From e9f4aae440ba762002f7f7e6524626f7bc9aec00 Mon Sep 17 00:00:00 2001 From: Natalia Portillo Date: Thu, 1 Mar 2018 03:04:08 +0000 Subject: [PATCH] Add support for GEM character set. --- .../Claunia.Encoding.Tests.csproj | 2 +- Claunia.Encoding.sln | 2 +- Claunia.Encoding/Claunia.Encoding.csproj | 7 +- Claunia.Encoding/Encoding.cs | 4 + Claunia.Encoding/Gem.cs | 746 ++++++++++++++++++ README.md | 1 + 6 files changed, 757 insertions(+), 5 deletions(-) create mode 100644 Claunia.Encoding/Gem.cs diff --git a/Claunia.Encoding.Tests/Claunia.Encoding.Tests.csproj b/Claunia.Encoding.Tests/Claunia.Encoding.Tests.csproj index 5534ed5..f57d0f9 100644 --- a/Claunia.Encoding.Tests/Claunia.Encoding.Tests.csproj +++ b/Claunia.Encoding.Tests/Claunia.Encoding.Tests.csproj @@ -8,7 +8,7 @@ Claunia.Encoding.Tests Claunia.Encoding.Tests v4.5 - 1.4 + 1.5 true diff --git a/Claunia.Encoding.sln b/Claunia.Encoding.sln index 72193f7..b940aef 100644 --- a/Claunia.Encoding.sln +++ b/Claunia.Encoding.sln @@ -29,6 +29,6 @@ Global $2.TabsToSpaces = True $0.CSharpFormattingPolicy = $3 $3.scope = text/x-csharp - version = 1.4 + version = 1.5 EndGlobalSection EndGlobal diff --git a/Claunia.Encoding/Claunia.Encoding.csproj b/Claunia.Encoding/Claunia.Encoding.csproj index 89df0d2..86745f8 100644 --- a/Claunia.Encoding/Claunia.Encoding.csproj +++ b/Claunia.Encoding/Claunia.Encoding.csproj @@ -13,7 +13,7 @@ Profile136 true Claunia.Encoding - 1.4 + 1.5 Natalia Portillo true Natalia Portillo @@ -22,8 +22,8 @@ Claunia.Encoding Library to provide codepage conversion to and from archaic and old computer systems and Unicode. https://raw.githubusercontent.com/claunia/Claunia.Encoding/master/LICENSE.MIT - 1.4 - Added DEC Radix-50. + 1.5 + Added GEM character set. true @@ -49,6 +49,7 @@ + diff --git a/Claunia.Encoding/Encoding.cs b/Claunia.Encoding/Encoding.cs index 2630d77..aa85142 100644 --- a/Claunia.Encoding/Encoding.cs +++ b/Claunia.Encoding/Encoding.cs @@ -56,6 +56,10 @@ namespace Claunia.Encoding /// Static instance for the DEC Radix-50 encoding /// public static System.Text.Encoding Radix50Encoding = new Radix50(); + /// + /// Static instance for the GEM encoding + /// + public static System.Text.Encoding GemEncoding = new Gem(); /// /// Gets a value indicating whether the current encoding can be used by browser clients for displaying content. diff --git a/Claunia.Encoding/Gem.cs b/Claunia.Encoding/Gem.cs new file mode 100644 index 0000000..c9f9c92 --- /dev/null +++ b/Claunia.Encoding/Gem.cs @@ -0,0 +1,746 @@ +// +// Gem.cs +// +// Author: +// Natalia Portillo +// +// Copyright © 2016-2018 Natalia Portillo +// +// Permission is hereby granted, free of charge, to any person obtaining a copy +// of this software and associated documentation files (the "Software"), to deal +// in the Software without restriction, including without limitation the rights +// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +// copies of the Software, and to permit persons to whom the Software is +// furnished to do so, subject to the following conditions: +// +// The above copyright notice and this permission notice shall be included in +// all copies or substantial portions of the Software. +// +// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +// THE SOFTWARE. + +using System; + +namespace Claunia.Encoding +{ + /// + /// Represents a GEM character encoding of Unicode characters. + /// + public class Gem : Encoding + { + const string _bodyname = "gem"; + const int _codepage = 0; + const string _encodingname = "Western European (GEM)"; + const string _headername = "gem"; + const string _webname = ""; + const int _windowsCodepage = 0; + + const bool browserDisplay = false; + const bool browserSave = false; + const bool mailNewsDisplay = false; + const bool mailNewsSave = false; + const bool readOnly = false; + const bool singleByte = true; + + /// + /// The GEM to Unicode character map. + /// Pending: 0x09 => 0x0001F552, 0x0A => 0x0001F514 + /// + static readonly char[] GemTable = + { + // 0x00 + '\u0000', '\u21E7', '\u21E9', '\u21E8', '\u21E6', '\u25FC', '\uFFFD', '\u25C6', + // 0x08 + '\u2713', '\uFFFD', '\uFFFD', '\u266A', '\u25B4', '\u25BE', '\u25B8', '\u25C2', + // 0x10 + '\u25BA', '\u25C4', '\u29D3', '\u2582', '\u00B6', '\u00A7', '\u2195', '\u21A8', + // 0x18 + '\u2191', '\u2193', '\u2192', '\u2190', '\u221F', '\u2194', '\u25B2', '\u25BC', + // 0x20 + '\u0020', '\u0021', '\u0022', '\u0023', '\u0024', '\u0025', '\u0026', '\u0027', + // 0x28 + '\u0028', '\u0029', '\u002A', '\u002B', '\u002C', '\u002D', '\u002E', '\u002F', + // 0x30 + '\u0030', '\u0031', '\u0032', '\u0033', '\u0034', '\u0035', '\u0036', '\u0037', + // 0x38 + '\u0038', '\u0039', '\u003A', '\u003B', '\u003C', '\u003D', '\u003E', '\u003F', + // 0x40 + '\u0040', '\u0041', '\u0042', '\u0043', '\u0044', '\u0045', '\u0046', '\u0047', + // 0x48 + '\u0048', '\u0049', '\u004A', '\u004B', '\u004C', '\u004D', '\u004E', '\u004F', + // 0x50 + '\u0050', '\u0051', '\u0052', '\u0053', '\u0054', '\u0055', '\u0056', '\u0057', + // 0x58 + '\u0058', '\u0059', '\u005A', '\u005B', '\u005C', '\u005D', '\u005E', '\u005F', + // 0x60 + '\u0060', '\u0061', '\u0062', '\u0063', '\u0064', '\u0065', '\u0066', '\u0067', + // 0x68 + '\u0068', '\u0069', '\u006A', '\u006B', '\u006C', '\u006D', '\u006E', '\u006F', + // 0x70 + '\u0070', '\u0071', '\u0072', '\u0073', '\u0074', '\u0075', '\u0076', '\u0077', + // 0x78 + '\u0078', '\u0079', '\u007A', '\u007B', '\u007C', '\u007D', '\u007E', '\u2302', + // 0x80 + '\u00C7', '\u00FC', '\u00E9', '\u00E2', '\u00E4', '\u00E0', '\u00E5', '\u00E7', + // 0x88 + '\u00EA', '\u00EB', '\u00E8', '\u00EF', '\u00EE', '\u00EC', '\u00C4', '\u00C5', + // 0x90 + '\u00C9', '\u00E6', '\u00C6', '\u00F4', '\u00F6', '\u00F2', '\u00FB', '\u00F9', + // 0x98 + '\u00FF', '\u00D6', '\u00DC', '\u00FB', '\u00A3', '\u00D8', '\u00A4', '\u0192', + // 0xA0 + '\u00E1', '\u00ED', '\u00F3', '\u00FA', '\u00F1', '\u00D1', '\u00AA', '\u00BA', + // 0xA8 + '\u00BF', '\u201C', '\u201D', '\u2039', '\u203A', '\u00A1', '\u00AB', '\u00BB', + // 0xB0 + '\u00E3', '\u00F5', '\u00A5', '\u00A2', '\u0153', '\u0152', '\u00C0', '\u00C3', + // 0xB8 + '\u00D5', '\u00A7', '\u2021', '\u2020', '\u00B6', '\u00A9', '\u00AE', '\u2122', + // 0xC0 + '\u201E', '\u2026', '\u2030', '\u2022', '\u2013', '\u2014', '\u2070', '\u00C1', + // 0xC8 + '\u00C2', '\u00C8', '\u00CA', '\u00CB', '\u00CC', '\u00CD', '\u00CE', '\u00CF', + // 0xD0 + '\u00D2', '\u00D3', '\u00D4', '\u0160', '\u0161', '\u00D9', '\u00DA', '\u00DB', + // 0xD8 + '\u0178', '\u00DF', '\uFFFD', '\uFFFD', '\uFFFD', '\uFFFD', '\uFFFD', '\uFFFD', + // 0xE0 + '\u03B1', '\u03B2', '\u0393', '\u03C0', '\u03A3', '\u03C3', '\u00B5', '\u03C4', + // 0xE8 + '\u03A6', '\u0398', '\u03A9', '\u03B4', '\u222E', '\u0278', '\u2208', '\u2229', + // 0xF0 + '\u2261', '\u00B1', '\u2265', '\u2264', '\u2320', '\u2321', '\u00F7', '\u2248', + // 0xF8 + '\u00B0', '\u2219', '\u00B7', '\u221A', '\u207F', '\u00B2', '\u25A0', '\u2205' + }; + + /// + /// Gets a value indicating whether the current encoding can be used by browser clients for displaying content. + /// + public override bool IsBrowserDisplay => browserDisplay; + + /// + /// Gets a value indicating whether the current encoding can be used by browser clients for saving content. + /// + public override bool IsBrowserSave => browserSave; + + /// + /// Gets a value indicating whether the current encoding can be used by mail and news clients for displaying content. + /// + public override bool IsMailNewsDisplay => mailNewsDisplay; + + /// + /// Gets a value indicating whether the current encoding can be used by mail and news clients for saving content. + /// + public override bool IsMailNewsSave => mailNewsSave; + + /// + /// Gets a value indicating whether the current encoding is read-only. + /// + /// The is single byte. + public override bool IsReadOnly => readOnly; + + /// + /// Gets a value indicating whether the current encoding uses single-byte code points. + /// + public override bool IsSingleByte => singleByte; + + /// + /// Gets the code page identifier of the current Encoding. + /// + public override int CodePage => _codepage; + + /// + /// Gets a name for the current encoding that can be used with mail agent body tags + /// + public override string BodyName => _bodyname; + + /// + /// Gets a name for the current encoding that can be used with mail agent header tags + /// + public override string HeaderName => _headername; + + /// + /// Ggets the name registered with the Internet Assigned Numbers Authority (IANA) for the current encoding. + /// + public override string WebName => _webname; + + /// + /// Gets the human-readable description of the current encoding. + /// + public override string EncodingName => _encodingname; + + /// + /// Gets the Windows operating system code page that most closely corresponds to the current encoding. + /// + public override int WindowsCodePage => _windowsCodepage; + + /// + /// Calculates the number of bytes produced by encoding the characters in the specified . + /// + /// The number of bytes produced by encoding the specified characters. + /// The containing the set of characters to encode. + public override int GetByteCount(string s) + { + if(s == null) throw new ArgumentNullException(nameof(s)); + + return s.Length; + } + + /// + /// Calculates the number of bytes produced by encoding a set of characters from the specified character array. + /// + /// The number of bytes produced by encoding the specified characters. + /// The character array containing the set of characters to encode. + /// The index of the first character to encode. + /// The number of characters to encode. + public override int GetByteCount(char[] chars, int index, int count) + { + if(chars == null) throw new ArgumentNullException(nameof(chars)); + + if(index < 0 || index >= chars.Length) throw new ArgumentOutOfRangeException(nameof(index)); + + if(count < 0 || index + count > chars.Length) throw new ArgumentOutOfRangeException(nameof(index)); + + return count; + } + + /// + /// Calculates the number of bytes produced by encoding all the characters in the specified character array. + /// + /// The number of bytes produced by encoding all the characters in the specified character array. + /// The character array containing the characters to encode. + public override int GetByteCount(char[] chars) + { + if(chars == null) throw new ArgumentNullException(nameof(chars)); + + return chars.Length; + } + + /// + /// Encodes a set of characters from the specified into the specified byte array. + /// + /// The actual number of bytes written into bytes. + /// The containing the set of characters to encode. + /// The index of the first character to encode. + /// The number of characters to encode. + /// The byte array to contain the resulting sequence of bytes. + /// The index at which to start writing the resulting sequence of bytes. + public override int GetBytes(string s, int charIndex, int charCount, byte[] bytes, int byteIndex) + { + return GetBytes(s.ToCharArray(), charIndex, charCount, bytes, byteIndex); + } + + /// + /// Encodes all the characters in the specified string into a sequence of bytes. + /// + /// A byte array containing the results of encoding the specified set of characters. + /// The string containing the characters to encode. + public override byte[] GetBytes(string s) + { + if(s == null) throw new ArgumentNullException(nameof(s)); + + return GetBytes(s.ToCharArray(), 0, s.Length); + } + + /// + /// Encodes a set of characters from the specified character array into the specified byte array. + /// + /// The actual number of bytes written into bytes. + /// The character array containing the set of characters to encode. + /// The index of the first character to encode. + /// The number of characters to encode. + /// The byte array to contain the resulting sequence of bytes. + /// The index at which to start writing the resulting sequence of bytes. + public override int GetBytes(char[] chars, int charIndex, int charCount, byte[] bytes, int byteIndex) + { + if(chars == null) throw new ArgumentNullException(nameof(chars)); + + if(bytes == null) throw new ArgumentNullException(nameof(bytes)); + + if(charIndex < 0) throw new ArgumentOutOfRangeException(nameof(charIndex)); + + if(charCount < 0) throw new ArgumentOutOfRangeException(nameof(charCount)); + + if(byteIndex < 0) throw new ArgumentOutOfRangeException(nameof(byteIndex)); + + if(charIndex >= chars.Length) throw new ArgumentOutOfRangeException(nameof(charIndex)); + + if(charCount + charIndex > chars.Length) throw new ArgumentOutOfRangeException(nameof(charCount)); + + if(byteIndex >= bytes.Length) throw new ArgumentOutOfRangeException(nameof(byteIndex)); + + if(byteIndex + charCount > bytes.Length) throw new ArgumentException(nameof(bytes)); + + byte[] temp = GetBytes(chars, charIndex, charCount); + + for(int i = 0; i < temp.Length; i++) bytes[i + byteIndex] = temp[i]; + + return charCount; + } + + /// + /// Encodes a set of characters from the specified character array into a sequence of bytes. + /// + /// A byte array containing the results of encoding the specified set of characters. + /// The character array containing the set of characters to encode. + /// The index of the first character to encode. + /// The number of characters to encode. + public override byte[] GetBytes(char[] chars, int index, int count) + { + if(chars == null) throw new ArgumentNullException(nameof(chars)); + + if(index < 0) throw new ArgumentOutOfRangeException(nameof(index)); + + if(count < 0) throw new ArgumentOutOfRangeException(nameof(count)); + + if(count + index > chars.Length) throw new ArgumentOutOfRangeException(nameof(count)); + + byte[] bytes = new byte[count]; + + for(int i = 0; i < count; i++) bytes[i] = GetByte(chars[index + i]); + + return bytes; + } + + /// + /// Encodes all the characters in the specified character array into a sequence of bytes. + /// + /// A byte array containing the results of encoding the specified set of characters. + /// The character array containing the characters to encode. + public override byte[] GetBytes(char[] chars) + { + return GetBytes(chars, 0, chars.Length); + } + + /// + /// Calculates the number of characters produced by decoding all the bytes in the specified byte array. + /// + /// The number of characters produced by decoding the specified sequence of bytes. + /// The byte array containing the sequence of bytes to decode. + public override int GetCharCount(byte[] bytes) + { + return GetCharCount(bytes, 0, bytes.Length); + } + + /// + /// Calculates the number of characters produced by decoding a sequence of bytes from the specified byte array. + /// + /// The number of characters produced by decoding the specified sequence of bytes. + /// The byte array containing the sequence of bytes to decode. + /// The index of the first byte to decode. + /// The number of bytes to decode. + public override int GetCharCount(byte[] bytes, int index, int count) + { + if(bytes == null) throw new ArgumentNullException(nameof(bytes)); + + if(index < 0) throw new ArgumentOutOfRangeException(nameof(index)); + + if(count < 0) throw new ArgumentOutOfRangeException(nameof(count)); + + if(count + index > bytes.Length) throw new ArgumentOutOfRangeException(nameof(count)); + + return count; + } + + /// + /// Decodes a sequence of bytes from the specified byte array into the specified character array. + /// + /// The actual number of characters written into chars. + /// The byte array containing the sequence of bytes to decode. + /// The index of the first byte to decode. + /// The number of bytes to decode. + /// The character array to contain the resulting set of characters. + /// The index at which to start writing the resulting set of characters. + public override int GetChars(byte[] bytes, int byteIndex, int byteCount, char[] chars, int charIndex) + { + if(bytes == null) throw new ArgumentNullException(nameof(bytes)); + + if(chars == null) throw new ArgumentNullException(nameof(chars)); + + if(byteIndex < 0) throw new ArgumentOutOfRangeException(nameof(byteIndex)); + + if(byteCount < 0) throw new ArgumentOutOfRangeException(nameof(byteCount)); + + if(charIndex < 0) throw new ArgumentOutOfRangeException(nameof(charIndex)); + + if(byteIndex >= bytes.Length) throw new ArgumentOutOfRangeException(nameof(byteIndex)); + + if(byteCount + byteIndex > bytes.Length) throw new ArgumentOutOfRangeException(nameof(byteCount)); + + if(charIndex >= chars.Length) throw new ArgumentOutOfRangeException(nameof(charIndex)); + + if(charIndex + byteCount > chars.Length) throw new ArgumentException(nameof(chars)); + + char[] temp = GetChars(bytes, byteIndex, byteCount); + + for(int i = 0; i < temp.Length; i++) chars[i + charIndex] = temp[i]; + + return byteCount; + } + + /// + /// Decodes all the bytes in the specified byte array into a set of characters. + /// + /// A character array containing the results of decoding the specified sequence of bytes. + /// The byte array containing the sequence of bytes to decode. + public override char[] GetChars(byte[] bytes) + { + return GetChars(bytes, 0, bytes.Length); + } + + /// + /// Decodes a sequence of bytes from the specified byte array into a set of characters. + /// + /// The chars. + /// The byte array containing the sequence of bytes to decode. + /// The index of the first byte to decode. + /// The number of bytes to decode. + public override char[] GetChars(byte[] bytes, int index, int count) + { + if(bytes == null) throw new ArgumentNullException(nameof(bytes)); + + if(index < 0) throw new ArgumentOutOfRangeException(nameof(index)); + + if(count < 0) throw new ArgumentOutOfRangeException(nameof(count)); + + if(count + index > bytes.Length) throw new ArgumentOutOfRangeException(nameof(count)); + + char[] chars = new char[count]; + + for(int i = 0; i < count; i++) chars[i] = GetChar(bytes[index + i]); + + return chars; + } + + /// + /// Calculates the maximum number of bytes produced by encoding the specified number of characters. + /// + /// The maximum number of bytes produced by encoding the specified number of characters. + /// The number of characters to encode. + public override int GetMaxByteCount(int charCount) + { + if(charCount < 0) throw new ArgumentOutOfRangeException(nameof(charCount)); + + return charCount; + } + + /// + /// Calculates the maximum number of characters produced by decoding the specified number of bytes. + /// + /// The maximum number of characters produced by decoding the specified number of bytes. + /// The number of bytes to decode. + public override int GetMaxCharCount(int byteCount) + { + if(byteCount < 0) throw new ArgumentOutOfRangeException(nameof(byteCount)); + + return byteCount; + } + + /// + /// Returns a sequence of bytes that specifies the encoding used. + /// + /// A byte array of length zero, as a preamble is not required. + public override byte[] GetPreamble() + { + return new byte[0]; + } + + /// + /// Decodes all the bytes in the specified byte array into a string. + /// + /// A string that contains the results of decoding the specified sequence of bytes. + /// The byte array containing the sequence of bytes to decode. + public string GetString(byte[] bytes) + { + return GetString(bytes, 0, bytes.Length); + } + + /// + /// Decodes a sequence of bytes from the specified byte array into a string. + /// + /// A string that contains the results of decoding the specified sequence of bytes. + /// The byte array containing the sequence of bytes to decode. + /// The index of the first byte to decode. + /// The number of bytes to decode. + public override string GetString(byte[] bytes, int index, int count) + { + return new string(GetChars(bytes, index, count)); + } + + /// + /// Converts a GEM character to an Unicode character + /// + /// Unicode character. + /// GEM character. + static char GetChar(byte character) + { + return GemTable[character]; + } + + /// + /// Converts a Unicode character to an GEM character + /// + /// GEM character. + /// Unicode character. + static byte GetByte(char character) + { + switch(character) + { + case '\u0000': return 0x00; + case '\u21E7': return 0x01; + case '\u21E9': return 0x02; + case '\u21E8': return 0x03; + case '\u21E6': return 0x04; + case '\u25FC': return 0x05; + case '\u25C6': return 0x07; + case '\u2713': return 0x08; + case '\u266A': return 0x0B; + case '\u25B4': return 0x0C; + case '\u25BE': return 0x0D; + case '\u25B8': return 0x0E; + case '\u25C2': return 0x0F; + case '\u25BA': return 0x10; + case '\u25C4': return 0x11; + case '\u29D3': return 0x12; + case '\u2582': return 0x13; + case '\u2195': return 0x16; + case '\u21A8': return 0x17; + case '\u2191': return 0x18; + case '\u2193': return 0x19; + case '\u2192': return 0x1A; + case '\u2190': return 0x1B; + case '\u221F': return 0x1C; + case '\u2194': return 0x1D; + case '\u25B2': return 0x1E; + case '\u25BC': return 0x1F; + case '\u0020': return 0x20; + case '\u0021': return 0x21; + case '\u0022': return 0x22; + case '\u0023': return 0x23; + case '\u0024': return 0x24; + case '\u0025': return 0x25; + case '\u0026': return 0x26; + case '\u0027': return 0x27; + case '\u0028': return 0x28; + case '\u0029': return 0x29; + case '\u002A': return 0x2A; + case '\u002B': return 0x2B; + case '\u002C': return 0x2C; + case '\u002D': return 0x2D; + case '\u002E': return 0x2E; + case '\u002F': return 0x2F; + case '\u0030': return 0x30; + case '\u0031': return 0x31; + case '\u0032': return 0x32; + case '\u0033': return 0x33; + case '\u0034': return 0x34; + case '\u0035': return 0x35; + case '\u0036': return 0x36; + case '\u0037': return 0x37; + case '\u0038': return 0x38; + case '\u0039': return 0x39; + case '\u003A': return 0x3A; + case '\u003B': return 0x3B; + case '\u003C': return 0x3C; + case '\u003D': return 0x3D; + case '\u003E': return 0x3E; + case '\u003F': return 0x3F; + case '\u0040': return 0x40; + case '\u0041': return 0x41; + case '\u0042': return 0x42; + case '\u0043': return 0x43; + case '\u0044': return 0x44; + case '\u0045': return 0x45; + case '\u0046': return 0x46; + case '\u0047': return 0x47; + case '\u0048': return 0x48; + case '\u0049': return 0x49; + case '\u004A': return 0x4A; + case '\u004B': return 0x4B; + case '\u004C': return 0x4C; + case '\u004D': return 0x4D; + case '\u004E': return 0x4E; + case '\u004F': return 0x4F; + case '\u0050': return 0x50; + case '\u0051': return 0x51; + case '\u0052': return 0x52; + case '\u0053': return 0x53; + case '\u0054': return 0x54; + case '\u0055': return 0x55; + case '\u0056': return 0x56; + case '\u0057': return 0x57; + case '\u0058': return 0x58; + case '\u0059': return 0x59; + case '\u005A': return 0x5A; + case '\u005B': return 0x5B; + case '\u005C': return 0x5C; + case '\u005D': return 0x5D; + case '\u005E': return 0x5E; + case '\u005F': return 0x5F; + case '\u0060': return 0x60; + case '\u0061': return 0x61; + case '\u0062': return 0x62; + case '\u0063': return 0x63; + case '\u0064': return 0x64; + case '\u0065': return 0x65; + case '\u0066': return 0x66; + case '\u0067': return 0x67; + case '\u0068': return 0x68; + case '\u0069': return 0x69; + case '\u006A': return 0x6A; + case '\u006B': return 0x6B; + case '\u006C': return 0x6C; + case '\u006D': return 0x6D; + case '\u006E': return 0x6E; + case '\u006F': return 0x6F; + case '\u0070': return 0x70; + case '\u0071': return 0x71; + case '\u0072': return 0x72; + case '\u0073': return 0x73; + case '\u0074': return 0x74; + case '\u0075': return 0x75; + case '\u0076': return 0x76; + case '\u0077': return 0x77; + case '\u0078': return 0x78; + case '\u0079': return 0x79; + case '\u007A': return 0x7A; + case '\u007B': return 0x7B; + case '\u007C': return 0x7C; + case '\u007D': return 0x7D; + case '\u007E': return 0x7E; + case '\u2302': return 0x7F; + case '\u00C7': return 0x80; + case '\u00FC': return 0x81; + case '\u00E9': return 0x82; + case '\u00E2': return 0x83; + case '\u00E4': return 0x84; + case '\u00E0': return 0x85; + case '\u00E5': return 0x86; + case '\u00E7': return 0x87; + case '\u00EA': return 0x88; + case '\u00EB': return 0x89; + case '\u00E8': return 0x8A; + case '\u00EF': return 0x8B; + case '\u00EE': return 0x8C; + case '\u00EC': return 0x8D; + case '\u00C4': return 0x8E; + case '\u00C5': return 0x8F; + case '\u00C9': return 0x90; + case '\u00E6': return 0x91; + case '\u00C6': return 0x92; + case '\u00F4': return 0x93; + case '\u00F6': return 0x94; + case '\u00F2': return 0x95; + case '\u00FB': return 0x96; + case '\u00F9': return 0x97; + case '\u00FF': return 0x98; + case '\u00D6': return 0x99; + case '\u00DC': return 0x9A; + case '\u00F8': return 0x9B; + case '\u00A3': return 0x9C; + case '\u00D8': return 0x9D; + case '\u00A4': return 0x9E; + case '\u0192': return 0x9F; + case '\u00E1': return 0xA0; + case '\u00ED': return 0xA1; + case '\u00F3': return 0xA2; + case '\u00FA': return 0xA3; + case '\u00F1': return 0xA4; + case '\u00D1': return 0xA5; + case '\u00AA': return 0xA6; + case '\u00BA': return 0xA7; + case '\u00BF': return 0xA8; + case '\u201C': return 0xA9; + case '\u201D': return 0xAA; + case '\u2039': return 0xAB; + case '\u203A': return 0xAC; + case '\u00A1': return 0xAD; + case '\u00AB': return 0xAE; + case '\u00BB': return 0xAF; + case '\u00E3': return 0xB0; + case '\u00F5': return 0xB1; + case '\u00A5': return 0xB2; + case '\u00A2': return 0xB3; + case '\u0153': return 0xB4; + case '\u0152': return 0xB5; + case '\u00C0': return 0xB6; + case '\u00C3': return 0xB7; + case '\u00D5': return 0xB8; + case '\u00A7': return 0xB9; + case '\u2821': return 0xBA; + case '\u2020': return 0xBB; + case '\u00B6': return 0xBC; + case '\u00A9': return 0xBD; + case '\u00AE': return 0xBE; + case '\u2122': return 0xBF; + case '\u201E': return 0xC0; + case '\u2026': return 0xC1; + case '\u2030': return 0xC2; + case '\u2022': return 0xC3; + case '\u2013': return 0xC4; + case '\u2014': return 0xC5; + case '\u2070': return 0xC6; + case '\u00C1': return 0xC7; + case '\u00C2': return 0xC8; + case '\u00C8': return 0xC9; + case '\u00CA': return 0xCA; + case '\u00CB': return 0xCB; + case '\u00CC': return 0xCC; + case '\u00CD': return 0xCD; + case '\u00CE': return 0xCE; + case '\u00CF': return 0xCF; + case '\u00D2': return 0xD0; + case '\u00D3': return 0xD1; + case '\u00D4': return 0xD2; + case '\u0160': return 0xD3; + case '\u0161': return 0xD4; + case '\u00D9': return 0xD5; + case '\u00DA': return 0xD6; + case '\u00DB': return 0xD7; + case '\u0178': return 0xD8; + case '\u00DF': return 0xD9; + case '\u03B1': return 0xE0; + case '\u03B2': return 0xE1; + case '\u0393': return 0xE2; + case '\u03C0': return 0xE3; + case '\u03A3': return 0xE4; + case '\u03C3': return 0xE5; + case '\u00B5': return 0xE6; + case '\u03C4': return 0xE7; + case '\u03A6': return 0xE8; + case '\u0398': return 0xE9; + case '\u03A9': return 0xEA; + case '\u03B4': return 0xEB; + case '\u222E': return 0xEC; + case '\u0278': return 0xED; + case '\u2208': return 0xEE; + case '\u2229': return 0xEF; + case '\u2261': return 0xF0; + case '\u00B1': return 0xF1; + case '\u2265': return 0xF2; + case '\u2264': return 0xF3; + case '\u2320': return 0xF4; + case '\u2321': return 0xF5; + case '\u00F7': return 0xF6; + case '\u2248': return 0xF7; + case '\u00B0': return 0xF8; + case '\u2219': return 0xF9; + case '\u00B7': return 0xFA; + case '\u221A': return 0xFB; + case '\u207F': return 0xFC; + case '\u00B2': return 0xFD; + case '\u25A0': return 0xFE; + case '\u2205': return 0xFF; + default: + // Fallback to '?' + return 0x3F; + } + } + } +} \ No newline at end of file diff --git a/README.md b/README.md index 66f2c78..810d9d5 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,7 @@ Supported encodings * Atari ST character set * Commodore PET Standard Code for Information Interchange (PETSCII) * DEC Radix-50 +* GEM Character Set * MacArabic * MacCentralEuropean * MacCroatian