e'; + break; + + case '\u24A0': // â’  [PARENTHESIZED LATIN SMALL LETTER E] + output[opos++] = '('; + output[opos++] = 'e'; + output[opos++] = ')'; + break; + + case '\u0191': + // Æ‘ [LATIN CAPITAL LETTER F WITH HOOK] + case '\u1E1E': + // Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE] + case '\u24BB': + // â’» [CIRCLED LATIN CAPITAL LETTER F] + case '\uA730': + // ꜰ [LATIN LETTER SMALL CAPITAL F] + case '\uA77B': + // � [LATIN CAPITAL LETTER INSULAR F] + case '\uA7FB': + // ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F] + case '\uFF26': // Ｆ [FULLWIDTH LATIN CAPITAL LETTER F] + output[opos++] = 'F'; + break; + + case '\u0192': + // Æ’ [LATIN SMALL LETTER F WITH HOOK] + case '\u1D6E': + // áµ® [LATIN SMALL LETTER F WITH MIDDLE TILDE] + case '\u1D82': + // ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK] + case '\u1E1F': + // ḟ [LATIN SMALL LETTER F WITH DOT ABOVE] + case '\u1E9B': + // ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE] + case '\u24D5': + // â“• [CIRCLED LATIN SMALL LETTER F] + case '\uA77C': + // � [LATIN SMALL LETTER INSULAR F] + case '\uFF46': // ｆ [FULLWIDTH LATIN SMALL LETTER F] + output[opos++] = 'f'; + break; + + case '\u24A1': // â’¡ [PARENTHESIZED LATIN SMALL LETTER F] + output[opos++] = '('; + output[opos++] = 'f'; + output[opos++] = ')'; + break; + + case '\uFB00': // ff [LATIN SMALL LIGATURE FF] + output[opos++] = 'f'; + output[opos++] = 'f'; + break; + + case '\uFB03': // ffi [LATIN SMALL LIGATURE FFI] + output[opos++] = 'f'; + output[opos++] = 'f'; + output[opos++] = 'i'; + break; + + case '\uFB04': // ffl [LATIN SMALL LIGATURE FFL] + output[opos++] = 'f'; + output[opos++] = 'f'; + output[opos++] = 'l'; + break; + + case '\uFB01': // � [LATIN SMALL LIGATURE FI] + output[opos++] = 'f'; + output[opos++] = 'i'; + break; + + case '\uFB02': // fl [LATIN SMALL LIGATURE FL] + output[opos++] = 'f'; + output[opos++] = 'l'; + break; + + case '\u011C': + // Äœ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX] + case '\u011E': + // Äž [LATIN CAPITAL LETTER G WITH BREVE] + case '\u0120': + // Ä  [LATIN CAPITAL LETTER G WITH DOT ABOVE] + case '\u0122': + // Ä¢ [LATIN CAPITAL LETTER G WITH CEDILLA] + case '\u0193': + // Æ“ [LATIN CAPITAL LETTER G WITH HOOK] + case '\u01E4': + // Ǥ [LATIN CAPITAL LETTER G WITH STROKE] + case '\u01E5': + // Ç¥ [LATIN SMALL LETTER G WITH STROKE] + case '\u01E6': + // Ǧ [LATIN CAPITAL LETTER G WITH CARON] + case '\u01E7': + // ǧ [LATIN SMALL LETTER G WITH CARON] + case '\u01F4': + // Ç´ [LATIN CAPITAL LETTER G WITH ACUTE] + case '\u0262': + // É¢ [LATIN LETTER SMALL CAPITAL G] + case '\u029B': + // Ê› [LATIN LETTER SMALL CAPITAL G WITH HOOK] + case '\u1E20': + // Ḡ [LATIN CAPITAL LETTER G WITH MACRON] + case '\u24BC': + // â’¼ [CIRCLED LATIN CAPITAL LETTER G] + case '\uA77D': + // � [LATIN CAPITAL LETTER INSULAR G] + case '\uA77E': + // � [LATIN CAPITAL LETTER TURNED INSULAR G] + case '\uFF27': // Ｇ [FULLWIDTH LATIN CAPITAL LETTER G] + output[opos++] = 'G'; + break; + + case '\u011D': + // � [LATIN SMALL LETTER G WITH CIRCUMFLEX] + case '\u011F': + // ÄŸ [LATIN SMALL LETTER G WITH BREVE] + case '\u0121': + // Ä¡ [LATIN SMALL LETTER G WITH DOT ABOVE] + case '\u0123': + // Ä£ [LATIN SMALL LETTER G WITH CEDILLA] + case '\u01F5': + // ǵ [LATIN SMALL LETTER G WITH ACUTE] + case '\u0260': + // É  [LATIN SMALL LETTER G WITH HOOK] + case '\u0261': + // É¡ [LATIN SMALL LETTER SCRIPT G] + case '\u1D77': + // áµ· [LATIN SMALL LETTER TURNED G] + case '\u1D79': + // áµ¹ [LATIN SMALL LETTER INSULAR G] + case '\u1D83': + // ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK] + case '\u1E21': + // ḡ [LATIN SMALL LETTER G WITH MACRON] + case '\u24D6': + // â“– [CIRCLED LATIN SMALL LETTER G] + case '\uA77F': + // � [LATIN SMALL LETTER TURNED INSULAR G] + case '\uFF47': // ｇ [FULLWIDTH LATIN SMALL LETTER G] + output[opos++] = 'g'; + break; + + case '\u24A2': // â’¢ [PARENTHESIZED LATIN SMALL LETTER G] + output[opos++] = '('; + output[opos++] = 'g'; + output[opos++] = ')'; + break; + + case '\u0124': + // Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX] + case '\u0126': + // Ħ [LATIN CAPITAL LETTER H WITH STROKE] + case '\u021E': + // Èž [LATIN CAPITAL LETTER H WITH CARON] + case '\u029C': + // Êœ [LATIN LETTER SMALL CAPITAL H] + case '\u1E22': + // Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE] + case '\u1E24': + // Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW] + case '\u1E26': + // Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS] + case '\u1E28': + // Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA] + case '\u1E2A': + // Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW] + case '\u24BD': + // â’½ [CIRCLED LATIN CAPITAL LETTER H] + case '\u2C67': + // Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER] + case '\u2C75': + // â±µ [LATIN CAPITAL LETTER HALF H] + case '\uFF28': // Ｈ [FULLWIDTH LATIN CAPITAL LETTER H] + output[opos++] = 'H'; + break; + + case '\u0125': + // Ä¥ [LATIN SMALL LETTER H WITH CIRCUMFLEX] + case '\u0127': + // ħ [LATIN SMALL LETTER H WITH STROKE] + case '\u021F': + // ÈŸ [LATIN SMALL LETTER H WITH CARON] + case '\u0265': + // É¥ [LATIN SMALL LETTER TURNED H] + case '\u0266': + // ɦ [LATIN SMALL LETTER H WITH HOOK] + case '\u02AE': + // Ê® [LATIN SMALL LETTER TURNED H WITH FISHHOOK] + case '\u02AF': + // ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL] + case '\u1E23': + // ḣ [LATIN SMALL LETTER H WITH DOT ABOVE] + case '\u1E25': + // ḥ [LATIN SMALL LETTER H WITH DOT BELOW] + case '\u1E27': + // ḧ [LATIN SMALL LETTER H WITH DIAERESIS] + case '\u1E29': + // ḩ [LATIN SMALL LETTER H WITH CEDILLA] + case '\u1E2B': + // ḫ [LATIN SMALL LETTER H WITH BREVE BELOW] + case '\u1E96': + // ẖ [LATIN SMALL LETTER H WITH LINE BELOW] + case '\u24D7': + // â“— [CIRCLED LATIN SMALL LETTER H] + case '\u2C68': + // ⱨ [LATIN SMALL LETTER H WITH DESCENDER] + case '\u2C76': + // ⱶ [LATIN SMALL LETTER HALF H] + case '\uFF48': // ｈ [FULLWIDTH LATIN SMALL LETTER H] + output[opos++] = 'h'; + break; + + case '\u01F6': // Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR] + output[opos++] = 'H'; + output[opos++] = 'V'; + break; + + case '\u24A3': // â’£ [PARENTHESIZED LATIN SMALL LETTER H] + output[opos++] = '('; + output[opos++] = 'h'; + output[opos++] = ')'; + break; + + case '\u0195': // Æ• [LATIN SMALL LETTER HV] + output[opos++] = 'h'; + output[opos++] = 'v'; + break; + + case '\u00CC': + // ÃŒ [LATIN CAPITAL LETTER I WITH GRAVE] + case '\u00CD': + // � [LATIN CAPITAL LETTER I WITH ACUTE] + case '\u00CE': + // ÃŽ [LATIN CAPITAL LETTER I WITH CIRCUMFLEX] + case '\u00CF': + // � [LATIN CAPITAL LETTER I WITH DIAERESIS] + case '\u0128': + // Ĩ [LATIN CAPITAL LETTER I WITH TILDE] + case '\u012A': + // Ī [LATIN CAPITAL LETTER I WITH MACRON] + case '\u012C': + // Ĭ [LATIN CAPITAL LETTER I WITH BREVE] + case '\u012E': + // Ä® [LATIN CAPITAL LETTER I WITH OGONEK] + case '\u0130': + // Ä° [LATIN CAPITAL LETTER I WITH DOT ABOVE] + case '\u0196': + // Æ– [LATIN CAPITAL LETTER IOTA] + case '\u0197': + // Æ— [LATIN CAPITAL LETTER I WITH STROKE] + case '\u01CF': + // � [LATIN CAPITAL LETTER I WITH CARON] + case '\u0208': + // Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE] + case '\u020A': + // ÈŠ [LATIN CAPITAL LETTER I WITH INVERTED BREVE] + case '\u026A': + // ɪ [LATIN LETTER SMALL CAPITAL I] + case '\u1D7B': + // áµ» [LATIN SMALL CAPITAL LETTER I WITH STROKE] + case '\u1E2C': + // Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW] + case '\u1E2E': + // Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE] + case '\u1EC8': + // Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE] + case '\u1ECA': + // Ị [LATIN CAPITAL LETTER I WITH DOT BELOW] + case '\u24BE': + // â’¾ [CIRCLED LATIN CAPITAL LETTER I] + case '\uA7FE': + // ꟾ [LATIN EPIGRAPHIC LETTER I LONGA] + case '\uFF29': // Ｉ [FULLWIDTH LATIN CAPITAL LETTER I] + output[opos++] = 'I'; + break; + + case '\u00EC': + // ì [LATIN SMALL LETTER I WITH GRAVE] + case '\u00ED': + // í [LATIN SMALL LETTER I WITH ACUTE] + case '\u00EE': + // î [LATIN SMALL LETTER I WITH CIRCUMFLEX] + case '\u00EF': + // ï [LATIN SMALL LETTER I WITH DIAERESIS] + case '\u0129': + // Ä© [LATIN SMALL LETTER I WITH TILDE] + case '\u012B': + // Ä« [LATIN SMALL LETTER I WITH MACRON] + case '\u012D': + // Ä­ [LATIN SMALL LETTER I WITH BREVE] + case '\u012F': + // į [LATIN SMALL LETTER I WITH OGONEK] + case '\u0131': + // ı [LATIN SMALL LETTER DOTLESS I] + case '\u01D0': + // � [LATIN SMALL LETTER I WITH CARON] + case '\u0209': + // ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE] + case '\u020B': + // È‹ [LATIN SMALL LETTER I WITH INVERTED BREVE] + case '\u0268': + // ɨ [LATIN SMALL LETTER I WITH STROKE] + case '\u1D09': + // á´‰ [LATIN SMALL LETTER TURNED I] + case '\u1D62': + // áµ¢ [LATIN SUBSCRIPT SMALL LETTER I] + case '\u1D7C': + // áµ¼ [LATIN SMALL LETTER IOTA WITH STROKE] + case '\u1D96': + // ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK] + case '\u1E2D': + // ḭ [LATIN SMALL LETTER I WITH TILDE BELOW] + case '\u1E2F': + // ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE] + case '\u1EC9': + // ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE] + case '\u1ECB': + // ị [LATIN SMALL LETTER I WITH DOT BELOW] + case '\u2071': + // � [SUPERSCRIPT LATIN SMALL LETTER I] + case '\u24D8': + // ⓘ [CIRCLED LATIN SMALL LETTER I] + case '\uFF49': // ｉ [FULLWIDTH LATIN SMALL LETTER I] + output[opos++] = 'i'; + break; + + case '\u0132': // IJ [LATIN CAPITAL LIGATURE IJ] + output[opos++] = 'I'; + output[opos++] = 'J'; + break; + + case '\u24A4': // â’¤ [PARENTHESIZED LATIN SMALL LETTER I] + output[opos++] = '('; + output[opos++] = 'i'; + output[opos++] = ')'; + break; + + case '\u0133': // ij [LATIN SMALL LIGATURE IJ] + output[opos++] = 'i'; + output[opos++] = 'j'; + break; + + case '\u0134': + // Ä´ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX] + case '\u0248': + // Ɉ [LATIN CAPITAL LETTER J WITH STROKE] + case '\u1D0A': + // á´Š [LATIN LETTER SMALL CAPITAL J] + case '\u24BF': + // â’¿ [CIRCLED LATIN CAPITAL LETTER J] + case '\uFF2A': // Ｊ [FULLWIDTH LATIN CAPITAL LETTER J] + output[opos++] = 'J'; + break; + + case '\u0135': + // ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX] + case '\u01F0': + // Ç° [LATIN SMALL LETTER J WITH CARON] + case '\u0237': + // È· [LATIN SMALL LETTER DOTLESS J] + case '\u0249': + // ɉ [LATIN SMALL LETTER J WITH STROKE] + case '\u025F': + // ÉŸ [LATIN SMALL LETTER DOTLESS J WITH STROKE] + case '\u0284': + // Ê„ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK] + case '\u029D': + // � [LATIN SMALL LETTER J WITH CROSSED-TAIL] + case '\u24D9': + // â“™ [CIRCLED LATIN SMALL LETTER J] + case '\u2C7C': + // â±¼ [LATIN SUBSCRIPT SMALL LETTER J] + case '\uFF4A': // ｊ [FULLWIDTH LATIN SMALL LETTER J] + output[opos++] = 'j'; + break; + + case '\u24A5': // â’¥ [PARENTHESIZED LATIN SMALL LETTER J] + output[opos++] = '('; + output[opos++] = 'j'; + output[opos++] = ')'; + break; + + case '\u0136': + // Ķ [LATIN CAPITAL LETTER K WITH CEDILLA] + case '\u0198': + // Ƙ [LATIN CAPITAL LETTER K WITH HOOK] + case '\u01E8': + // Ǩ [LATIN CAPITAL LETTER K WITH CARON] + case '\u1D0B': + // á´‹ [LATIN LETTER SMALL CAPITAL K] + case '\u1E30': + // Ḱ [LATIN CAPITAL LETTER K WITH ACUTE] + case '\u1E32': + // Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW] + case '\u1E34': + // Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW] + case '\u24C0': + // â“€ [CIRCLED LATIN CAPITAL LETTER K] + case '\u2C69': + // Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER] + case '\uA740': + // � [LATIN CAPITAL LETTER K WITH STROKE] + case '\uA742': + // � [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE] + case '\uA744': + // � [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE] + case '\uFF2B': // Ｋ [FULLWIDTH LATIN CAPITAL LETTER K] + output[opos++] = 'K'; + break; + + case '\u0137': + // Ä· [LATIN SMALL LETTER K WITH CEDILLA] + case '\u0199': + // Æ™ [LATIN SMALL LETTER K WITH HOOK] + case '\u01E9': + // Ç© [LATIN SMALL LETTER K WITH CARON] + case '\u029E': + // Êž [LATIN SMALL LETTER TURNED K] + case '\u1D84': + // ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK] + case '\u1E31': + // ḱ [LATIN SMALL LETTER K WITH ACUTE] + case '\u1E33': + // ḳ [LATIN SMALL LETTER K WITH DOT BELOW] + case '\u1E35': + // ḵ [LATIN SMALL LETTER K WITH LINE BELOW] + case '\u24DA': + // â“š [CIRCLED LATIN SMALL LETTER K] + case '\u2C6A': + // ⱪ [LATIN SMALL LETTER K WITH DESCENDER] + case '\uA741': + // � [LATIN SMALL LETTER K WITH STROKE] + case '\uA743': + // � [LATIN SMALL LETTER K WITH DIAGONAL STROKE] + case '\uA745': + // � [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE] + case '\uFF4B': // ｋ [FULLWIDTH LATIN SMALL LETTER K] + output[opos++] = 'k'; + break; + + case '\u24A6': // â’¦ [PARENTHESIZED LATIN SMALL LETTER K] + output[opos++] = '('; + output[opos++] = 'k'; + output[opos++] = ')'; + break; + + case '\u0139': + // Ĺ [LATIN CAPITAL LETTER L WITH ACUTE] + case '\u013B': + // Ä» [LATIN CAPITAL LETTER L WITH CEDILLA] + case '\u013D': + // Ľ [LATIN CAPITAL LETTER L WITH CARON] + case '\u013F': + // Ä¿ [LATIN CAPITAL LETTER L WITH MIDDLE DOT] + case '\u0141': + // � [LATIN CAPITAL LETTER L WITH STROKE] + case '\u023D': + // Ƚ [LATIN CAPITAL LETTER L WITH BAR] + case '\u029F': + // ÊŸ [LATIN LETTER SMALL CAPITAL L] + case '\u1D0C': + // á´Œ [LATIN LETTER SMALL CAPITAL L WITH STROKE] + case '\u1E36': + // Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW] + case '\u1E38': + // Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON] + case '\u1E3A': + // Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW] + case '\u1E3C': + // Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW] + case '\u24C1': + // � [CIRCLED LATIN CAPITAL LETTER L] + case '\u2C60': + // â±  [LATIN CAPITAL LETTER L WITH DOUBLE BAR] + case '\u2C62': + // â±¢ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE] + case '\uA746': + // � [LATIN CAPITAL LETTER BROKEN L] + case '\uA748': + // � [LATIN CAPITAL LETTER L WITH HIGH STROKE] + case '\uA780': + // Ꞁ [LATIN CAPITAL LETTER TURNED L] + case '\uFF2C': // Ｌ [FULLWIDTH LATIN CAPITAL LETTER L] + output[opos++] = 'L'; + break; + + case '\u013A': + // ĺ [LATIN SMALL LETTER L WITH ACUTE] + case '\u013C': + // ļ [LATIN SMALL LETTER L WITH CEDILLA] + case '\u013E': + // ľ [LATIN SMALL LETTER L WITH CARON] + case '\u0140': + // Å€ [LATIN SMALL LETTER L WITH MIDDLE DOT] + case '\u0142': + // Å‚ [LATIN SMALL LETTER L WITH STROKE] + case '\u019A': + // Æš [LATIN SMALL LETTER L WITH BAR] + case '\u0234': + // È´ [LATIN SMALL LETTER L WITH CURL] + case '\u026B': + // É« [LATIN SMALL LETTER L WITH MIDDLE TILDE] + case '\u026C': + // ɬ [LATIN SMALL LETTER L WITH BELT] + case '\u026D': + // É­ [LATIN SMALL LETTER L WITH RETROFLEX HOOK] + case '\u1D85': + // ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK] + case '\u1E37': + // ḷ [LATIN SMALL LETTER L WITH DOT BELOW] + case '\u1E39': + // ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON] + case '\u1E3B': + // ḻ [LATIN SMALL LETTER L WITH LINE BELOW] + case '\u1E3D': + // ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW] + case '\u24DB': + // â“› [CIRCLED LATIN SMALL LETTER L] + case '\u2C61': + // ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR] + case '\uA747': + // � [LATIN SMALL LETTER BROKEN L] + case '\uA749': + // � [LATIN SMALL LETTER L WITH HIGH STROKE] + case '\uA781': + // � [LATIN SMALL LETTER TURNED L] + case '\uFF4C': // ｌ [FULLWIDTH LATIN SMALL LETTER L] + output[opos++] = 'l'; + break; + + case '\u01C7': // LJ [LATIN CAPITAL LETTER LJ] + output[opos++] = 'L'; + output[opos++] = 'J'; + break; + + case '\u1EFA': // Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL] + output[opos++] = 'L'; + output[opos++] = 'L'; + break; + + case '\u01C8': // Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J] + output[opos++] = 'L'; + output[opos++] = 'j'; + break; + + case '\u24A7': // â’§ [PARENTHESIZED LATIN SMALL LETTER L] + output[opos++] = '('; + output[opos++] = 'l'; + output[opos++] = ')'; + break; + + case '\u01C9': // lj [LATIN SMALL LETTER LJ] + output[opos++] = 'l'; + output[opos++] = 'j'; + break; + + case '\u1EFB': // á»» [LATIN SMALL LETTER MIDDLE-WELSH LL] + output[opos++] = 'l'; + output[opos++] = 'l'; + break; + + case '\u02AA': // ʪ [LATIN SMALL LETTER LS DIGRAPH] + output[opos++] = 'l'; + output[opos++] = 's'; + break; + + case '\u02AB': // Ê« [LATIN SMALL LETTER LZ DIGRAPH] + output[opos++] = 'l'; + output[opos++] = 'z'; + break; + + case '\u019C': + // Æœ [LATIN CAPITAL LETTER TURNED M] + case '\u1D0D': + // á´� [LATIN LETTER SMALL CAPITAL M] + case '\u1E3E': + // Ḿ [LATIN CAPITAL LETTER M WITH ACUTE] + case '\u1E40': + // á¹€ [LATIN CAPITAL LETTER M WITH DOT ABOVE] + case '\u1E42': + // Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW] + case '\u24C2': + // â“‚ [CIRCLED LATIN CAPITAL LETTER M] + case '\u2C6E': + // â±® [LATIN CAPITAL LETTER M WITH HOOK] + case '\uA7FD': + // ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M] + case '\uA7FF': + // ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M] + case '\uFF2D': // ï¼­ [FULLWIDTH LATIN CAPITAL LETTER M] + output[opos++] = 'M'; + break; + + case '\u026F': + // ɯ [LATIN SMALL LETTER TURNED M] + case '\u0270': + // É° [LATIN SMALL LETTER TURNED M WITH LONG LEG] + case '\u0271': + // ɱ [LATIN SMALL LETTER M WITH HOOK] + case '\u1D6F': + // ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE] + case '\u1D86': + // ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK] + case '\u1E3F': + // ḿ [LATIN SMALL LETTER M WITH ACUTE] + case '\u1E41': + // � [LATIN SMALL LETTER M WITH DOT ABOVE] + case '\u1E43': + // ṃ [LATIN SMALL LETTER M WITH DOT BELOW] + case '\u24DC': + // â“œ [CIRCLED LATIN SMALL LETTER M] + case '\uFF4D': // � [FULLWIDTH LATIN SMALL LETTER M] + output[opos++] = 'm'; + break; + + case '\u24A8': // â’¨ [PARENTHESIZED LATIN SMALL LETTER M] + output[opos++] = '('; + output[opos++] = 'm'; + output[opos++] = ')'; + break; + + case '\u00D1': + // Ñ [LATIN CAPITAL LETTER N WITH TILDE] + case '\u0143': + // Ã…Æ’ [LATIN CAPITAL LETTER N WITH ACUTE] + case '\u0145': + // Å… [LATIN CAPITAL LETTER N WITH CEDILLA] + case '\u0147': + // Ň [LATIN CAPITAL LETTER N WITH CARON] + case '\u014A': + // Ã…Å  http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG] + case '\u019D': + // � [LATIN CAPITAL LETTER N WITH LEFT HOOK] + case '\u01F8': + // Ǹ [LATIN CAPITAL LETTER N WITH GRAVE] + case '\u0220': + // È  [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG] + case '\u0274': + // É´ [LATIN LETTER SMALL CAPITAL N] + case '\u1D0E': + // á´Ž [LATIN LETTER SMALL CAPITAL REVERSED N] + case '\u1E44': + // Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE] + case '\u1E46': + // Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW] + case '\u1E48': + // Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW] + case '\u1E4A': + // Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW] + case '\u24C3': + // Ⓝ [CIRCLED LATIN CAPITAL LETTER N] + case '\uFF2E': // ï¼® [FULLWIDTH LATIN CAPITAL LETTER N] + output[opos++] = 'N'; + break; + + case '\u00F1': + // ñ [LATIN SMALL LETTER N WITH TILDE] + case '\u0144': + // Å„ [LATIN SMALL LETTER N WITH ACUTE] + case '\u0146': + // ņ [LATIN SMALL LETTER N WITH CEDILLA] + case '\u0148': + // ň [LATIN SMALL LETTER N WITH CARON] + case '\u0149': + // ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE] + case '\u014B': + // Å‹ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG] + case '\u019E': + // Æž [LATIN SMALL LETTER N WITH LONG RIGHT LEG] + case '\u01F9': + // ǹ [LATIN SMALL LETTER N WITH GRAVE] + case '\u0235': + // ȵ [LATIN SMALL LETTER N WITH CURL] + case '\u0272': + // ɲ [LATIN SMALL LETTER N WITH LEFT HOOK] + case '\u0273': + // ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK] + case '\u1D70': + // áµ° [LATIN SMALL LETTER N WITH MIDDLE TILDE] + case '\u1D87': + // ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK] + case '\u1E45': + // á¹… [LATIN SMALL LETTER N WITH DOT ABOVE] + case '\u1E47': + // ṇ [LATIN SMALL LETTER N WITH DOT BELOW] + case '\u1E49': + // ṉ [LATIN SMALL LETTER N WITH LINE BELOW] + case '\u1E4B': + // ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW] + case '\u207F': + // � [SUPERSCRIPT LATIN SMALL LETTER N] + case '\u24DD': + // � [CIRCLED LATIN SMALL LETTER N] + case '\uFF4E': // ｎ [FULLWIDTH LATIN SMALL LETTER N] + output[opos++] = 'n'; + break; + + case '\u01CA': // ÇŠ [LATIN CAPITAL LETTER NJ] + output[opos++] = 'N'; + output[opos++] = 'J'; + break; + + case '\u01CB': // Ç‹ [LATIN CAPITAL LETTER N WITH SMALL LETTER J] + output[opos++] = 'N'; + output[opos++] = 'j'; + break; + + case '\u24A9': // â’© [PARENTHESIZED LATIN SMALL LETTER N] + output[opos++] = '('; + output[opos++] = 'n'; + output[opos++] = ')'; + break; + + case '\u01CC': // ÇŒ [LATIN SMALL LETTER NJ] + output[opos++] = 'n'; + output[opos++] = 'j'; + break; + + case '\u00D2': + // Ã’ [LATIN CAPITAL LETTER O WITH GRAVE] + case '\u00D3': + // Ó [LATIN CAPITAL LETTER O WITH ACUTE] + case '\u00D4': + // �? [LATIN CAPITAL LETTER O WITH CIRCUMFLEX] + case '\u00D5': + // Õ [LATIN CAPITAL LETTER O WITH TILDE] + case '\u00D6': + // Ö [LATIN CAPITAL LETTER O WITH DIAERESIS] + case '\u00D8': + // Ø [LATIN CAPITAL LETTER O WITH STROKE] + case '\u014C': + // Ã…Å’ [LATIN CAPITAL LETTER O WITH MACRON] + case '\u014E': + // ÅŽ [LATIN CAPITAL LETTER O WITH BREVE] + case '\u0150': + // � [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE] + case '\u0186': + // Ɔ [LATIN CAPITAL LETTER OPEN O] + case '\u019F': + // ÆŸ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE] + case '\u01A0': + // Æ  [LATIN CAPITAL LETTER O WITH HORN] + case '\u01D1': + // Ç‘ [LATIN CAPITAL LETTER O WITH CARON] + case '\u01EA': + // Ǫ [LATIN CAPITAL LETTER O WITH OGONEK] + case '\u01EC': + // Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON] + case '\u01FE': + // Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE] + case '\u020C': + // ÈŒ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE] + case '\u020E': + // ÈŽ [LATIN CAPITAL LETTER O WITH INVERTED BREVE] + case '\u022A': + // Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON] + case '\u022C': + // Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON] + case '\u022E': + // È® [LATIN CAPITAL LETTER O WITH DOT ABOVE] + case '\u0230': + // È° [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON] + case '\u1D0F': + // á´� [LATIN LETTER SMALL CAPITAL O] + case '\u1D10': + // á´� [LATIN LETTER SMALL CAPITAL OPEN O] + case '\u1E4C': + // Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE] + case '\u1E4E': + // Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS] + case '\u1E50': + // � [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE] + case '\u1E52': + // á¹’ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE] + case '\u1ECC': + // Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW] + case '\u1ECE': + // Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE] + case '\u1ED0': + // � [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE] + case '\u1ED2': + // á»’ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE] + case '\u1ED4': + // �? [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1ED6': + // á»– [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE] + case '\u1ED8': + // Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW] + case '\u1EDA': + // Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE] + case '\u1EDC': + // Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE] + case '\u1EDE': + // Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE] + case '\u1EE0': + // á»  [LATIN CAPITAL LETTER O WITH HORN AND TILDE] + case '\u1EE2': + // Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW] + case '\u24C4': + // â“„ [CIRCLED LATIN CAPITAL LETTER O] + case '\uA74A': + // � [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY] + case '\uA74C': + // � [LATIN CAPITAL LETTER O WITH LOOP] + case '\uFF2F': // Ｏ [FULLWIDTH LATIN CAPITAL LETTER O] + output[opos++] = 'O'; + break; + + case '\u00F2': + // ò [LATIN SMALL LETTER O WITH GRAVE] + case '\u00F3': + // ó [LATIN SMALL LETTER O WITH ACUTE] + case '\u00F4': + // ô [LATIN SMALL LETTER O WITH CIRCUMFLEX] + case '\u00F5': + // õ [LATIN SMALL LETTER O WITH TILDE] + case '\u00F6': + // ö [LATIN SMALL LETTER O WITH DIAERESIS] + case '\u00F8': + // ø [LATIN SMALL LETTER O WITH STROKE] + case '\u014D': + // � [LATIN SMALL LETTER O WITH MACRON] + case '\u014F': + // � [LATIN SMALL LETTER O WITH BREVE] + case '\u0151': + // Å‘ [LATIN SMALL LETTER O WITH DOUBLE ACUTE] + case '\u01A1': + // Æ¡ [LATIN SMALL LETTER O WITH HORN] + case '\u01D2': + // Ç’ [LATIN SMALL LETTER O WITH CARON] + case '\u01EB': + // Ç« [LATIN SMALL LETTER O WITH OGONEK] + case '\u01ED': + // Ç­ [LATIN SMALL LETTER O WITH OGONEK AND MACRON] + case '\u01FF': + // Ç¿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE] + case '\u020D': + // � [LATIN SMALL LETTER O WITH DOUBLE GRAVE] + case '\u020F': + // � [LATIN SMALL LETTER O WITH INVERTED BREVE] + case '\u022B': + // È« [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON] + case '\u022D': + // È­ [LATIN SMALL LETTER O WITH TILDE AND MACRON] + case '\u022F': + // ȯ [LATIN SMALL LETTER O WITH DOT ABOVE] + case '\u0231': + // ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON] + case '\u0254': + // �? [LATIN SMALL LETTER OPEN O] + case '\u0275': + // ɵ [LATIN SMALL LETTER BARRED O] + case '\u1D16': + // á´– [LATIN SMALL LETTER TOP HALF O] + case '\u1D17': + // á´— [LATIN SMALL LETTER BOTTOM HALF O] + case '\u1D97': + // ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK] + case '\u1E4D': + // � [LATIN SMALL LETTER O WITH TILDE AND ACUTE] + case '\u1E4F': + // � [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS] + case '\u1E51': + // ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE] + case '\u1E53': + // ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE] + case '\u1ECD': + // � [LATIN SMALL LETTER O WITH DOT BELOW] + case '\u1ECF': + // � [LATIN SMALL LETTER O WITH HOOK ABOVE] + case '\u1ED1': + // ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE] + case '\u1ED3': + // ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE] + case '\u1ED5': + // ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] + case '\u1ED7': + // á»— [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE] + case '\u1ED9': + // á»™ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW] + case '\u1EDB': + // á»› [LATIN SMALL LETTER O WITH HORN AND ACUTE] + case '\u1EDD': + // � [LATIN SMALL LETTER O WITH HORN AND GRAVE] + case '\u1EDF': + // ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE] + case '\u1EE1': + // ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE] + case '\u1EE3': + // ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW] + case '\u2092': + // â‚’ [LATIN SUBSCRIPT SMALL LETTER O] + case '\u24DE': + // â“ž [CIRCLED LATIN SMALL LETTER O] + case '\u2C7A': + // ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE] + case '\uA74B': + // � [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY] + case '\uA74D': + // � [LATIN SMALL LETTER O WITH LOOP] + case '\uFF4F': // � [FULLWIDTH LATIN SMALL LETTER O] + output[opos++] = 'o'; + break; + + case '\u0152': + // Å’ [LATIN CAPITAL LIGATURE OE] + case '\u0276': // ɶ [LATIN LETTER SMALL CAPITAL OE] + output[opos++] = 'O'; + output[opos++] = 'E'; + break; + + case '\uA74E': // � [LATIN CAPITAL LETTER OO] + output[opos++] = 'O'; + output[opos++] = 'O'; + break; + + case '\u0222': + // È¢ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU] + case '\u1D15': // á´• [LATIN LETTER SMALL CAPITAL OU] + output[opos++] = 'O'; + output[opos++] = 'U'; + break; + + case '\u24AA': // â’ª [PARENTHESIZED LATIN SMALL LETTER O] + output[opos++] = '('; + output[opos++] = 'o'; + output[opos++] = ')'; + break; + + case '\u0153': + // Å“ [LATIN SMALL LIGATURE OE] + case '\u1D14': // á´�? [LATIN SMALL LETTER TURNED OE] + output[opos++] = 'o'; + output[opos++] = 'e'; + break; + + case '\uA74F': // � [LATIN SMALL LETTER OO] + output[opos++] = 'o'; + output[opos++] = 'o'; + break; + + case '\u0223': // È£ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU] + output[opos++] = 'o'; + output[opos++] = 'u'; + break; + + case '\u01A4': + // Ƥ [LATIN CAPITAL LETTER P WITH HOOK] + case '\u1D18': + // á´˜ [LATIN LETTER SMALL CAPITAL P] + case '\u1E54': + // �? [LATIN CAPITAL LETTER P WITH ACUTE] + case '\u1E56': + // á¹– [LATIN CAPITAL LETTER P WITH DOT ABOVE] + case '\u24C5': + // â“… [CIRCLED LATIN CAPITAL LETTER P] + case '\u2C63': + // â±£ [LATIN CAPITAL LETTER P WITH STROKE] + case '\uA750': + // � [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER] + case '\uA752': + // � [LATIN CAPITAL LETTER P WITH FLOURISH] + case '\uA754': + // �? [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL] + case '\uFF30': // ï¼° [FULLWIDTH LATIN CAPITAL LETTER P] + output[opos++] = 'P'; + break; + + case '\u01A5': + // Æ¥ [LATIN SMALL LETTER P WITH HOOK] + case '\u1D71': + // áµ± [LATIN SMALL LETTER P WITH MIDDLE TILDE] + case '\u1D7D': + // áµ½ [LATIN SMALL LETTER P WITH STROKE] + case '\u1D88': + // ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK] + case '\u1E55': + // ṕ [LATIN SMALL LETTER P WITH ACUTE] + case '\u1E57': + // á¹— [LATIN SMALL LETTER P WITH DOT ABOVE] + case '\u24DF': + // â“Ÿ [CIRCLED LATIN SMALL LETTER P] + case '\uA751': + // � [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER] + case '\uA753': + // � [LATIN SMALL LETTER P WITH FLOURISH] + case '\uA755': + // � [LATIN SMALL LETTER P WITH SQUIRREL TAIL] + case '\uA7FC': + // ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P] + case '\uFF50': // � [FULLWIDTH LATIN SMALL LETTER P] + output[opos++] = 'p'; + break; + + case '\u24AB': // â’« [PARENTHESIZED LATIN SMALL LETTER P] + output[opos++] = '('; + output[opos++] = 'p'; + output[opos++] = ')'; + break; + + case '\u024A': + // ÉŠ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL] + case '\u24C6': + // Ⓠ [CIRCLED LATIN CAPITAL LETTER Q] + case '\uA756': + // � [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER] + case '\uA758': + // � [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE] + case '\uFF31': // ï¼± [FULLWIDTH LATIN CAPITAL LETTER Q] + output[opos++] = 'Q'; + break; + + case '\u0138': + // ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA] + case '\u024B': + // É‹ [LATIN SMALL LETTER Q WITH HOOK TAIL] + case '\u02A0': + // Ê  [LATIN SMALL LETTER Q WITH HOOK] + case '\u24E0': + // â“  [CIRCLED LATIN SMALL LETTER Q] + case '\uA757': + // � [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER] + case '\uA759': + // � [LATIN SMALL LETTER Q WITH DIAGONAL STROKE] + case '\uFF51': // ｑ [FULLWIDTH LATIN SMALL LETTER Q] + output[opos++] = 'q'; + break; + + case '\u24AC': // â’¬ [PARENTHESIZED LATIN SMALL LETTER Q] + output[opos++] = '('; + output[opos++] = 'q'; + output[opos++] = ')'; + break; + + case '\u0239': // ȹ [LATIN SMALL LETTER QP DIGRAPH] + output[opos++] = 'q'; + output[opos++] = 'p'; + break; + + case '\u0154': + // �? [LATIN CAPITAL LETTER R WITH ACUTE] + case '\u0156': + // Å– [LATIN CAPITAL LETTER R WITH CEDILLA] + case '\u0158': + // Ã…Ëœ [LATIN CAPITAL LETTER R WITH CARON] + case '\u0210': + // È’ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE] + case '\u0212': + // È’ [LATIN CAPITAL LETTER R WITH INVERTED BREVE] + case '\u024C': + // ÉŒ [LATIN CAPITAL LETTER R WITH STROKE] + case '\u0280': + // Ê€ [LATIN LETTER SMALL CAPITAL R] + case '\u0281': + // � [LATIN LETTER SMALL CAPITAL INVERTED R] + case '\u1D19': + // á´™ [LATIN LETTER SMALL CAPITAL REVERSED R] + case '\u1D1A': + // á´š [LATIN LETTER SMALL CAPITAL TURNED R] + case '\u1E58': + // Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE] + case '\u1E5A': + // Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW] + case '\u1E5C': + // Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON] + case '\u1E5E': + // Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW] + case '\u24C7': + // Ⓡ [CIRCLED LATIN CAPITAL LETTER R] + case '\u2C64': + // Ɽ [LATIN CAPITAL LETTER R WITH TAIL] + case '\uA75A': + // � [LATIN CAPITAL LETTER R ROTUNDA] + case '\uA782': + // êž‚ [LATIN CAPITAL LETTER INSULAR R] + case '\uFF32': // ï¼² [FULLWIDTH LATIN CAPITAL LETTER R] + output[opos++] = 'R'; + break; + + case '\u0155': + // Å• [LATIN SMALL LETTER R WITH ACUTE] + case '\u0157': + // Å— [LATIN SMALL LETTER R WITH CEDILLA] + case '\u0159': + // Ã…â„¢ [LATIN SMALL LETTER R WITH CARON] + case '\u0211': + // È‘ [LATIN SMALL LETTER R WITH DOUBLE GRAVE] + case '\u0213': + // È“ [LATIN SMALL LETTER R WITH INVERTED BREVE] + case '\u024D': + // � [LATIN SMALL LETTER R WITH STROKE] + case '\u027C': + // ɼ [LATIN SMALL LETTER R WITH LONG LEG] + case '\u027D': + // ɽ [LATIN SMALL LETTER R WITH TAIL] + case '\u027E': + // ɾ [LATIN SMALL LETTER R WITH FISHHOOK] + case '\u027F': + // É¿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK] + case '\u1D63': + // áµ£ [LATIN SUBSCRIPT SMALL LETTER R] + case '\u1D72': + // áµ² [LATIN SMALL LETTER R WITH MIDDLE TILDE] + case '\u1D73': + // áµ³ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE] + case '\u1D89': + // ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK] + case '\u1E59': + // á¹™ [LATIN SMALL LETTER R WITH DOT ABOVE] + case '\u1E5B': + // á¹› [LATIN SMALL LETTER R WITH DOT BELOW] + case '\u1E5D': + // � [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON] + case '\u1E5F': + // ṟ [LATIN SMALL LETTER R WITH LINE BELOW] + case '\u24E1': + // â“¡ [CIRCLED LATIN SMALL LETTER R] + case '\uA75B': + // � [LATIN SMALL LETTER R ROTUNDA] + case '\uA783': + // ꞃ [LATIN SMALL LETTER INSULAR R] + case '\uFF52': // ï½’ [FULLWIDTH LATIN SMALL LETTER R] + output[opos++] = 'r'; + break; + + case '\u24AD': // â’­ [PARENTHESIZED LATIN SMALL LETTER R] + output[opos++] = '('; + output[opos++] = 'r'; + output[opos++] = ')'; + break; + + case '\u015A': + // Ã…Å¡ [LATIN CAPITAL LETTER S WITH ACUTE] + case '\u015C': + // Ã…Å“ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX] + case '\u015E': + // Åž [LATIN CAPITAL LETTER S WITH CEDILLA] + case '\u0160': + // Å  [LATIN CAPITAL LETTER S WITH CARON] + case '\u0218': + // Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW] + case '\u1E60': + // á¹  [LATIN CAPITAL LETTER S WITH DOT ABOVE] + case '\u1E62': + // á¹¢ [LATIN CAPITAL LETTER S WITH DOT BELOW] + case '\u1E64': + // Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE] + case '\u1E66': + // Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE] + case '\u1E68': + // Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE] + case '\u24C8': + // Ⓢ [CIRCLED LATIN CAPITAL LETTER S] + case '\uA731': + // ꜱ [LATIN LETTER SMALL CAPITAL S] + case '\uA785': + // êž… [LATIN SMALL LETTER INSULAR S] + case '\uFF33': // ï¼³ [FULLWIDTH LATIN CAPITAL LETTER S] + output[opos++] = 'S'; + break; + + case '\u015B': + // Å› [LATIN SMALL LETTER S WITH ACUTE] + case '\u015D': + // � [LATIN SMALL LETTER S WITH CIRCUMFLEX] + case '\u015F': + // ÅŸ [LATIN SMALL LETTER S WITH CEDILLA] + case '\u0161': + // Å¡ [LATIN SMALL LETTER S WITH CARON] + case '\u017F': + // Å¿ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S] + case '\u0219': + // È™ [LATIN SMALL LETTER S WITH COMMA BELOW] + case '\u023F': + // È¿ [LATIN SMALL LETTER S WITH SWASH TAIL] + case '\u0282': + // Ê‚ [LATIN SMALL LETTER S WITH HOOK] + case '\u1D74': + // áµ´ [LATIN SMALL LETTER S WITH MIDDLE TILDE] + case '\u1D8A': + // ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK] + case '\u1E61': + // ṡ [LATIN SMALL LETTER S WITH DOT ABOVE] + case '\u1E63': + // á¹£ [LATIN SMALL LETTER S WITH DOT BELOW] + case '\u1E65': + // á¹¥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE] + case '\u1E67': + // ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE] + case '\u1E69': + // ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE] + case '\u1E9C': + // ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE] + case '\u1E9D': + // � [LATIN SMALL LETTER LONG S WITH HIGH STROKE] + case '\u24E2': + // â“¢ [CIRCLED LATIN SMALL LETTER S] + case '\uA784': + // êž„ [LATIN CAPITAL LETTER INSULAR S] + case '\uFF53': // ｓ [FULLWIDTH LATIN SMALL LETTER S] + output[opos++] = 's'; + break; + + case '\u1E9E': // ẞ [LATIN CAPITAL LETTER SHARP S] + output[opos++] = 'S'; + output[opos++] = 'S'; + break; + + case '\u24AE': // â’® [PARENTHESIZED LATIN SMALL LETTER S] + output[opos++] = '('; + output[opos++] = 's'; + output[opos++] = ')'; + break; + + case '\u00DF': // ß [LATIN SMALL LETTER SHARP S] + output[opos++] = 's'; + output[opos++] = 's'; + break; + + case '\uFB06': // st [LATIN SMALL LIGATURE ST] + output[opos++] = 's'; + output[opos++] = 't'; + break; + + case '\u0162': + // Å¢ [LATIN CAPITAL LETTER T WITH CEDILLA] + case '\u0164': + // Ť [LATIN CAPITAL LETTER T WITH CARON] + case '\u0166': + // Ŧ [LATIN CAPITAL LETTER T WITH STROKE] + case '\u01AC': + // Ƭ [LATIN CAPITAL LETTER T WITH HOOK] + case '\u01AE': + // Æ® [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK] + case '\u021A': + // Èš [LATIN CAPITAL LETTER T WITH COMMA BELOW] + case '\u023E': + // Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE] + case '\u1D1B': + // á´› [LATIN LETTER SMALL CAPITAL T] + case '\u1E6A': + // Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE] + case '\u1E6C': + // Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW] + case '\u1E6E': + // á¹® [LATIN CAPITAL LETTER T WITH LINE BELOW] + case '\u1E70': + // á¹° [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW] + case '\u24C9': + // Ⓣ [CIRCLED LATIN CAPITAL LETTER T] + case '\uA786': + // Ꞇ [LATIN CAPITAL LETTER INSULAR T] + case '\uFF34': // ï¼´ [FULLWIDTH LATIN CAPITAL LETTER T] + output[opos++] = 'T'; + break; + + case '\u0163': + // Å£ [LATIN SMALL LETTER T WITH CEDILLA] + case '\u0165': + // Ã…Â¥ [LATIN SMALL LETTER T WITH CARON] + case '\u0167': + // ŧ [LATIN SMALL LETTER T WITH STROKE] + case '\u01AB': + // Æ« [LATIN SMALL LETTER T WITH PALATAL HOOK] + case '\u01AD': + // Æ­ [LATIN SMALL LETTER T WITH HOOK] + case '\u021B': + // È› [LATIN SMALL LETTER T WITH COMMA BELOW] + case '\u0236': + // ȶ [LATIN SMALL LETTER T WITH CURL] + case '\u0287': + // ʇ [LATIN SMALL LETTER TURNED T] + case '\u0288': + // ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK] + case '\u1D75': + // áµµ [LATIN SMALL LETTER T WITH MIDDLE TILDE] + case '\u1E6B': + // ṫ [LATIN SMALL LETTER T WITH DOT ABOVE] + case '\u1E6D': + // á¹­ [LATIN SMALL LETTER T WITH DOT BELOW] + case '\u1E6F': + // ṯ [LATIN SMALL LETTER T WITH LINE BELOW] + case '\u1E71': + // á¹± [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW] + case '\u1E97': + // ẗ [LATIN SMALL LETTER T WITH DIAERESIS] + case '\u24E3': + // â“£ [CIRCLED LATIN SMALL LETTER T] + case '\u2C66': + // ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE] + case '\uFF54': // �? [FULLWIDTH LATIN SMALL LETTER T] + output[opos++] = 't'; + break; + + case '\u00DE': + // Þ [LATIN CAPITAL LETTER THORN] + case '\uA766': // � [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER] + output[opos++] = 'T'; + output[opos++] = 'H'; + break; + + case '\uA728': // Ꜩ [LATIN CAPITAL LETTER TZ] + output[opos++] = 'T'; + output[opos++] = 'Z'; + break; + + case '\u24AF': // â’¯ [PARENTHESIZED LATIN SMALL LETTER T] + output[opos++] = '('; + output[opos++] = 't'; + output[opos++] = ')'; + break; + + case '\u02A8': // ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL] + output[opos++] = 't'; + output[opos++] = 'c'; + break; + + case '\u00FE': + // þ [LATIN SMALL LETTER THORN] + case '\u1D7A': + // ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH] + case '\uA767': // � [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER] + output[opos++] = 't'; + output[opos++] = 'h'; + break; + + case '\u02A6': // ʦ [LATIN SMALL LETTER TS DIGRAPH] + output[opos++] = 't'; + output[opos++] = 's'; + break; + + case '\uA729': // ꜩ [LATIN SMALL LETTER TZ] + output[opos++] = 't'; + output[opos++] = 'z'; + break; + + case '\u00D9': + // Ù [LATIN CAPITAL LETTER U WITH GRAVE] + case '\u00DA': + // Ú [LATIN CAPITAL LETTER U WITH ACUTE] + case '\u00DB': + // Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX] + case '\u00DC': + // Ãœ [LATIN CAPITAL LETTER U WITH DIAERESIS] + case '\u0168': + // Ũ [LATIN CAPITAL LETTER U WITH TILDE] + case '\u016A': + // Ū [LATIN CAPITAL LETTER U WITH MACRON] + case '\u016C': + // Ŭ [LATIN CAPITAL LETTER U WITH BREVE] + case '\u016E': + // Å® [LATIN CAPITAL LETTER U WITH RING ABOVE] + case '\u0170': + // Å° [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE] + case '\u0172': + // Ų [LATIN CAPITAL LETTER U WITH OGONEK] + case '\u01AF': + // Ư [LATIN CAPITAL LETTER U WITH HORN] + case '\u01D3': + // Ç“ [LATIN CAPITAL LETTER U WITH CARON] + case '\u01D5': + // Ç• [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON] + case '\u01D7': + // Ç— [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE] + case '\u01D9': + // Ç™ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON] + case '\u01DB': + // Ç› [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE] + case '\u0214': + // �? [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE] + case '\u0216': + // È– [LATIN CAPITAL LETTER U WITH INVERTED BREVE] + case '\u0244': + // É„ [LATIN CAPITAL LETTER U BAR] + case '\u1D1C': + // á´œ [LATIN LETTER SMALL CAPITAL U] + case '\u1D7E': + // áµ¾ [LATIN SMALL CAPITAL LETTER U WITH STROKE] + case '\u1E72': + // á¹² [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW] + case '\u1E74': + // á¹´ [LATIN CAPITAL LETTER U WITH TILDE BELOW] + case '\u1E76': + // Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW] + case '\u1E78': + // Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE] + case '\u1E7A': + // Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS] + case '\u1EE4': + // Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW] + case '\u1EE6': + // Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE] + case '\u1EE8': + // Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE] + case '\u1EEA': + // Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE] + case '\u1EEC': + // Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE] + case '\u1EEE': + // á»® [LATIN CAPITAL LETTER U WITH HORN AND TILDE] + case '\u1EF0': + // á»° [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW] + case '\u24CA': + // â“Š [CIRCLED LATIN CAPITAL LETTER U] + case '\uFF35': // ï¼µ [FULLWIDTH LATIN CAPITAL LETTER U] + output[opos++] = 'U'; + break; + + case '\u00F9': + // ù [LATIN SMALL LETTER U WITH GRAVE] + case '\u00FA': + // ú [LATIN SMALL LETTER U WITH ACUTE] + case '\u00FB': + // û [LATIN SMALL LETTER U WITH CIRCUMFLEX] + case '\u00FC': + // ü [LATIN SMALL LETTER U WITH DIAERESIS] + case '\u0169': + // Å© [LATIN SMALL LETTER U WITH TILDE] + case '\u016B': + // Å« [LATIN SMALL LETTER U WITH MACRON] + case '\u016D': + // Å­ [LATIN SMALL LETTER U WITH BREVE] + case '\u016F': + // ů [LATIN SMALL LETTER U WITH RING ABOVE] + case '\u0171': + // ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE] + case '\u0173': + // ų [LATIN SMALL LETTER U WITH OGONEK] + case '\u01B0': + // Æ° [LATIN SMALL LETTER U WITH HORN] + case '\u01D4': + // �? [LATIN SMALL LETTER U WITH CARON] + case '\u01D6': + // Ç– [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON] + case '\u01D8': + // ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE] + case '\u01DA': + // Çš [LATIN SMALL LETTER U WITH DIAERESIS AND CARON] + case '\u01DC': + // Çœ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE] + case '\u0215': + // È• [LATIN SMALL LETTER U WITH DOUBLE GRAVE] + case '\u0217': + // È— [LATIN SMALL LETTER U WITH INVERTED BREVE] + case '\u0289': + // ʉ [LATIN SMALL LETTER U BAR] + case '\u1D64': + // ᵤ [LATIN SUBSCRIPT SMALL LETTER U] + case '\u1D99': + // ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK] + case '\u1E73': + // á¹³ [LATIN SMALL LETTER U WITH DIAERESIS BELOW] + case '\u1E75': + // á¹µ [LATIN SMALL LETTER U WITH TILDE BELOW] + case '\u1E77': + // á¹· [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW] + case '\u1E79': + // á¹¹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE] + case '\u1E7B': + // á¹» [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS] + case '\u1EE5': + // ụ [LATIN SMALL LETTER U WITH DOT BELOW] + case '\u1EE7': + // ủ [LATIN SMALL LETTER U WITH HOOK ABOVE] + case '\u1EE9': + // ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE] + case '\u1EEB': + // ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE] + case '\u1EED': + // á»­ [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE] + case '\u1EEF': + // ữ [LATIN SMALL LETTER U WITH HORN AND TILDE] + case '\u1EF1': + // á»± [LATIN SMALL LETTER U WITH HORN AND DOT BELOW] + case '\u24E4': + // ⓤ [CIRCLED LATIN SMALL LETTER U] + case '\uFF55': // ｕ [FULLWIDTH LATIN SMALL LETTER U] + output[opos++] = 'u'; + break; + + case '\u24B0': // â’° [PARENTHESIZED LATIN SMALL LETTER U] + output[opos++] = '('; + output[opos++] = 'u'; + output[opos++] = ')'; + break; + + case '\u1D6B': // ᵫ [LATIN SMALL LETTER UE] + output[opos++] = 'u'; + output[opos++] = 'e'; + break; + + case '\u01B2': + // Ʋ [LATIN CAPITAL LETTER V WITH HOOK] + case '\u0245': + // É… [LATIN CAPITAL LETTER TURNED V] + case '\u1D20': + // á´  [LATIN LETTER SMALL CAPITAL V] + case '\u1E7C': + // á¹¼ [LATIN CAPITAL LETTER V WITH TILDE] + case '\u1E7E': + // á¹¾ [LATIN CAPITAL LETTER V WITH DOT BELOW] + case '\u1EFC': + // Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V] + case '\u24CB': + // â“‹ [CIRCLED LATIN CAPITAL LETTER V] + case '\uA75E': + // � [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE] + case '\uA768': + // � [LATIN CAPITAL LETTER VEND] + case '\uFF36': // Ｖ [FULLWIDTH LATIN CAPITAL LETTER V] + output[opos++] = 'V'; + break; + + case '\u028B': + // Ê‹ [LATIN SMALL LETTER V WITH HOOK] + case '\u028C': + // ÊŒ [LATIN SMALL LETTER TURNED V] + case '\u1D65': + // áµ¥ [LATIN SUBSCRIPT SMALL LETTER V] + case '\u1D8C': + // ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK] + case '\u1E7D': + // á¹½ [LATIN SMALL LETTER V WITH TILDE] + case '\u1E7F': + // ṿ [LATIN SMALL LETTER V WITH DOT BELOW] + case '\u24E5': + // â“¥ [CIRCLED LATIN SMALL LETTER V] + case '\u2C71': + // â±± [LATIN SMALL LETTER V WITH RIGHT HOOK] + case '\u2C74': + // â±´ [LATIN SMALL LETTER V WITH CURL] + case '\uA75F': + // � [LATIN SMALL LETTER V WITH DIAGONAL STROKE] + case '\uFF56': // ï½– [FULLWIDTH LATIN SMALL LETTER V] + output[opos++] = 'v'; + break; + + case '\uA760': // � [LATIN CAPITAL LETTER VY] + output[opos++] = 'V'; + output[opos++] = 'Y'; + break; + + case '\u24B1': // â’± [PARENTHESIZED LATIN SMALL LETTER V] + output[opos++] = '('; + output[opos++] = 'v'; + output[opos++] = ')'; + break; + + case '\uA761': // � [LATIN SMALL LETTER VY] + output[opos++] = 'v'; + output[opos++] = 'y'; + break; + + case '\u0174': + // Å´ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX] + case '\u01F7': + // Ç· http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN] + case '\u1D21': + // á´¡ [LATIN LETTER SMALL CAPITAL W] + case '\u1E80': + // Ẁ [LATIN CAPITAL LETTER W WITH GRAVE] + case '\u1E82': + // Ẃ [LATIN CAPITAL LETTER W WITH ACUTE] + case '\u1E84': + // Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS] + case '\u1E86': + // Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE] + case '\u1E88': + // Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW] + case '\u24CC': + // â“Œ [CIRCLED LATIN CAPITAL LETTER W] + case '\u2C72': + // â±² [LATIN CAPITAL LETTER W WITH HOOK] + case '\uFF37': // ï¼· [FULLWIDTH LATIN CAPITAL LETTER W] + output[opos++] = 'W'; + break; + + case '\u0175': + // ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX] + case '\u01BF': + // Æ¿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN] + case '\u028D': + // � [LATIN SMALL LETTER TURNED W] + case '\u1E81': + // � [LATIN SMALL LETTER W WITH GRAVE] + case '\u1E83': + // ẃ [LATIN SMALL LETTER W WITH ACUTE] + case '\u1E85': + // ẅ [LATIN SMALL LETTER W WITH DIAERESIS] + case '\u1E87': + // ẇ [LATIN SMALL LETTER W WITH DOT ABOVE] + case '\u1E89': + // ẉ [LATIN SMALL LETTER W WITH DOT BELOW] + case '\u1E98': + // ẘ [LATIN SMALL LETTER W WITH RING ABOVE] + case '\u24E6': + // ⓦ [CIRCLED LATIN SMALL LETTER W] + case '\u2C73': + // â±³ [LATIN SMALL LETTER W WITH HOOK] + case '\uFF57': // ï½— [FULLWIDTH LATIN SMALL LETTER W] + output[opos++] = 'w'; + break; + + case '\u24B2': // â’² [PARENTHESIZED LATIN SMALL LETTER W] + output[opos++] = '('; + output[opos++] = 'w'; + output[opos++] = ')'; + break; + + case '\u1E8A': + // Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE] + case '\u1E8C': + // Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS] + case '\u24CD': + // � [CIRCLED LATIN CAPITAL LETTER X] + case '\uFF38': // Ｘ [FULLWIDTH LATIN CAPITAL LETTER X] + output[opos++] = 'X'; + break; + + case '\u1D8D': + // � [LATIN SMALL LETTER X WITH PALATAL HOOK] + case '\u1E8B': + // ẋ [LATIN SMALL LETTER X WITH DOT ABOVE] + case '\u1E8D': + // � [LATIN SMALL LETTER X WITH DIAERESIS] + case '\u2093': + // â‚“ [LATIN SUBSCRIPT SMALL LETTER X] + case '\u24E7': + // ⓧ [CIRCLED LATIN SMALL LETTER X] + case '\uFF58': // ｘ [FULLWIDTH LATIN SMALL LETTER X] + output[opos++] = 'x'; + break; + + case '\u24B3': // â’³ [PARENTHESIZED LATIN SMALL LETTER X] + output[opos++] = '('; + output[opos++] = 'x'; + output[opos++] = ')'; + break; + + case '\u00DD': + // � [LATIN CAPITAL LETTER Y WITH ACUTE] + case '\u0176': + // Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX] + case '\u0178': + // Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS] + case '\u01B3': + // Ƴ [LATIN CAPITAL LETTER Y WITH HOOK] + case '\u0232': + // Ȳ [LATIN CAPITAL LETTER Y WITH MACRON] + case '\u024E': + // ÉŽ [LATIN CAPITAL LETTER Y WITH STROKE] + case '\u028F': + // � [LATIN LETTER SMALL CAPITAL Y] + case '\u1E8E': + // Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE] + case '\u1EF2': + // Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE] + case '\u1EF4': + // á»´ [LATIN CAPITAL LETTER Y WITH DOT BELOW] + case '\u1EF6': + // Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE] + case '\u1EF8': + // Ỹ [LATIN CAPITAL LETTER Y WITH TILDE] + case '\u1EFE': + // Ỿ [LATIN CAPITAL LETTER Y WITH LOOP] + case '\u24CE': + // â“Ž [CIRCLED LATIN CAPITAL LETTER Y] + case '\uFF39': // ï¼¹ [FULLWIDTH LATIN CAPITAL LETTER Y] + output[opos++] = 'Y'; + break; + + case '\u00FD': + // ý [LATIN SMALL LETTER Y WITH ACUTE] + case '\u00FF': + // ÿ [LATIN SMALL LETTER Y WITH DIAERESIS] + case '\u0177': + // Å· [LATIN SMALL LETTER Y WITH CIRCUMFLEX] + case '\u01B4': + // Æ´ [LATIN SMALL LETTER Y WITH HOOK] + case '\u0233': + // ȳ [LATIN SMALL LETTER Y WITH MACRON] + case '\u024F': + // � [LATIN SMALL LETTER Y WITH STROKE] + case '\u028E': + // ÊŽ [LATIN SMALL LETTER TURNED Y] + case '\u1E8F': + // � [LATIN SMALL LETTER Y WITH DOT ABOVE] + case '\u1E99': + // ẙ [LATIN SMALL LETTER Y WITH RING ABOVE] + case '\u1EF3': + // ỳ [LATIN SMALL LETTER Y WITH GRAVE] + case '\u1EF5': + // ỵ [LATIN SMALL LETTER Y WITH DOT BELOW] + case '\u1EF7': + // á»· [LATIN SMALL LETTER Y WITH HOOK ABOVE] + case '\u1EF9': + // ỹ [LATIN SMALL LETTER Y WITH TILDE] + case '\u1EFF': + // ỿ [LATIN SMALL LETTER Y WITH LOOP] + case '\u24E8': + // ⓨ [CIRCLED LATIN SMALL LETTER Y] + case '\uFF59': // ï½™ [FULLWIDTH LATIN SMALL LETTER Y] + output[opos++] = 'y'; + break; + + case '\u24B4': // â’´ [PARENTHESIZED LATIN SMALL LETTER Y] + output[opos++] = '('; + output[opos++] = 'y'; + output[opos++] = ')'; + break; + + case '\u0179': + // Ź [LATIN CAPITAL LETTER Z WITH ACUTE] + case '\u017B': + // Å» [LATIN CAPITAL LETTER Z WITH DOT ABOVE] + case '\u017D': + // Ž [LATIN CAPITAL LETTER Z WITH CARON] + case '\u01B5': + // Ƶ [LATIN CAPITAL LETTER Z WITH STROKE] + case '\u021C': + // Èœ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH] + case '\u0224': + // Ȥ [LATIN CAPITAL LETTER Z WITH HOOK] + case '\u1D22': + // á´¢ [LATIN LETTER SMALL CAPITAL Z] + case '\u1E90': + // � [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX] + case '\u1E92': + // Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW] + case '\u1E94': + // �? [LATIN CAPITAL LETTER Z WITH LINE BELOW] + case '\u24CF': + // � [CIRCLED LATIN CAPITAL LETTER Z] + case '\u2C6B': + // Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER] + case '\uA762': + // � [LATIN CAPITAL LETTER VISIGOTHIC Z] + case '\uFF3A': // Ｚ [FULLWIDTH LATIN CAPITAL LETTER Z] + output[opos++] = 'Z'; + break; + + case '\u017A': + // ź [LATIN SMALL LETTER Z WITH ACUTE] + case '\u017C': + // ż [LATIN SMALL LETTER Z WITH DOT ABOVE] + case '\u017E': + // ž [LATIN SMALL LETTER Z WITH CARON] + case '\u01B6': + // ƶ [LATIN SMALL LETTER Z WITH STROKE] + case '\u021D': + // � http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH] + case '\u0225': + // È¥ [LATIN SMALL LETTER Z WITH HOOK] + case '\u0240': + // É€ [LATIN SMALL LETTER Z WITH SWASH TAIL] + case '\u0290': + // � [LATIN SMALL LETTER Z WITH RETROFLEX HOOK] + case '\u0291': + // Ê‘ [LATIN SMALL LETTER Z WITH CURL] + case '\u1D76': + // ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE] + case '\u1D8E': + // ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK] + case '\u1E91': + // ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX] + case '\u1E93': + // ẓ [LATIN SMALL LETTER Z WITH DOT BELOW] + case '\u1E95': + // ẕ [LATIN SMALL LETTER Z WITH LINE BELOW] + case '\u24E9': + // â“© [CIRCLED LATIN SMALL LETTER Z] + case '\u2C6C': + // ⱬ [LATIN SMALL LETTER Z WITH DESCENDER] + case '\uA763': + // � [LATIN SMALL LETTER VISIGOTHIC Z] + case '\uFF5A': // ｚ [FULLWIDTH LATIN SMALL LETTER Z] + output[opos++] = 'z'; + break; + + case '\u24B5': // â’µ [PARENTHESIZED LATIN SMALL LETTER Z] + output[opos++] = '('; + output[opos++] = 'z'; + output[opos++] = ')'; + break; + + case '\u2070': + // � [SUPERSCRIPT ZERO] + case '\u2080': + // â‚€ [SUBSCRIPT ZERO] + case '\u24EA': + // ⓪ [CIRCLED DIGIT ZERO] + case '\u24FF': + // â“¿ [NEGATIVE CIRCLED DIGIT ZERO] + case '\uFF10': // � [FULLWIDTH DIGIT ZERO] + output[opos++] = '0'; + break; + + case '\u00B9': + // ¹ [SUPERSCRIPT ONE] + case '\u2081': + // � [SUBSCRIPT ONE] + case '\u2460': + // â‘  [CIRCLED DIGIT ONE] + case '\u24F5': + // ⓵ [DOUBLE CIRCLED DIGIT ONE] + case '\u2776': + // � [DINGBAT NEGATIVE CIRCLED DIGIT ONE] + case '\u2780': + // ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE] + case '\u278A': + // ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE] + case '\uFF11': // １ [FULLWIDTH DIGIT ONE] + output[opos++] = '1'; + break; + + case '\u2488': // â’ˆ [DIGIT ONE FULL STOP] + output[opos++] = '1'; + output[opos++] = '.'; + break; + + case '\u2474': // â‘´ [PARENTHESIZED DIGIT ONE] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = ')'; + break; + + case '\u00B2': + // ² [SUPERSCRIPT TWO] + case '\u2082': + // â‚‚ [SUBSCRIPT TWO] + case '\u2461': + // â‘¡ [CIRCLED DIGIT TWO] + case '\u24F6': + // ⓶ [DOUBLE CIRCLED DIGIT TWO] + case '\u2777': + // � [DINGBAT NEGATIVE CIRCLED DIGIT TWO] + case '\u2781': + // � [DINGBAT CIRCLED SANS-SERIF DIGIT TWO] + case '\u278B': + // âž‹ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO] + case '\uFF12': // ï¼’ [FULLWIDTH DIGIT TWO] + output[opos++] = '2'; + break; + + case '\u2489': // â’‰ [DIGIT TWO FULL STOP] + output[opos++] = '2'; + output[opos++] = '.'; + break; + + case '\u2475': // ⑵ [PARENTHESIZED DIGIT TWO] + output[opos++] = '('; + output[opos++] = '2'; + output[opos++] = ')'; + break; + + case '\u00B3': + // ³ [SUPERSCRIPT THREE] + case '\u2083': + // ₃ [SUBSCRIPT THREE] + case '\u2462': + // â‘¢ [CIRCLED DIGIT THREE] + case '\u24F7': + // â“· [DOUBLE CIRCLED DIGIT THREE] + case '\u2778': + // � [DINGBAT NEGATIVE CIRCLED DIGIT THREE] + case '\u2782': + // âž‚ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE] + case '\u278C': + // ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE] + case '\uFF13': // ３ [FULLWIDTH DIGIT THREE] + output[opos++] = '3'; + break; + + case '\u248A': // â’Š [DIGIT THREE FULL STOP] + output[opos++] = '3'; + output[opos++] = '.'; + break; + + case '\u2476': // ⑶ [PARENTHESIZED DIGIT THREE] + output[opos++] = '('; + output[opos++] = '3'; + output[opos++] = ')'; + break; + + case '\u2074': + // � [SUPERSCRIPT FOUR] + case '\u2084': + // â‚„ [SUBSCRIPT FOUR] + case '\u2463': + // â‘£ [CIRCLED DIGIT FOUR] + case '\u24F8': + // ⓸ [DOUBLE CIRCLED DIGIT FOUR] + case '\u2779': + // � [DINGBAT NEGATIVE CIRCLED DIGIT FOUR] + case '\u2783': + // ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR] + case '\u278D': + // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR] + case '\uFF14': // �? [FULLWIDTH DIGIT FOUR] + output[opos++] = '4'; + break; + + case '\u248B': // â’‹ [DIGIT FOUR FULL STOP] + output[opos++] = '4'; + output[opos++] = '.'; + break; + + case '\u2477': // â‘· [PARENTHESIZED DIGIT FOUR] + output[opos++] = '('; + output[opos++] = '4'; + output[opos++] = ')'; + break; + + case '\u2075': + // � [SUPERSCRIPT FIVE] + case '\u2085': + // â‚… [SUBSCRIPT FIVE] + case '\u2464': + // ⑤ [CIRCLED DIGIT FIVE] + case '\u24F9': + // ⓹ [DOUBLE CIRCLED DIGIT FIVE] + case '\u277A': + // � [DINGBAT NEGATIVE CIRCLED DIGIT FIVE] + case '\u2784': + // âž„ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE] + case '\u278E': + // ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE] + case '\uFF15': // ５ [FULLWIDTH DIGIT FIVE] + output[opos++] = '5'; + break; + + case '\u248C': // â’Œ [DIGIT FIVE FULL STOP] + output[opos++] = '5'; + output[opos++] = '.'; + break; + + case '\u2478': // ⑸ [PARENTHESIZED DIGIT FIVE] + output[opos++] = '('; + output[opos++] = '5'; + output[opos++] = ')'; + break; + + case '\u2076': + // � [SUPERSCRIPT SIX] + case '\u2086': + // ₆ [SUBSCRIPT SIX] + case '\u2465': + // â‘¥ [CIRCLED DIGIT SIX] + case '\u24FA': + // ⓺ [DOUBLE CIRCLED DIGIT SIX] + case '\u277B': + // � [DINGBAT NEGATIVE CIRCLED DIGIT SIX] + case '\u2785': + // âž… [DINGBAT CIRCLED SANS-SERIF DIGIT SIX] + case '\u278F': + // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX] + case '\uFF16': // ï¼– [FULLWIDTH DIGIT SIX] + output[opos++] = '6'; + break; + + case '\u248D': // â’� [DIGIT SIX FULL STOP] + output[opos++] = '6'; + output[opos++] = '.'; + break; + + case '\u2479': // ⑹ [PARENTHESIZED DIGIT SIX] + output[opos++] = '('; + output[opos++] = '6'; + output[opos++] = ')'; + break; + + case '\u2077': + // � [SUPERSCRIPT SEVEN] + case '\u2087': + // ₇ [SUBSCRIPT SEVEN] + case '\u2466': + // ⑦ [CIRCLED DIGIT SEVEN] + case '\u24FB': + // â“» [DOUBLE CIRCLED DIGIT SEVEN] + case '\u277C': + // � [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN] + case '\u2786': + // ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN] + case '\u2790': + // � [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN] + case '\uFF17': // ï¼— [FULLWIDTH DIGIT SEVEN] + output[opos++] = '7'; + break; + + case '\u248E': // â’Ž [DIGIT SEVEN FULL STOP] + output[opos++] = '7'; + output[opos++] = '.'; + break; + + case '\u247A': // ⑺ [PARENTHESIZED DIGIT SEVEN] + output[opos++] = '('; + output[opos++] = '7'; + output[opos++] = ')'; + break; + + case '\u2078': + // � [SUPERSCRIPT EIGHT] + case '\u2088': + // ₈ [SUBSCRIPT EIGHT] + case '\u2467': + // ⑧ [CIRCLED DIGIT EIGHT] + case '\u24FC': + // ⓼ [DOUBLE CIRCLED DIGIT EIGHT] + case '\u277D': + // � [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT] + case '\u2787': + // ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT] + case '\u2791': + // âž‘ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT] + case '\uFF18': // ８ [FULLWIDTH DIGIT EIGHT] + output[opos++] = '8'; + break; + + case '\u248F': // â’� [DIGIT EIGHT FULL STOP] + output[opos++] = '8'; + output[opos++] = '.'; + break; + + case '\u247B': // â‘» [PARENTHESIZED DIGIT EIGHT] + output[opos++] = '('; + output[opos++] = '8'; + output[opos++] = ')'; + break; + + case '\u2079': + // � [SUPERSCRIPT NINE] + case '\u2089': + // ₉ [SUBSCRIPT NINE] + case '\u2468': + // ⑨ [CIRCLED DIGIT NINE] + case '\u24FD': + // ⓽ [DOUBLE CIRCLED DIGIT NINE] + case '\u277E': + // � [DINGBAT NEGATIVE CIRCLED DIGIT NINE] + case '\u2788': + // ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE] + case '\u2792': + // âž’ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE] + case '\uFF19': // ï¼™ [FULLWIDTH DIGIT NINE] + output[opos++] = '9'; + break; + + case '\u2490': // â’� [DIGIT NINE FULL STOP] + output[opos++] = '9'; + output[opos++] = '.'; + break; + + case '\u247C': // ⑼ [PARENTHESIZED DIGIT NINE] + output[opos++] = '('; + output[opos++] = '9'; + output[opos++] = ')'; + break; + + case '\u2469': + // â‘© [CIRCLED NUMBER TEN] + case '\u24FE': + // ⓾ [DOUBLE CIRCLED NUMBER TEN] + case '\u277F': + // � [DINGBAT NEGATIVE CIRCLED NUMBER TEN] + case '\u2789': + // ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN] + case '\u2793': // âž“ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN] + output[opos++] = '1'; + output[opos++] = '0'; + break; + + case '\u2491': // â’‘ [NUMBER TEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '0'; + output[opos++] = '.'; + break; + + case '\u247D': // ⑽ [PARENTHESIZED NUMBER TEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '0'; + output[opos++] = ')'; + break; + + case '\u246A': + // ⑪ [CIRCLED NUMBER ELEVEN] + case '\u24EB': // â“« [NEGATIVE CIRCLED NUMBER ELEVEN] + output[opos++] = '1'; + output[opos++] = '1'; + break; + + case '\u2492': // â’’ [NUMBER ELEVEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '1'; + output[opos++] = '.'; + break; + + case '\u247E': // ⑾ [PARENTHESIZED NUMBER ELEVEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '1'; + output[opos++] = ')'; + break; + + case '\u246B': + // â‘« [CIRCLED NUMBER TWELVE] + case '\u24EC': // ⓬ [NEGATIVE CIRCLED NUMBER TWELVE] + output[opos++] = '1'; + output[opos++] = '2'; + break; + + case '\u2493': // â’“ [NUMBER TWELVE FULL STOP] + output[opos++] = '1'; + output[opos++] = '2'; + output[opos++] = '.'; + break; + + case '\u247F': // â‘¿ [PARENTHESIZED NUMBER TWELVE] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '2'; + output[opos++] = ')'; + break; + + case '\u246C': + // ⑬ [CIRCLED NUMBER THIRTEEN] + case '\u24ED': // â“­ [NEGATIVE CIRCLED NUMBER THIRTEEN] + output[opos++] = '1'; + output[opos++] = '3'; + break; + + case '\u2494': // â’�? [NUMBER THIRTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '3'; + output[opos++] = '.'; + break; + + case '\u2480': // â’€ [PARENTHESIZED NUMBER THIRTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '3'; + output[opos++] = ')'; + break; + + case '\u246D': + // â‘­ [CIRCLED NUMBER FOURTEEN] + case '\u24EE': // â“® [NEGATIVE CIRCLED NUMBER FOURTEEN] + output[opos++] = '1'; + output[opos++] = '4'; + break; + + case '\u2495': // â’• [NUMBER FOURTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '4'; + output[opos++] = '.'; + break; + + case '\u2481': // â’� [PARENTHESIZED NUMBER FOURTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '4'; + output[opos++] = ')'; + break; + + case '\u246E': + // â‘® [CIRCLED NUMBER FIFTEEN] + case '\u24EF': // ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN] + output[opos++] = '1'; + output[opos++] = '5'; + break; + + case '\u2496': // â’– [NUMBER FIFTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '5'; + output[opos++] = '.'; + break; + + case '\u2482': // â’‚ [PARENTHESIZED NUMBER FIFTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '5'; + output[opos++] = ')'; + break; + + case '\u246F': + // ⑯ [CIRCLED NUMBER SIXTEEN] + case '\u24F0': // â“° [NEGATIVE CIRCLED NUMBER SIXTEEN] + output[opos++] = '1'; + output[opos++] = '6'; + break; + + case '\u2497': // â’— [NUMBER SIXTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '6'; + output[opos++] = '.'; + break; + + case '\u2483': // â’ƒ [PARENTHESIZED NUMBER SIXTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '6'; + output[opos++] = ')'; + break; + + case '\u2470': + // â‘° [CIRCLED NUMBER SEVENTEEN] + case '\u24F1': // ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN] + output[opos++] = '1'; + output[opos++] = '7'; + break; + + case '\u2498': // â’˜ [NUMBER SEVENTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '7'; + output[opos++] = '.'; + break; + + case '\u2484': // â’„ [PARENTHESIZED NUMBER SEVENTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '7'; + output[opos++] = ')'; + break; + + case '\u2471': + // ⑱ [CIRCLED NUMBER EIGHTEEN] + case '\u24F2': // ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN] + output[opos++] = '1'; + output[opos++] = '8'; + break; + + case '\u2499': // â’™ [NUMBER EIGHTEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '8'; + output[opos++] = '.'; + break; + + case '\u2485': // â’… [PARENTHESIZED NUMBER EIGHTEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '8'; + output[opos++] = ')'; + break; + + case '\u2472': + // ⑲ [CIRCLED NUMBER NINETEEN] + case '\u24F3': // ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN] + output[opos++] = '1'; + output[opos++] = '9'; + break; + + case '\u249A': // â’š [NUMBER NINETEEN FULL STOP] + output[opos++] = '1'; + output[opos++] = '9'; + output[opos++] = '.'; + break; + + case '\u2486': // â’† [PARENTHESIZED NUMBER NINETEEN] + output[opos++] = '('; + output[opos++] = '1'; + output[opos++] = '9'; + output[opos++] = ')'; + break; + + case '\u2473': + // ⑳ [CIRCLED NUMBER TWENTY] + case '\u24F4': // â“´ [NEGATIVE CIRCLED NUMBER TWENTY] + output[opos++] = '2'; + output[opos++] = '0'; + break; + + case '\u249B': // â’› [NUMBER TWENTY FULL STOP] + output[opos++] = '2'; + output[opos++] = '0'; + output[opos++] = '.'; + break; + + case '\u2487': // â’‡ [PARENTHESIZED NUMBER TWENTY] + output[opos++] = '('; + output[opos++] = '2'; + output[opos++] = '0'; + output[opos++] = ')'; + break; + + case '\u00AB': + // « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK] + case '\u00BB': + // » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK] + case '\u201C': + // “ [LEFT DOUBLE QUOTATION MARK] + case '\u201D': + // � [RIGHT DOUBLE QUOTATION MARK] + case '\u201E': + // „ [DOUBLE LOW-9 QUOTATION MARK] + case '\u2033': + // ″ [DOUBLE PRIME] + case '\u2036': + // ‶ [REVERSED DOUBLE PRIME] + case '\u275D': + // � [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT] + case '\u275E': + // � [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT] + case '\u276E': + // � [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT] + case '\u276F': + // � [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT] + case '\uFF02': // ＂ [FULLWIDTH QUOTATION MARK] + output[opos++] = '"'; + break; + + case '\u2018': + // ‘ [LEFT SINGLE QUOTATION MARK] + case '\u2019': + // ’ [RIGHT SINGLE QUOTATION MARK] + case '\u201A': + // ‚ [SINGLE LOW-9 QUOTATION MARK] + case '\u201B': + // ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK] + case '\u2032': + // ′ [PRIME] + case '\u2035': + // ‵ [REVERSED PRIME] + case '\u2039': + // ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK] + case '\u203A': + // › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK] + case '\u275B': + // � [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT] + case '\u275C': + // � [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT] + case '\uFF07': // ＇ [FULLWIDTH APOSTROPHE] + output[opos++] = '\''; + break; + + case '\u2010': + // � [HYPHEN] + case '\u2011': + // ‑ [NON-BREAKING HYPHEN] + case '\u2012': + // ‒ [FIGURE DASH] + case '\u2013': + // – [EN DASH] + case '\u2014': + // �? [EM DASH] + case '\u207B': + // � [SUPERSCRIPT MINUS] + case '\u208B': + // â‚‹ [SUBSCRIPT MINUS] + case '\uFF0D': // � [FULLWIDTH HYPHEN-MINUS] + output[opos++] = '-'; + break; + + case '\u2045': + // � [LEFT SQUARE BRACKET WITH QUILL] + case '\u2772': + // � [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT] + case '\uFF3B': // ï¼» [FULLWIDTH LEFT SQUARE BRACKET] + output[opos++] = '['; + break; + + case '\u2046': + // � [RIGHT SQUARE BRACKET WITH QUILL] + case '\u2773': + // � [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT] + case '\uFF3D': // ï¼½ [FULLWIDTH RIGHT SQUARE BRACKET] + output[opos++] = ']'; + break; + + case '\u207D': + // � [SUPERSCRIPT LEFT PARENTHESIS] + case '\u208D': + // � [SUBSCRIPT LEFT PARENTHESIS] + case '\u2768': + // � [MEDIUM LEFT PARENTHESIS ORNAMENT] + case '\u276A': + // � [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT] + case '\uFF08': // （ [FULLWIDTH LEFT PARENTHESIS] + output[opos++] = '('; + break; + + case '\u2E28': // ⸨ [LEFT DOUBLE PARENTHESIS] + output[opos++] = '('; + output[opos++] = '('; + break; + + case '\u207E': + // � [SUPERSCRIPT RIGHT PARENTHESIS] + case '\u208E': + // â‚Ž [SUBSCRIPT RIGHT PARENTHESIS] + case '\u2769': + // � [MEDIUM RIGHT PARENTHESIS ORNAMENT] + case '\u276B': + // � [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT] + case '\uFF09': // ） [FULLWIDTH RIGHT PARENTHESIS] + output[opos++] = ')'; + break; + + case '\u2E29': // ⸩ [RIGHT DOUBLE PARENTHESIS] + output[opos++] = ')'; + output[opos++] = ')'; + break; + + case '\u276C': + // � [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT] + case '\u2770': + // � [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT] + case '\uFF1C': // ＜ [FULLWIDTH LESS-THAN SIGN] + output[opos++] = '<'; + break; + + case '\u276D': + // � [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT] + case '\u2771': + // � [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT] + case '\uFF1E': // ＞ [FULLWIDTH GREATER-THAN SIGN] + output[opos++] = '>'; + break; + + case '\u2774': + // � [MEDIUM LEFT CURLY BRACKET ORNAMENT] + case '\uFF5B': // ï½› [FULLWIDTH LEFT CURLY BRACKET] + output[opos++] = '{'; + break; + + case '\u2775': + // � [MEDIUM RIGHT CURLY BRACKET ORNAMENT] + case '\uFF5D': // � [FULLWIDTH RIGHT CURLY BRACKET] + output[opos++] = '}'; + break; + + case '\u207A': + // � [SUPERSCRIPT PLUS SIGN] + case '\u208A': + // â‚Š [SUBSCRIPT PLUS SIGN] + case '\uFF0B': // ＋ [FULLWIDTH PLUS SIGN] + output[opos++] = '+'; + break; + + case '\u207C': + // � [SUPERSCRIPT EQUALS SIGN] + case '\u208C': + // â‚Œ [SUBSCRIPT EQUALS SIGN] + case '\uFF1D': // � [FULLWIDTH EQUALS SIGN] + output[opos++] = '='; + break; + + case '\uFF01': // � [FULLWIDTH EXCLAMATION MARK] + output[opos++] = '!'; + break; + + case '\u203C': // ‼ [DOUBLE EXCLAMATION MARK] + output[opos++] = '!'; + output[opos++] = '!'; + break; + + case '\u2049': // � [EXCLAMATION QUESTION MARK] + output[opos++] = '!'; + output[opos++] = '?'; + break; + + case '\uFF03': // ＃ [FULLWIDTH NUMBER SIGN] + output[opos++] = '#'; + break; + + case '\uFF04': // ＄ [FULLWIDTH DOLLAR SIGN] + output[opos++] = '$'; + break; + + case '\u2052': + // � [COMMERCIAL MINUS SIGN] + case '\uFF05': // ï¼… [FULLWIDTH PERCENT SIGN] + output[opos++] = '%'; + break; + + case '\uFF06': // ＆ [FULLWIDTH AMPERSAND] + output[opos++] = '&'; + break; + + case '\u204E': + // � [LOW ASTERISK] + case '\uFF0A': // ＊ [FULLWIDTH ASTERISK] + output[opos++] = '*'; + break; + + case '\uFF0C': // ， [FULLWIDTH COMMA] + output[opos++] = ','; + break; + + case '\uFF0E': // ． [FULLWIDTH FULL STOP] + output[opos++] = '.'; + break; + + case '\u2044': + // � [FRACTION SLASH] + case '\uFF0F': // � [FULLWIDTH SOLIDUS] + output[opos++] = '/'; + break; + + case '\uFF1A': // ： [FULLWIDTH COLON] + output[opos++] = ':'; + break; + + case '\u204F': + // � [REVERSED SEMICOLON] + case '\uFF1B': // ï¼› [FULLWIDTH SEMICOLON] + output[opos++] = ';'; + break; + + case '\uFF1F': // ？ [FULLWIDTH QUESTION MARK] + output[opos++] = '?'; + break; + + case '\u2047': // � [DOUBLE QUESTION MARK] + output[opos++] = '?'; + output[opos++] = '?'; + break; + + case '\u2048': // � [QUESTION EXCLAMATION MARK] + output[opos++] = '?'; + output[opos++] = '!'; + break; + + case '\uFF20': // ï¼  [FULLWIDTH COMMERCIAL AT] + output[opos++] = '@'; + break; + + case '\uFF3C': // ï¼¼ [FULLWIDTH REVERSE SOLIDUS] + output[opos++] = '\\'; + break; + + case '\u2038': + // ‸ [CARET] + case '\uFF3E': // ï¼¾ [FULLWIDTH CIRCUMFLEX ACCENT] + output[opos++] = '^'; + break; + + case '\uFF3F': // ＿ [FULLWIDTH LOW LINE] + output[opos++] = '_'; + break; + + case '\u2053': + // � [SWUNG DASH] + case '\uFF5E': // ～ [FULLWIDTH TILDE] + output[opos++] = '~'; + break; + + // BEGIN CUSTOM TRANSLITERATION OF CYRILIC CHARS + + // russian uppercase "А Б В Г Д Е Ё Ж З И Й К Л М Н О П Р С Т У Ф Х Ц Ч Ш Щ Ъ Ы Ь Э Ю Я" + // russian lowercase "а б в г д е ё ж з и й к л м н о п р с т у ф х ц ч ш щ ъ ы ь э ю я" + + // notes + // read http://www.vesic.org/english/blog/c-sharp/transliteration-easy-way-microsoft-transliteration-utility/ + // should we look into MS Transliteration Utility (http://msdn.microsoft.com/en-US/goglobal/bb688104.aspx) + // also UnicodeSharpFork https://bitbucket.org/DimaStefantsov/unidecodesharpfork + // also Transliterator http://transliterator.codeplex.com/ + // + // in any case it would be good to generate all those "case" statements instead of writing them by hand + // time for a T4 template? + // also we should support extensibility so ppl can register more cases in external code + + // TODO: transliterates Анастасия as Anastasiya, and not Anastasia + // Ольга --> Ol'ga, Татьяна --> Tat'yana -- that's bad (?) + // Note: should ä (German umlaut) become a or ae ? + case '\u0410': // А + output[opos++] = 'A'; + break; + case '\u0430': // а + output[opos++] = 'a'; + break; + case '\u0411': // Б + output[opos++] = 'B'; + break; + case '\u0431': // б + output[opos++] = 'b'; + break; + case '\u0412': // В + output[opos++] = 'V'; + break; + case '\u0432': // в + output[opos++] = 'v'; + break; + case '\u0413': // Г + output[opos++] = 'G'; + break; + case '\u0433': // г + output[opos++] = 'g'; + break; + case '\u0414': // Д + output[opos++] = 'D'; + break; + case '\u0434': // д + output[opos++] = 'd'; + break; + case '\u0415': // Е + output[opos++] = 'E'; + break; + case '\u0435': // е + output[opos++] = 'e'; + break; + case '\u0401': // Ё + output[opos++] = 'E'; // alt. Yo + break; + case '\u0451': // ё + output[opos++] = 'e'; // alt. yo + break; + case '\u0416': // Ж + output[opos++] = 'Z'; + output[opos++] = 'h'; + break; + case '\u0436': // ж + output[opos++] = 'z'; + output[opos++] = 'h'; + break; + case '\u0417': // З + output[opos++] = 'Z'; + break; + case '\u0437': // з + output[opos++] = 'z'; + break; + case '\u0418': // И + output[opos++] = 'I'; + break; + case '\u0438': // и + output[opos++] = 'i'; + break; + case '\u0419': // Й + output[opos++] = 'I'; // alt. Y, J + break; + case '\u0439': // й + output[opos++] = 'i'; // alt. y, j + break; + case '\u041A': // К + output[opos++] = 'K'; + break; + case '\u043A': // к + output[opos++] = 'k'; + break; + case '\u041B': // Л + output[opos++] = 'L'; + break; + case '\u043B': // л + output[opos++] = 'l'; + break; + case '\u041C': // М + output[opos++] = 'M'; + break; + case '\u043C': // м + output[opos++] = 'm'; + break; + case '\u041D': // Н + output[opos++] = 'N'; + break; + case '\u043D': // н + output[opos++] = 'n'; + break; + case '\u041E': // О + output[opos++] = 'O'; + break; + case '\u043E': // о + output[opos++] = 'o'; + break; + case '\u041F': // П + output[opos++] = 'P'; + break; + case '\u043F': // п + output[opos++] = 'p'; + break; + case '\u0420': // Р + output[opos++] = 'R'; + break; + case '\u0440': // р + output[opos++] = 'r'; + break; + case '\u0421': // С + output[opos++] = 'S'; + break; + case '\u0441': // с + output[opos++] = 's'; + break; + case '\u0422': // Т + output[opos++] = 'T'; + break; + case '\u0442': // т + output[opos++] = 't'; + break; + case '\u0423': // У + output[opos++] = 'U'; + break; + case '\u0443': // у + output[opos++] = 'u'; + break; + case '\u0424': // Ф + output[opos++] = 'F'; + break; + case '\u0444': // ф + output[opos++] = 'f'; + break; + case '\u0425': // Х + output[opos++] = 'K'; // alt. X + output[opos++] = 'h'; + break; + case '\u0445': // х + output[opos++] = 'k'; // alt. x + output[opos++] = 'h'; + break; + case '\u0426': // Ц + output[opos++] = 'F'; + break; + case '\u0446': // ц + output[opos++] = 'f'; + break; + case '\u0427': // Ч + output[opos++] = 'C'; // alt. Ts, C + output[opos++] = 'h'; + break; + case '\u0447': // ч + output[opos++] = 'c'; // alt. ts, c + output[opos++] = 'h'; + break; + case '\u0428': // Ш + output[opos++] = 'S'; // alt. Ch, S + output[opos++] = 'h'; + break; + case '\u0448': // ш + output[opos++] = 's'; // alt. ch, s + output[opos++] = 'h'; + break; + case '\u0429': // Щ + output[opos++] = 'S'; // alt. Shch, Sc + output[opos++] = 'h'; + break; + case '\u0449': // щ + output[opos++] = 's'; // alt. shch, sc + output[opos++] = 'h'; + break; + case '\u042A': // Ъ + output[opos++] = '"'; // " + break; + case '\u044A': // ъ + output[opos++] = '"'; // " + break; + case '\u042B': // Ы + output[opos++] = 'Y'; + break; + case '\u044B': // ы + output[opos++] = 'y'; + break; + case '\u042C': // Ь + output[opos++] = '\''; // ' + break; + case '\u044C': // ь + output[opos++] = '\''; // ' + break; + case '\u042D': // Э + output[opos++] = 'E'; + break; + case '\u044D': // э + output[opos++] = 'e'; + break; + case '\u042E': // Ю + output[opos++] = 'Y'; // alt. Ju + output[opos++] = 'u'; + break; + case '\u044E': // ю + output[opos++] = 'y'; // alt. ju + output[opos++] = 'u'; + break; + case '\u042F': // Я + output[opos++] = 'Y'; // alt. Ja + output[opos++] = 'a'; + break; + case '\u044F': // я + output[opos++] = 'y'; // alt. ja + output[opos++] = 'a'; + break; + + // BEGIN EXTRA + /* + case '£': + output[opos++] = 'G'; + output[opos++] = 'B'; + output[opos++] = 'P'; + break; + + case '€': + output[opos++] = 'E'; + output[opos++] = 'U'; + output[opos++] = 'R'; + break; + + case '©': + output[opos++] = '('; + output[opos++] = 'C'; + output[opos++] = ')'; + break; + */ + default: + // if (ToMoreAscii(input, ipos, output, ref opos)) + // break; + + // if (!char.IsLetterOrDigit(c)) // that would not catch eg 汉 unfortunately + // output[opos++] = '?'; + // else + // output[opos++] = c; + + // strict ASCII + output[opos++] = fail; + + break; + } + } + } + + // private static bool ToMoreAscii(char[] input, int ipos, char[] output, ref int opos) + // { + // var c = input[ipos]; + + // switch (c) + // { + // case '£': + // output[opos++] = 'G'; + // output[opos++] = 'B'; + // output[opos++] = 'P'; + // break; + + // case '€': + // output[opos++] = 'E'; + // output[opos++] = 'U'; + // output[opos++] = 'R'; + // break; + + // case '©': + // output[opos++] = '('; + // output[opos++] = 'C'; + // output[opos++] = ')'; + // break; + + // default: + // return false; + // } + + // return true; + // } +} +#endif diff --git a/src/Umbraco.Core/Strings/Utf8ToAsciiConverterStatic.cs b/src/Umbraco.Core/Strings/Utf8ToAsciiConverterStatic.cs new file mode 100644 index 0000000000..17618ca887 --- /dev/null +++ b/src/Umbraco.Core/Strings/Utf8ToAsciiConverterStatic.cs @@ -0,0 +1,50 @@ +using Microsoft.Extensions.FileProviders; +using Microsoft.Extensions.Hosting; +using Microsoft.Extensions.Logging.Abstractions; + +namespace Umbraco.Cms.Core.Strings; + +/// +/// Static wrapper for backward compatibility with existing code. +/// +/// +/// Use via dependency injection for new code. +/// +public static class Utf8ToAsciiConverterStatic +{ + private static readonly Lazy DefaultConverter = new(() => + { + var hostEnv = new SimpleHostEnvironment { ContentRootPath = AppContext.BaseDirectory }; + var loader = new CharacterMappingLoader(hostEnv, NullLogger.Instance); + return new Utf8ToAsciiConverter(loader); + }); + + // Simple IHostEnvironment implementation for static initialization + private sealed class SimpleHostEnvironment : IHostEnvironment + { + public string EnvironmentName { get; set; } = "Production"; + public string ApplicationName { get; set; } = "Umbraco"; + public string ContentRootPath { get; set; } = string.Empty; + public IFileProvider ContentRootFileProvider { get; set; } = null!; + } + + /// + /// Converts an UTF-8 string into an ASCII string. + /// + /// The text to convert. + /// The character to use to replace characters that cannot be converted. + /// The converted text. + [Obsolete("Use IUtf8ToAsciiConverter via dependency injection. This will be removed in v15.")] + public static string ToAsciiString(string text, char fail = '?') + => DefaultConverter.Value.Convert(text, fail); + + /// + /// Converts an UTF-8 string into an array of ASCII characters. + /// + /// The text to convert. + /// The character to use to replace characters that cannot be converted. + /// The converted text as char array. + [Obsolete("Use IUtf8ToAsciiConverter via dependency injection. This will be removed in v15.")] + public static char[] ToAsciiCharArray(string text, char fail = '?') + => DefaultConverter.Value.Convert(text, fail).ToCharArray(); +} diff --git a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/ShortStringHelper/DefaultShortStringHelperTestsWithoutSetup.cs b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/ShortStringHelper/DefaultShortStringHelperTestsWithoutSetup.cs index 30ab94f3f2..91f9fe4039 100644 --- a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/ShortStringHelper/DefaultShortStringHelperTestsWithoutSetup.cs +++ b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/ShortStringHelper/DefaultShortStringHelperTestsWithoutSetup.cs @@ -343,7 +343,7 @@ public class DefaultShortStringHelperTestsWithoutSetup public void Utf8ToAsciiConverter() { const string str = "a\U00010F00z\uA74Ftéô"; - var output = global::Umbraco.Cms.Core.Strings.Utf8ToAsciiConverter.ToAsciiString(str); + var output = global::Umbraco.Cms.Core.Strings.Utf8ToAsciiConverterStatic.ToAsciiString(str); Assert.AreEqual("a?zooteo", output); } diff --git a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterGoldenTests.cs b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterGoldenTests.cs index d833a95e16..7a8c1c52dc 100644 --- a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterGoldenTests.cs +++ b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterGoldenTests.cs @@ -53,7 +53,7 @@ public class Utf8ToAsciiConverterGoldenTests hostEnv.Object, NullLogger.Instance); - _newConverter = new Utf8ToAsciiConverterNew(loader); + _newConverter = new Utf8ToAsciiConverter(loader); } public static IEnumerable GetGoldenMappings() @@ -74,23 +74,8 @@ public class Utf8ToAsciiConverterGoldenTests [TestCaseSource(nameof(GetGoldenMappings))] public void NewConverter_MatchesOriginalBehavior(string input, string expected) { - // Compare new implementation against original - // Note: Original has buffer overflow bugs for chars that expand to 4+ chars (e.g., ⑽→(10)) - string? originalResult; - try - { - originalResult = Utf8ToAsciiConverter.ToAsciiString(input); - } - catch (IndexOutOfRangeException) - { - // Original converter has known buffer bugs for high-expansion characters - // New converter fixes these - verify it produces the expected golden mapping - var newResult = _newConverter.Convert(input); - Assert.That(newResult, Is.EqualTo(expected), - $"Original throws IndexOutOfRangeException, but new converter should match golden mapping"); - return; - } - + // Compare new implementation against static wrapper (which uses new implementation) + var originalResult = Utf8ToAsciiConverterStatic.ToAsciiString(input); var result = _newConverter.Convert(input); Assert.That(result, Is.EqualTo(originalResult)); } diff --git a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterNewTests.cs b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterTests.cs similarity index 98% rename from tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterNewTests.cs rename to tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterTests.cs index db2369648d..761b9e12db 100644 --- a/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterNewTests.cs +++ b/tests/Umbraco.Tests.UnitTests/Umbraco.Core/Strings/Utf8ToAsciiConverterTests.cs @@ -7,7 +7,7 @@ using Umbraco.Cms.Core.Strings; namespace Umbraco.Cms.Tests.UnitTests.Umbraco.Core.Strings; [TestFixture] -public class Utf8ToAsciiConverterNewTests +public class Utf8ToAsciiConverterTests { private IUtf8ToAsciiConverter _converter = null!; @@ -21,7 +21,7 @@ public class Utf8ToAsciiConverterNewTests hostEnv.Object, NullLogger.Instance); - _converter = new Utf8ToAsciiConverterNew(loader); + _converter = new Utf8ToAsciiConverter(loader); } // === Null/Empty ===