| 1 | const std = @import("std"); |
| 2 | |
| 3 | /// https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WindowsBestFit/bestfit1252.txt |
| 4 | pub fn toCodepoint(c: u8) u16 { |
| 5 | return switch (c) { |
| 6 | 0x80 => 0x20ac, // Euro Sign |
| 7 | 0x82 => 0x201a, // Single Low-9 Quotation Mark |
| 8 | 0x83 => 0x0192, // Latin Small Letter F With Hook |
| 9 | 0x84 => 0x201e, // Double Low-9 Quotation Mark |
| 10 | 0x85 => 0x2026, // Horizontal Ellipsis |
| 11 | 0x86 => 0x2020, // Dagger |
| 12 | 0x87 => 0x2021, // Double Dagger |
| 13 | 0x88 => 0x02c6, // Modifier Letter Circumflex Accent |
| 14 | 0x89 => 0x2030, // Per Mille Sign |
| 15 | 0x8a => 0x0160, // Latin Capital Letter S With Caron |
| 16 | 0x8b => 0x2039, // Single Left-Pointing Angle Quotation Mark |
| 17 | 0x8c => 0x0152, // Latin Capital Ligature Oe |
| 18 | 0x8e => 0x017d, // Latin Capital Letter Z With Caron |
| 19 | 0x91 => 0x2018, // Left Single Quotation Mark |
| 20 | 0x92 => 0x2019, // Right Single Quotation Mark |
| 21 | 0x93 => 0x201c, // Left Double Quotation Mark |
| 22 | 0x94 => 0x201d, // Right Double Quotation Mark |
| 23 | 0x95 => 0x2022, // Bullet |
| 24 | 0x96 => 0x2013, // En Dash |
| 25 | 0x97 => 0x2014, // Em Dash |
| 26 | 0x98 => 0x02dc, // Small Tilde |
| 27 | 0x99 => 0x2122, // Trade Mark Sign |
| 28 | 0x9a => 0x0161, // Latin Small Letter S With Caron |
| 29 | 0x9b => 0x203a, // Single Right-Pointing Angle Quotation Mark |
| 30 | 0x9c => 0x0153, // Latin Small Ligature Oe |
| 31 | 0x9e => 0x017e, // Latin Small Letter Z With Caron |
| 32 | 0x9f => 0x0178, // Latin Capital Letter Y With Diaeresis |
| 33 | else => c, |
| 34 | }; |
| 35 | } |
| 36 | |
| 37 | /// https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WindowsBestFit/bestfit1252.txt |
| 38 | /// Plus some mappings found empirically by iterating all codepoints: |
| 39 | /// 0x2007 => 0xA0, // Figure Space |
| 40 | /// 0x2008 => ' ', // Punctuation Space |
| 41 | /// 0x2009 => ' ', // Thin Space |
| 42 | /// 0x200A => ' ', // Hair Space |
| 43 | /// 0x2012 => '-', // Figure Dash |
| 44 | /// 0x2015 => '-', // Horizontal Bar |
| 45 | /// 0x201B => '\'', // Single High-reversed-9 Quotation Mark |
| 46 | /// 0x201F => '"', // Double High-reversed-9 Quotation Mark |
| 47 | /// 0x202F => 0xA0, // Narrow No-Break Space |
| 48 | /// 0x2033 => '"', // Double Prime |
| 49 | /// 0x2036 => '"', // Reversed Double Prime |
| 50 | pub fn bestFitFromCodepoint(codepoint: u21) ?u8 { |
| 51 | return switch (codepoint) { |
| 52 | 0x00...0x7F, |
| 53 | 0x81, |
| 54 | 0x8D, |
| 55 | 0x8F, |
| 56 | 0x90, |
| 57 | 0x9D, |
| 58 | 0xA0...0xFF, |
| 59 | => @intCast(codepoint), |
| 60 | 0x0100 => 0x41, // Latin Capital Letter A With Macron |
| 61 | 0x0101 => 0x61, // Latin Small Letter A With Macron |
| 62 | 0x0102 => 0x41, // Latin Capital Letter A With Breve |
| 63 | 0x0103 => 0x61, // Latin Small Letter A With Breve |
| 64 | 0x0104 => 0x41, // Latin Capital Letter A With Ogonek |
| 65 | 0x0105 => 0x61, // Latin Small Letter A With Ogonek |
| 66 | 0x0106 => 0x43, // Latin Capital Letter C With Acute |
| 67 | 0x0107 => 0x63, // Latin Small Letter C With Acute |
| 68 | 0x0108 => 0x43, // Latin Capital Letter C With Circumflex |
| 69 | 0x0109 => 0x63, // Latin Small Letter C With Circumflex |
| 70 | 0x010a => 0x43, // Latin Capital Letter C With Dot Above |
| 71 | 0x010b => 0x63, // Latin Small Letter C With Dot Above |
| 72 | 0x010c => 0x43, // Latin Capital Letter C With Caron |
| 73 | 0x010d => 0x63, // Latin Small Letter C With Caron |
| 74 | 0x010e => 0x44, // Latin Capital Letter D With Caron |
| 75 | 0x010f => 0x64, // Latin Small Letter D With Caron |
| 76 | 0x0110 => 0xd0, // Latin Capital Letter D With Stroke |
| 77 | 0x0111 => 0x64, // Latin Small Letter D With Stroke |
| 78 | 0x0112 => 0x45, // Latin Capital Letter E With Macron |
| 79 | 0x0113 => 0x65, // Latin Small Letter E With Macron |
| 80 | 0x0114 => 0x45, // Latin Capital Letter E With Breve |
| 81 | 0x0115 => 0x65, // Latin Small Letter E With Breve |
| 82 | 0x0116 => 0x45, // Latin Capital Letter E With Dot Above |
| 83 | 0x0117 => 0x65, // Latin Small Letter E With Dot Above |
| 84 | 0x0118 => 0x45, // Latin Capital Letter E With Ogonek |
| 85 | 0x0119 => 0x65, // Latin Small Letter E With Ogonek |
| 86 | 0x011a => 0x45, // Latin Capital Letter E With Caron |
| 87 | 0x011b => 0x65, // Latin Small Letter E With Caron |
| 88 | 0x011c => 0x47, // Latin Capital Letter G With Circumflex |
| 89 | 0x011d => 0x67, // Latin Small Letter G With Circumflex |
| 90 | 0x011e => 0x47, // Latin Capital Letter G With Breve |
| 91 | 0x011f => 0x67, // Latin Small Letter G With Breve |
| 92 | 0x0120 => 0x47, // Latin Capital Letter G With Dot Above |
| 93 | 0x0121 => 0x67, // Latin Small Letter G With Dot Above |
| 94 | 0x0122 => 0x47, // Latin Capital Letter G With Cedilla |
| 95 | 0x0123 => 0x67, // Latin Small Letter G With Cedilla |
| 96 | 0x0124 => 0x48, // Latin Capital Letter H With Circumflex |
| 97 | 0x0125 => 0x68, // Latin Small Letter H With Circumflex |
| 98 | 0x0126 => 0x48, // Latin Capital Letter H With Stroke |
| 99 | 0x0127 => 0x68, // Latin Small Letter H With Stroke |
| 100 | 0x0128 => 0x49, // Latin Capital Letter I With Tilde |
| 101 | 0x0129 => 0x69, // Latin Small Letter I With Tilde |
| 102 | 0x012a => 0x49, // Latin Capital Letter I With Macron |
| 103 | 0x012b => 0x69, // Latin Small Letter I With Macron |
| 104 | 0x012c => 0x49, // Latin Capital Letter I With Breve |
| 105 | 0x012d => 0x69, // Latin Small Letter I With Breve |
| 106 | 0x012e => 0x49, // Latin Capital Letter I With Ogonek |
| 107 | 0x012f => 0x69, // Latin Small Letter I With Ogonek |
| 108 | 0x0130 => 0x49, // Latin Capital Letter I With Dot Above |
| 109 | 0x0131 => 0x69, // Latin Small Letter Dotless I |
| 110 | 0x0134 => 0x4a, // Latin Capital Letter J With Circumflex |
| 111 | 0x0135 => 0x6a, // Latin Small Letter J With Circumflex |
| 112 | 0x0136 => 0x4b, // Latin Capital Letter K With Cedilla |
| 113 | 0x0137 => 0x6b, // Latin Small Letter K With Cedilla |
| 114 | 0x0139 => 0x4c, // Latin Capital Letter L With Acute |
| 115 | 0x013a => 0x6c, // Latin Small Letter L With Acute |
| 116 | 0x013b => 0x4c, // Latin Capital Letter L With Cedilla |
| 117 | 0x013c => 0x6c, // Latin Small Letter L With Cedilla |
| 118 | 0x013d => 0x4c, // Latin Capital Letter L With Caron |
| 119 | 0x013e => 0x6c, // Latin Small Letter L With Caron |
| 120 | 0x0141 => 0x4c, // Latin Capital Letter L With Stroke |
| 121 | 0x0142 => 0x6c, // Latin Small Letter L With Stroke |
| 122 | 0x0143 => 0x4e, // Latin Capital Letter N With Acute |
| 123 | 0x0144 => 0x6e, // Latin Small Letter N With Acute |
| 124 | 0x0145 => 0x4e, // Latin Capital Letter N With Cedilla |
| 125 | 0x0146 => 0x6e, // Latin Small Letter N With Cedilla |
| 126 | 0x0147 => 0x4e, // Latin Capital Letter N With Caron |
| 127 | 0x0148 => 0x6e, // Latin Small Letter N With Caron |
| 128 | 0x014c => 0x4f, // Latin Capital Letter O With Macron |
| 129 | 0x014d => 0x6f, // Latin Small Letter O With Macron |
| 130 | 0x014e => 0x4f, // Latin Capital Letter O With Breve |
| 131 | 0x014f => 0x6f, // Latin Small Letter O With Breve |
| 132 | 0x0150 => 0x4f, // Latin Capital Letter O With Double Acute |
| 133 | 0x0151 => 0x6f, // Latin Small Letter O With Double Acute |
| 134 | 0x0152 => 0x8c, // Latin Capital Ligature Oe |
| 135 | 0x0153 => 0x9c, // Latin Small Ligature Oe |
| 136 | 0x0154 => 0x52, // Latin Capital Letter R With Acute |
| 137 | 0x0155 => 0x72, // Latin Small Letter R With Acute |
| 138 | 0x0156 => 0x52, // Latin Capital Letter R With Cedilla |
| 139 | 0x0157 => 0x72, // Latin Small Letter R With Cedilla |
| 140 | 0x0158 => 0x52, // Latin Capital Letter R With Caron |
| 141 | 0x0159 => 0x72, // Latin Small Letter R With Caron |
| 142 | 0x015a => 0x53, // Latin Capital Letter S With Acute |
| 143 | 0x015b => 0x73, // Latin Small Letter S With Acute |
| 144 | 0x015c => 0x53, // Latin Capital Letter S With Circumflex |
| 145 | 0x015d => 0x73, // Latin Small Letter S With Circumflex |
| 146 | 0x015e => 0x53, // Latin Capital Letter S With Cedilla |
| 147 | 0x015f => 0x73, // Latin Small Letter S With Cedilla |
| 148 | 0x0160 => 0x8a, // Latin Capital Letter S With Caron |
| 149 | 0x0161 => 0x9a, // Latin Small Letter S With Caron |
| 150 | 0x0162 => 0x54, // Latin Capital Letter T With Cedilla |
| 151 | 0x0163 => 0x74, // Latin Small Letter T With Cedilla |
| 152 | 0x0164 => 0x54, // Latin Capital Letter T With Caron |
| 153 | 0x0165 => 0x74, // Latin Small Letter T With Caron |
| 154 | 0x0166 => 0x54, // Latin Capital Letter T With Stroke |
| 155 | 0x0167 => 0x74, // Latin Small Letter T With Stroke |
| 156 | 0x0168 => 0x55, // Latin Capital Letter U With Tilde |
| 157 | 0x0169 => 0x75, // Latin Small Letter U With Tilde |
| 158 | 0x016a => 0x55, // Latin Capital Letter U With Macron |
| 159 | 0x016b => 0x75, // Latin Small Letter U With Macron |
| 160 | 0x016c => 0x55, // Latin Capital Letter U With Breve |
| 161 | 0x016d => 0x75, // Latin Small Letter U With Breve |
| 162 | 0x016e => 0x55, // Latin Capital Letter U With Ring Above |
| 163 | 0x016f => 0x75, // Latin Small Letter U With Ring Above |
| 164 | 0x0170 => 0x55, // Latin Capital Letter U With Double Acute |
| 165 | 0x0171 => 0x75, // Latin Small Letter U With Double Acute |
| 166 | 0x0172 => 0x55, // Latin Capital Letter U With Ogonek |
| 167 | 0x0173 => 0x75, // Latin Small Letter U With Ogonek |
| 168 | 0x0174 => 0x57, // Latin Capital Letter W With Circumflex |
| 169 | 0x0175 => 0x77, // Latin Small Letter W With Circumflex |
| 170 | 0x0176 => 0x59, // Latin Capital Letter Y With Circumflex |
| 171 | 0x0177 => 0x79, // Latin Small Letter Y With Circumflex |
| 172 | 0x0178 => 0x9f, // Latin Capital Letter Y With Diaeresis |
| 173 | 0x0179 => 0x5a, // Latin Capital Letter Z With Acute |
| 174 | 0x017a => 0x7a, // Latin Small Letter Z With Acute |
| 175 | 0x017b => 0x5a, // Latin Capital Letter Z With Dot Above |
| 176 | 0x017c => 0x7a, // Latin Small Letter Z With Dot Above |
| 177 | 0x017d => 0x8e, // Latin Capital Letter Z With Caron |
| 178 | 0x017e => 0x9e, // Latin Small Letter Z With Caron |
| 179 | 0x0180 => 0x62, // Latin Small Letter B With Stroke |
| 180 | 0x0189 => 0xd0, // Latin Capital Letter African D |
| 181 | 0x0191 => 0x83, // Latin Capital Letter F With Hook |
| 182 | 0x0192 => 0x83, // Latin Small Letter F With Hook |
| 183 | 0x0197 => 0x49, // Latin Capital Letter I With Stroke |
| 184 | 0x019a => 0x6c, // Latin Small Letter L With Bar |
| 185 | 0x019f => 0x4f, // Latin Capital Letter O With Middle Tilde |
| 186 | 0x01a0 => 0x4f, // Latin Capital Letter O With Horn |
| 187 | 0x01a1 => 0x6f, // Latin Small Letter O With Horn |
| 188 | 0x01ab => 0x74, // Latin Small Letter T With Palatal Hook |
| 189 | 0x01ae => 0x54, // Latin Capital Letter T With Retroflex Hook |
| 190 | 0x01af => 0x55, // Latin Capital Letter U With Horn |
| 191 | 0x01b0 => 0x75, // Latin Small Letter U With Horn |
| 192 | 0x01b6 => 0x7a, // Latin Small Letter Z With Stroke |
| 193 | 0x01c0 => 0x7c, // Latin Letter Dental Click |
| 194 | 0x01c3 => 0x21, // Latin Letter Retroflex Click |
| 195 | 0x01cd => 0x41, // Latin Capital Letter A With Caron |
| 196 | 0x01ce => 0x61, // Latin Small Letter A With Caron |
| 197 | 0x01cf => 0x49, // Latin Capital Letter I With Caron |
| 198 | 0x01d0 => 0x69, // Latin Small Letter I With Caron |
| 199 | 0x01d1 => 0x4f, // Latin Capital Letter O With Caron |
| 200 | 0x01d2 => 0x6f, // Latin Small Letter O With Caron |
| 201 | 0x01d3 => 0x55, // Latin Capital Letter U With Caron |
| 202 | 0x01d4 => 0x75, // Latin Small Letter U With Caron |
| 203 | 0x01d5 => 0x55, // Latin Capital Letter U With Diaeresis And Macron |
| 204 | 0x01d6 => 0x75, // Latin Small Letter U With Diaeresis And Macron |
| 205 | 0x01d7 => 0x55, // Latin Capital Letter U With Diaeresis And Acute |
| 206 | 0x01d8 => 0x75, // Latin Small Letter U With Diaeresis And Acute |
| 207 | 0x01d9 => 0x55, // Latin Capital Letter U With Diaeresis And Caron |
| 208 | 0x01da => 0x75, // Latin Small Letter U With Diaeresis And Caron |
| 209 | 0x01db => 0x55, // Latin Capital Letter U With Diaeresis And Grave |
| 210 | 0x01dc => 0x75, // Latin Small Letter U With Diaeresis And Grave |
| 211 | 0x01de => 0x41, // Latin Capital Letter A With Diaeresis And Macron |
| 212 | 0x01df => 0x61, // Latin Small Letter A With Diaeresis And Macron |
| 213 | 0x01e4 => 0x47, // Latin Capital Letter G With Stroke |
| 214 | 0x01e5 => 0x67, // Latin Small Letter G With Stroke |
| 215 | 0x01e6 => 0x47, // Latin Capital Letter G With Caron |
| 216 | 0x01e7 => 0x67, // Latin Small Letter G With Caron |
| 217 | 0x01e8 => 0x4b, // Latin Capital Letter K With Caron |
| 218 | 0x01e9 => 0x6b, // Latin Small Letter K With Caron |
| 219 | 0x01ea => 0x4f, // Latin Capital Letter O With Ogonek |
| 220 | 0x01eb => 0x6f, // Latin Small Letter O With Ogonek |
| 221 | 0x01ec => 0x4f, // Latin Capital Letter O With Ogonek And Macron |
| 222 | 0x01ed => 0x6f, // Latin Small Letter O With Ogonek And Macron |
| 223 | 0x01f0 => 0x6a, // Latin Small Letter J With Caron |
| 224 | 0x0261 => 0x67, // Latin Small Letter Script G |
| 225 | 0x02b9 => 0x27, // Modifier Letter Prime |
| 226 | 0x02ba => 0x22, // Modifier Letter Double Prime |
| 227 | 0x02bc => 0x27, // Modifier Letter Apostrophe |
| 228 | 0x02c4 => 0x5e, // Modifier Letter Up Arrowhead |
| 229 | 0x02c6 => 0x88, // Modifier Letter Circumflex Accent |
| 230 | 0x02c8 => 0x27, // Modifier Letter Vertical Line |
| 231 | 0x02c9 => 0xaf, // Modifier Letter Macron |
| 232 | 0x02ca => 0xb4, // Modifier Letter Acute Accent |
| 233 | 0x02cb => 0x60, // Modifier Letter Grave Accent |
| 234 | 0x02cd => 0x5f, // Modifier Letter Low Macron |
| 235 | 0x02da => 0xb0, // Ring Above |
| 236 | 0x02dc => 0x98, // Small Tilde |
| 237 | 0x0300 => 0x60, // Combining Grave Accent |
| 238 | 0x0301 => 0xb4, // Combining Acute Accent |
| 239 | 0x0302 => 0x5e, // Combining Circumflex Accent |
| 240 | 0x0303 => 0x7e, // Combining Tilde |
| 241 | 0x0304 => 0xaf, // Combining Macron |
| 242 | 0x0305 => 0xaf, // Combining Overline |
| 243 | 0x0308 => 0xa8, // Combining Diaeresis |
| 244 | 0x030a => 0xb0, // Combining Ring Above |
| 245 | 0x030e => 0x22, // Combining Double Vertical Line Above |
| 246 | 0x0327 => 0xb8, // Combining Cedilla |
| 247 | 0x0331 => 0x5f, // Combining Macron Below |
| 248 | 0x0332 => 0x5f, // Combining Low Line |
| 249 | 0x037e => 0x3b, // Greek Question Mark |
| 250 | 0x0393 => 0x47, // Greek Capital Letter Gamma |
| 251 | 0x0398 => 0x54, // Greek Capital Letter Theta |
| 252 | 0x03a3 => 0x53, // Greek Capital Letter Sigma |
| 253 | 0x03a6 => 0x46, // Greek Capital Letter Phi |
| 254 | 0x03a9 => 0x4f, // Greek Capital Letter Omega |
| 255 | 0x03b1 => 0x61, // Greek Small Letter Alpha |
| 256 | 0x03b2 => 0xdf, // Greek Small Letter Beta |
| 257 | 0x03b4 => 0x64, // Greek Small Letter Delta |
| 258 | 0x03b5 => 0x65, // Greek Small Letter Epsilon |
| 259 | 0x03bc => 0xb5, // Greek Small Letter Mu |
| 260 | 0x03c0 => 0x70, // Greek Small Letter Pi |
| 261 | 0x03c3 => 0x73, // Greek Small Letter Sigma |
| 262 | 0x03c4 => 0x74, // Greek Small Letter Tau |
| 263 | 0x03c6 => 0x66, // Greek Small Letter Phi |
| 264 | 0x04bb => 0x68, // Cyrillic Small Letter Shha |
| 265 | 0x0589 => 0x3a, // Armenian Full Stop |
| 266 | 0x066a => 0x25, // Arabic Percent Sign |
| 267 | 0x2000 => 0x20, // En Quad |
| 268 | 0x2001 => 0x20, // Em Quad |
| 269 | 0x2002 => 0x20, // En Space |
| 270 | 0x2003 => 0x20, // Em Space |
| 271 | 0x2004 => 0x20, // Three-Per-Em Space |
| 272 | 0x2005 => 0x20, // Four-Per-Em Space |
| 273 | 0x2006 => 0x20, // Six-Per-Em Space |
| 274 | 0x2010 => 0x2d, // Hyphen |
| 275 | 0x2011 => 0x2d, // Non-Breaking Hyphen |
| 276 | 0x2013 => 0x96, // En Dash |
| 277 | 0x2014 => 0x97, // Em Dash |
| 278 | 0x2017 => 0x3d, // Double Low Line |
| 279 | 0x2018 => 0x91, // Left Single Quotation Mark |
| 280 | 0x2019 => 0x92, // Right Single Quotation Mark |
| 281 | 0x201a => 0x82, // Single Low-9 Quotation Mark |
| 282 | 0x201c => 0x93, // Left Double Quotation Mark |
| 283 | 0x201d => 0x94, // Right Double Quotation Mark |
| 284 | 0x201e => 0x84, // Double Low-9 Quotation Mark |
| 285 | 0x2020 => 0x86, // Dagger |
| 286 | 0x2021 => 0x87, // Double Dagger |
| 287 | 0x2022 => 0x95, // Bullet |
| 288 | 0x2024 => 0xb7, // One Dot Leader |
| 289 | 0x2026 => 0x85, // Horizontal Ellipsis |
| 290 | 0x2030 => 0x89, // Per Mille Sign |
| 291 | 0x2032 => 0x27, // Prime |
| 292 | 0x2035 => 0x60, // Reversed Prime |
| 293 | 0x2039 => 0x8b, // Single Left-Pointing Angle Quotation Mark |
| 294 | 0x203a => 0x9b, // Single Right-Pointing Angle Quotation Mark |
| 295 | 0x2044 => 0x2f, // Fraction Slash |
| 296 | 0x2070 => 0xb0, // Superscript Zero |
| 297 | 0x2074 => 0x34, // Superscript Four |
| 298 | 0x2075 => 0x35, // Superscript Five |
| 299 | 0x2076 => 0x36, // Superscript Six |
| 300 | 0x2077 => 0x37, // Superscript Seven |
| 301 | 0x2078 => 0x38, // Superscript Eight |
| 302 | 0x207f => 0x6e, // Superscript Latin Small Letter N |
| 303 | 0x2080 => 0x30, // Subscript Zero |
| 304 | 0x2081 => 0x31, // Subscript One |
| 305 | 0x2082 => 0x32, // Subscript Two |
| 306 | 0x2083 => 0x33, // Subscript Three |
| 307 | 0x2084 => 0x34, // Subscript Four |
| 308 | 0x2085 => 0x35, // Subscript Five |
| 309 | 0x2086 => 0x36, // Subscript Six |
| 310 | 0x2087 => 0x37, // Subscript Seven |
| 311 | 0x2088 => 0x38, // Subscript Eight |
| 312 | 0x2089 => 0x39, // Subscript Nine |
| 313 | 0x20ac => 0x80, // Euro Sign |
| 314 | 0x20a1 => 0xa2, // Colon Sign |
| 315 | 0x20a4 => 0xa3, // Lira Sign |
| 316 | 0x20a7 => 0x50, // Peseta Sign |
| 317 | 0x2102 => 0x43, // Double-Struck Capital C |
| 318 | 0x2107 => 0x45, // Euler Constant |
| 319 | 0x210a => 0x67, // Script Small G |
| 320 | 0x210b => 0x48, // Script Capital H |
| 321 | 0x210c => 0x48, // Black-Letter Capital H |
| 322 | 0x210d => 0x48, // Double-Struck Capital H |
| 323 | 0x210e => 0x68, // Planck Constant |
| 324 | 0x2110 => 0x49, // Script Capital I |
| 325 | 0x2111 => 0x49, // Black-Letter Capital I |
| 326 | 0x2112 => 0x4c, // Script Capital L |
| 327 | 0x2113 => 0x6c, // Script Small L |
| 328 | 0x2115 => 0x4e, // Double-Struck Capital N |
| 329 | 0x2118 => 0x50, // Script Capital P |
| 330 | 0x2119 => 0x50, // Double-Struck Capital P |
| 331 | 0x211a => 0x51, // Double-Struck Capital Q |
| 332 | 0x211b => 0x52, // Script Capital R |
| 333 | 0x211c => 0x52, // Black-Letter Capital R |
| 334 | 0x211d => 0x52, // Double-Struck Capital R |
| 335 | 0x2122 => 0x99, // Trade Mark Sign |
| 336 | 0x2124 => 0x5a, // Double-Struck Capital Z |
| 337 | 0x2128 => 0x5a, // Black-Letter Capital Z |
| 338 | 0x212a => 0x4b, // Kelvin Sign |
| 339 | 0x212b => 0xc5, // Angstrom Sign |
| 340 | 0x212c => 0x42, // Script Capital B |
| 341 | 0x212d => 0x43, // Black-Letter Capital C |
| 342 | 0x212e => 0x65, // Estimated Symbol |
| 343 | 0x212f => 0x65, // Script Small E |
| 344 | 0x2130 => 0x45, // Script Capital E |
| 345 | 0x2131 => 0x46, // Script Capital F |
| 346 | 0x2133 => 0x4d, // Script Capital M |
| 347 | 0x2134 => 0x6f, // Script Small O |
| 348 | 0x2205 => 0xd8, // Empty Set |
| 349 | 0x2212 => 0x2d, // Minus Sign |
| 350 | 0x2213 => 0xb1, // Minus-Or-Plus Sign |
| 351 | 0x2215 => 0x2f, // Division Slash |
| 352 | 0x2216 => 0x5c, // Set Minus |
| 353 | 0x2217 => 0x2a, // Asterisk Operator |
| 354 | 0x2218 => 0xb0, // Ring Operator |
| 355 | 0x2219 => 0xb7, // Bullet Operator |
| 356 | 0x221a => 0x76, // Square Root |
| 357 | 0x221e => 0x38, // Infinity |
| 358 | 0x2223 => 0x7c, // Divides |
| 359 | 0x2229 => 0x6e, // Intersection |
| 360 | 0x2236 => 0x3a, // Ratio |
| 361 | 0x223c => 0x7e, // Tilde Operator |
| 362 | 0x2248 => 0x98, // Almost Equal To |
| 363 | 0x2261 => 0x3d, // Identical To |
| 364 | 0x2264 => 0x3d, // Less-Than Or Equal To |
| 365 | 0x2265 => 0x3d, // Greater-Than Or Equal To |
| 366 | 0x226a => 0xab, // Much Less-Than |
| 367 | 0x226b => 0xbb, // Much Greater-Than |
| 368 | 0x22c5 => 0xb7, // Dot Operator |
| 369 | 0x2302 => 0xa6, // House |
| 370 | 0x2303 => 0x5e, // Up Arrowhead |
| 371 | 0x2310 => 0xac, // Reversed Not Sign |
| 372 | 0x2320 => 0x28, // Top Half Integral |
| 373 | 0x2321 => 0x29, // Bottom Half Integral |
| 374 | 0x2329 => 0x3c, // Left-Pointing Angle Bracket |
| 375 | 0x232a => 0x3e, // Right-Pointing Angle Bracket |
| 376 | 0x2500 => 0x2d, // Box Drawings Light Horizontal |
| 377 | 0x2502 => 0xa6, // Box Drawings Light Vertical |
| 378 | 0x250c => 0x2b, // Box Drawings Light Down And Right |
| 379 | 0x2510 => 0x2b, // Box Drawings Light Down And Left |
| 380 | 0x2514 => 0x2b, // Box Drawings Light Up And Right |
| 381 | 0x2518 => 0x2b, // Box Drawings Light Up And Left |
| 382 | 0x251c => 0x2b, // Box Drawings Light Vertical And Right |
| 383 | 0x2524 => 0xa6, // Box Drawings Light Vertical And Left |
| 384 | 0x252c => 0x2d, // Box Drawings Light Down And Horizontal |
| 385 | 0x2534 => 0x2d, // Box Drawings Light Up And Horizontal |
| 386 | 0x253c => 0x2b, // Box Drawings Light Vertical And Horizontal |
| 387 | 0x2550 => 0x2d, // Box Drawings Double Horizontal |
| 388 | 0x2551 => 0xa6, // Box Drawings Double Vertical |
| 389 | 0x2552 => 0x2b, // Box Drawings Down Single And Right Double |
| 390 | 0x2553 => 0x2b, // Box Drawings Down Double And Right Single |
| 391 | 0x2554 => 0x2b, // Box Drawings Double Down And Right |
| 392 | 0x2555 => 0x2b, // Box Drawings Down Single And Left Double |
| 393 | 0x2556 => 0x2b, // Box Drawings Down Double And Left Single |
| 394 | 0x2557 => 0x2b, // Box Drawings Double Down And Left |
| 395 | 0x2558 => 0x2b, // Box Drawings Up Single And Right Double |
| 396 | 0x2559 => 0x2b, // Box Drawings Up Double And Right Single |
| 397 | 0x255a => 0x2b, // Box Drawings Double Up And Right |
| 398 | 0x255b => 0x2b, // Box Drawings Up Single And Left Double |
| 399 | 0x255c => 0x2b, // Box Drawings Up Double And Left Single |
| 400 | 0x255d => 0x2b, // Box Drawings Double Up And Left |
| 401 | 0x255e => 0xa6, // Box Drawings Vertical Single And Right Double |
| 402 | 0x255f => 0xa6, // Box Drawings Vertical Double And Right Single |
| 403 | 0x2560 => 0xa6, // Box Drawings Double Vertical And Right |
| 404 | 0x2561 => 0xa6, // Box Drawings Vertical Single And Left Double |
| 405 | 0x2562 => 0xa6, // Box Drawings Vertical Double And Left Single |
| 406 | 0x2563 => 0xa6, // Box Drawings Double Vertical And Left |
| 407 | 0x2564 => 0x2d, // Box Drawings Down Single And Horizontal Double |
| 408 | 0x2565 => 0x2d, // Box Drawings Down Double And Horizontal Single |
| 409 | 0x2566 => 0x2d, // Box Drawings Double Down And Horizontal |
| 410 | 0x2567 => 0x2d, // Box Drawings Up Single And Horizontal Double |
| 411 | 0x2568 => 0x2d, // Box Drawings Up Double And Horizontal Single |
| 412 | 0x2569 => 0x2d, // Box Drawings Double Up And Horizontal |
| 413 | 0x256a => 0x2b, // Box Drawings Vertical Single And Horizontal Double |
| 414 | 0x256b => 0x2b, // Box Drawings Vertical Double And Horizontal Single |
| 415 | 0x256c => 0x2b, // Box Drawings Double Vertical And Horizontal |
| 416 | 0x2580 => 0xaf, // Upper Half Block |
| 417 | 0x2584 => 0x5f, // Lower Half Block |
| 418 | 0x2588 => 0xa6, // Full Block |
| 419 | 0x258c => 0xa6, // Left Half Block |
| 420 | 0x2590 => 0xa6, // Right Half Block |
| 421 | 0x2591 => 0xa6, // Light Shade |
| 422 | 0x2592 => 0xa6, // Medium Shade |
| 423 | 0x2593 => 0xa6, // Dark Shade |
| 424 | 0x25a0 => 0xa6, // Black Square |
| 425 | 0x263c => 0xa4, // White Sun With Rays |
| 426 | 0x2758 => 0x7c, // Light Vertical Bar |
| 427 | 0x3000 => 0x20, // Ideographic Space |
| 428 | 0x3008 => 0x3c, // Left Angle Bracket |
| 429 | 0x3009 => 0x3e, // Right Angle Bracket |
| 430 | 0x300a => 0xab, // Left Double Angle Bracket |
| 431 | 0x300b => 0xbb, // Right Double Angle Bracket |
| 432 | 0x301a => 0x5b, // Left White Square Bracket |
| 433 | 0x301b => 0x5d, // Right White Square Bracket |
| 434 | 0x30fb => 0xb7, // Katakana Middle Dot |
| 435 | 0xff01 => 0x21, // Fullwidth Exclamation Mark |
| 436 | 0xff02 => 0x22, // Fullwidth Quotation Mark |
| 437 | 0xff03 => 0x23, // Fullwidth Number Sign |
| 438 | 0xff04 => 0x24, // Fullwidth Dollar Sign |
| 439 | 0xff05 => 0x25, // Fullwidth Percent Sign |
| 440 | 0xff06 => 0x26, // Fullwidth Ampersand |
| 441 | 0xff07 => 0x27, // Fullwidth Apostrophe |
| 442 | 0xff08 => 0x28, // Fullwidth Left Parenthesis |
| 443 | 0xff09 => 0x29, // Fullwidth Right Parenthesis |
| 444 | 0xff0a => 0x2a, // Fullwidth Asterisk |
| 445 | 0xff0b => 0x2b, // Fullwidth Plus Sign |
| 446 | 0xff0c => 0x2c, // Fullwidth Comma |
| 447 | 0xff0d => 0x2d, // Fullwidth Hyphen-Minus |
| 448 | 0xff0e => 0x2e, // Fullwidth Full Stop |
| 449 | 0xff0f => 0x2f, // Fullwidth Solidus |
| 450 | 0xff10 => 0x30, // Fullwidth Digit Zero |
| 451 | 0xff11 => 0x31, // Fullwidth Digit One |
| 452 | 0xff12 => 0x32, // Fullwidth Digit Two |
| 453 | 0xff13 => 0x33, // Fullwidth Digit Three |
| 454 | 0xff14 => 0x34, // Fullwidth Digit Four |
| 455 | 0xff15 => 0x35, // Fullwidth Digit Five |
| 456 | 0xff16 => 0x36, // Fullwidth Digit Six |
| 457 | 0xff17 => 0x37, // Fullwidth Digit Seven |
| 458 | 0xff18 => 0x38, // Fullwidth Digit Eight |
| 459 | 0xff19 => 0x39, // Fullwidth Digit Nine |
| 460 | 0xff1a => 0x3a, // Fullwidth Colon |
| 461 | 0xff1b => 0x3b, // Fullwidth Semicolon |
| 462 | 0xff1c => 0x3c, // Fullwidth Less-Than Sign |
| 463 | 0xff1d => 0x3d, // Fullwidth Equals Sign |
| 464 | 0xff1e => 0x3e, // Fullwidth Greater-Than Sign |
| 465 | 0xff1f => 0x3f, // Fullwidth Question Mark |
| 466 | 0xff20 => 0x40, // Fullwidth Commercial At |
| 467 | 0xff21 => 0x41, // Fullwidth Latin Capital Letter A |
| 468 | 0xff22 => 0x42, // Fullwidth Latin Capital Letter B |
| 469 | 0xff23 => 0x43, // Fullwidth Latin Capital Letter C |
| 470 | 0xff24 => 0x44, // Fullwidth Latin Capital Letter D |
| 471 | 0xff25 => 0x45, // Fullwidth Latin Capital Letter E |
| 472 | 0xff26 => 0x46, // Fullwidth Latin Capital Letter F |
| 473 | 0xff27 => 0x47, // Fullwidth Latin Capital Letter G |
| 474 | 0xff28 => 0x48, // Fullwidth Latin Capital Letter H |
| 475 | 0xff29 => 0x49, // Fullwidth Latin Capital Letter I |
| 476 | 0xff2a => 0x4a, // Fullwidth Latin Capital Letter J |
| 477 | 0xff2b => 0x4b, // Fullwidth Latin Capital Letter K |
| 478 | 0xff2c => 0x4c, // Fullwidth Latin Capital Letter L |
| 479 | 0xff2d => 0x4d, // Fullwidth Latin Capital Letter M |
| 480 | 0xff2e => 0x4e, // Fullwidth Latin Capital Letter N |
| 481 | 0xff2f => 0x4f, // Fullwidth Latin Capital Letter O |
| 482 | 0xff30 => 0x50, // Fullwidth Latin Capital Letter P |
| 483 | 0xff31 => 0x51, // Fullwidth Latin Capital Letter Q |
| 484 | 0xff32 => 0x52, // Fullwidth Latin Capital Letter R |
| 485 | 0xff33 => 0x53, // Fullwidth Latin Capital Letter S |
| 486 | 0xff34 => 0x54, // Fullwidth Latin Capital Letter T |
| 487 | 0xff35 => 0x55, // Fullwidth Latin Capital Letter U |
| 488 | 0xff36 => 0x56, // Fullwidth Latin Capital Letter V |
| 489 | 0xff37 => 0x57, // Fullwidth Latin Capital Letter W |
| 490 | 0xff38 => 0x58, // Fullwidth Latin Capital Letter X |
| 491 | 0xff39 => 0x59, // Fullwidth Latin Capital Letter Y |
| 492 | 0xff3a => 0x5a, // Fullwidth Latin Capital Letter Z |
| 493 | 0xff3b => 0x5b, // Fullwidth Left Square Bracket |
| 494 | 0xff3c => 0x5c, // Fullwidth Reverse Solidus |
| 495 | 0xff3d => 0x5d, // Fullwidth Right Square Bracket |
| 496 | 0xff3e => 0x5e, // Fullwidth Circumflex Accent |
| 497 | 0xff3f => 0x5f, // Fullwidth Low Line |
| 498 | 0xff40 => 0x60, // Fullwidth Grave Accent |
| 499 | 0xff41 => 0x61, // Fullwidth Latin Small Letter A |
| 500 | 0xff42 => 0x62, // Fullwidth Latin Small Letter B |
| 501 | 0xff43 => 0x63, // Fullwidth Latin Small Letter C |
| 502 | 0xff44 => 0x64, // Fullwidth Latin Small Letter D |
| 503 | 0xff45 => 0x65, // Fullwidth Latin Small Letter E |
| 504 | 0xff46 => 0x66, // Fullwidth Latin Small Letter F |
| 505 | 0xff47 => 0x67, // Fullwidth Latin Small Letter G |
| 506 | 0xff48 => 0x68, // Fullwidth Latin Small Letter H |
| 507 | 0xff49 => 0x69, // Fullwidth Latin Small Letter I |
| 508 | 0xff4a => 0x6a, // Fullwidth Latin Small Letter J |
| 509 | 0xff4b => 0x6b, // Fullwidth Latin Small Letter K |
| 510 | 0xff4c => 0x6c, // Fullwidth Latin Small Letter L |
| 511 | 0xff4d => 0x6d, // Fullwidth Latin Small Letter M |
| 512 | 0xff4e => 0x6e, // Fullwidth Latin Small Letter N |
| 513 | 0xff4f => 0x6f, // Fullwidth Latin Small Letter O |
| 514 | 0xff50 => 0x70, // Fullwidth Latin Small Letter P |
| 515 | 0xff51 => 0x71, // Fullwidth Latin Small Letter Q |
| 516 | 0xff52 => 0x72, // Fullwidth Latin Small Letter R |
| 517 | 0xff53 => 0x73, // Fullwidth Latin Small Letter S |
| 518 | 0xff54 => 0x74, // Fullwidth Latin Small Letter T |
| 519 | 0xff55 => 0x75, // Fullwidth Latin Small Letter U |
| 520 | 0xff56 => 0x76, // Fullwidth Latin Small Letter V |
| 521 | 0xff57 => 0x77, // Fullwidth Latin Small Letter W |
| 522 | 0xff58 => 0x78, // Fullwidth Latin Small Letter X |
| 523 | 0xff59 => 0x79, // Fullwidth Latin Small Letter Y |
| 524 | 0xff5a => 0x7a, // Fullwidth Latin Small Letter Z |
| 525 | 0xff5b => 0x7b, // Fullwidth Left Curly Bracket |
| 526 | 0xff5c => 0x7c, // Fullwidth Vertical Line |
| 527 | 0xff5d => 0x7d, // Fullwidth Right Curly Bracket |
| 528 | 0xff5e => 0x7e, // Fullwidth Tilde |
| 529 | // Not in the best fit mapping, but RC uses these mappings too |
| 530 | 0x2007 => 0xA0, // Figure Space |
| 531 | 0x2008 => ' ', // Punctuation Space |
| 532 | 0x2009 => ' ', // Thin Space |
| 533 | 0x200A => ' ', // Hair Space |
| 534 | 0x2012 => '-', // Figure Dash |
| 535 | 0x2015 => '-', // Horizontal Bar |
| 536 | 0x201B => '\'', // Single High-reversed-9 Quotation Mark |
| 537 | 0x201F => '"', // Double High-reversed-9 Quotation Mark |
| 538 | 0x202F => 0xA0, // Narrow No-Break Space |
| 539 | 0x2033 => '"', // Double Prime |
| 540 | 0x2036 => '"', // Reversed Double Prime |
| 541 | else => null, |
| 542 | }; |
| 543 | } |