| 1 | /* This file is part of the project "Hilbert II" - http://www.qedeq.org |
| 2 | * |
| 3 | * Copyright 2000-2014, Michael Meyling <mime@qedeq.org>. |
| 4 | * |
| 5 | * "Hilbert II" is free software; you can redistribute |
| 6 | * it and/or modify it under the terms of the GNU General Public |
| 7 | * License as published by the Free Software Foundation; either |
| 8 | * version 2 of the License, or (at your option) any later version. |
| 9 | * |
| 10 | * This program is distributed in the hope that it will be useful, |
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | * GNU General Public License for more details. |
| 14 | */ |
| 15 | |
| 16 | package org.qedeq.kernel.bo.service.unicode; |
| 17 | |
| 18 | |
| 19 | /** |
| 20 | * Special LaTeX into UTF-8 transformations. |
| 21 | * |
| 22 | * @author Michael Meyling |
| 23 | */ |
| 24 | public final class Latex2UnicodeSpecials { |
| 25 | |
| 26 | /** Available subscript characters. */ |
| 27 | private static final String SUBSCRIPT_CHARACTERS = "0123456789()+-="; |
| 28 | |
| 29 | /** Available superscript characters. */ |
| 30 | private static final String SUPERSCRIPT_CHARACTERS = "0123456789()+-=n"; |
| 31 | |
| 32 | /** |
| 33 | * Constructor. |
| 34 | */ |
| 35 | private Latex2UnicodeSpecials() { |
| 36 | // never used |
| 37 | } |
| 38 | |
| 39 | /** |
| 40 | * Transform into bold characters. |
| 41 | * |
| 42 | * @param token String to transform. |
| 43 | * @return Result of transformation. |
| 44 | */ |
| 45 | public static String transform2Bold(final String token) { |
| 46 | final StringBuffer buffer = new StringBuffer(); |
| 47 | for (int i = 0; i < token.length(); i++) { |
| 48 | final char c = token.charAt(i); |
| 49 | switch (c) { |
| 50 | case 'A': |
| 51 | case 'B': |
| 52 | case 'C': |
| 53 | case 'D': |
| 54 | case 'E': |
| 55 | case 'F': |
| 56 | case 'G': |
| 57 | case 'H': |
| 58 | case 'I': |
| 59 | case 'J': |
| 60 | case 'K': |
| 61 | case 'L': |
| 62 | case 'M': |
| 63 | case 'N': |
| 64 | case 'O': |
| 65 | case 'P': |
| 66 | case 'Q': |
| 67 | case 'R': |
| 68 | case 'S': |
| 69 | case 'T': |
| 70 | case 'U': |
| 71 | case 'V': |
| 72 | case 'W': |
| 73 | case 'X': |
| 74 | case 'Y': |
| 75 | case 'Z': |
| 76 | buffer.append((char) ('\uFF21' - 'A' + c)); |
| 77 | break; |
| 78 | case 'a': |
| 79 | case 'b': |
| 80 | case 'c': |
| 81 | case 'd': |
| 82 | case 'e': |
| 83 | case 'f': |
| 84 | case 'g': |
| 85 | case 'h': |
| 86 | case 'i': |
| 87 | case 'j': |
| 88 | case 'k': |
| 89 | case 'l': |
| 90 | case 'm': |
| 91 | case 'n': |
| 92 | case 'o': |
| 93 | case 'p': |
| 94 | case 'q': |
| 95 | case 'r': |
| 96 | case 's': |
| 97 | case 't': |
| 98 | case 'u': |
| 99 | case 'v': |
| 100 | case 'w': |
| 101 | case 'x': |
| 102 | case 'y': |
| 103 | case 'z': |
| 104 | buffer.append((char) ('\uFF41' - 'a' + c)); |
| 105 | break; |
| 106 | default: |
| 107 | buffer.append(c); |
| 108 | } |
| 109 | } |
| 110 | return buffer.toString(); |
| 111 | } |
| 112 | |
| 113 | /** |
| 114 | * Transform into mathfrak characters. |
| 115 | * |
| 116 | * @param token String to transform. |
| 117 | * @return Result of transformation. |
| 118 | */ |
| 119 | public static String transform2Mathfrak(final String token) { |
| 120 | final StringBuffer buffer = new StringBuffer(); |
| 121 | for (int i = 0; i < token.length(); i++) { |
| 122 | final char c = token.charAt(i); |
| 123 | switch (c) { |
| 124 | case 'A': buffer.append("\u13AF"); |
| 125 | break; |
| 126 | case 'B': buffer.append("\u212C"); |
| 127 | break; |
| 128 | case 'b': buffer.append("\u13B2"); |
| 129 | break; |
| 130 | case 'C': buffer.append("\u212D"); |
| 131 | break; |
| 132 | case 'E': buffer.append("\u2130"); |
| 133 | break; |
| 134 | case 'e': buffer.append("\u212F"); |
| 135 | break; |
| 136 | case 'F': buffer.append("\u2131"); |
| 137 | break; |
| 138 | case 'G': buffer.append("\u13B6"); |
| 139 | break; |
| 140 | case 'g': buffer.append("\u210A"); |
| 141 | break; |
| 142 | case 'L': buffer.append("\u2112"); |
| 143 | break; |
| 144 | case 'l': buffer.append("\u2113"); |
| 145 | break; |
| 146 | case 'M': buffer.append("\u2133"); |
| 147 | break; |
| 148 | case 'o': buffer.append("\u2134"); |
| 149 | break; |
| 150 | case 'P': buffer.append("\u2118"); |
| 151 | break; |
| 152 | case 'R': buffer.append("\u211B"); |
| 153 | break; |
| 154 | case 'S': buffer.append("\u093D"); |
| 155 | break; |
| 156 | case 's': buffer.append("\u0D1F"); |
| 157 | break; |
| 158 | case 'T': buffer.append("\u01AC"); |
| 159 | break; |
| 160 | case 'V': buffer.append("\u01B2"); |
| 161 | break; |
| 162 | case 'Y': buffer.append("\u01B3"); |
| 163 | break; |
| 164 | case 'Z': buffer.append("\u2128"); |
| 165 | break; |
| 166 | default: |
| 167 | buffer.append(c); |
| 168 | } |
| 169 | } |
| 170 | return buffer.toString(); |
| 171 | } |
| 172 | |
| 173 | /** |
| 174 | * Transform into subscript characters. |
| 175 | * |
| 176 | * @param content String to transform. |
| 177 | * @return Result of transformation. |
| 178 | */ |
| 179 | public static String transform2Subscript(final String content) { |
| 180 | final StringBuffer buffer = new StringBuffer(); |
| 181 | boolean supported = true; |
| 182 | for (int i = 0; i < content.length(); i++) { |
| 183 | if (SUBSCRIPT_CHARACTERS.indexOf(content.charAt(i)) < 0) { |
| 184 | supported = false; |
| 185 | break; |
| 186 | } |
| 187 | } |
| 188 | if (!supported) { |
| 189 | if (content.length() == 1) { |
| 190 | buffer.append("_" + content); |
| 191 | } else { |
| 192 | buffer.append("_(" + content + ")"); |
| 193 | } |
| 194 | } else { |
| 195 | for (int i = 0; i < content.length(); i++) { |
| 196 | final char c = content.charAt(i); |
| 197 | switch (c) { |
| 198 | case '0': |
| 199 | case '1': |
| 200 | case '2': |
| 201 | case '3': |
| 202 | case '4': |
| 203 | case '5': |
| 204 | case '6': |
| 205 | case '7': |
| 206 | case '8': |
| 207 | case '9': |
| 208 | buffer.append((char) (c - '0' + '\u2080')); |
| 209 | break; |
| 210 | case '+': |
| 211 | buffer.append('\u208A'); |
| 212 | break; |
| 213 | case '-': |
| 214 | buffer.append('\u208B'); |
| 215 | break; |
| 216 | case '=': |
| 217 | buffer.append('\u208C'); |
| 218 | break; |
| 219 | case '(': |
| 220 | buffer.append('\u208D'); |
| 221 | break; |
| 222 | case ')': |
| 223 | buffer.append('\u208E'); |
| 224 | break; |
| 225 | default: |
| 226 | buffer.append(c); |
| 227 | } |
| 228 | } |
| 229 | } |
| 230 | return buffer.toString(); |
| 231 | } |
| 232 | |
| 233 | /** |
| 234 | * Transform into superscript characters. |
| 235 | * |
| 236 | * @param content String to transform. |
| 237 | * @return Result of transformation. |
| 238 | */ |
| 239 | public static String transform2Superscript(final String content) { |
| 240 | final StringBuffer buffer = new StringBuffer(); |
| 241 | boolean supported = true; |
| 242 | for (int i = 0; i < content.length(); i++) { |
| 243 | if (SUPERSCRIPT_CHARACTERS.indexOf(content.charAt(i)) < 0) { |
| 244 | supported = false; |
| 245 | break; |
| 246 | } |
| 247 | } |
| 248 | if (!supported) { |
| 249 | if (content.length() == 1) { |
| 250 | buffer.append("^" + content); |
| 251 | } else { |
| 252 | buffer.append("^(" + content + ")"); |
| 253 | } |
| 254 | } else { |
| 255 | for (int i = 0; i < content.length(); i++) { |
| 256 | final char c = content.charAt(i); |
| 257 | switch (c) { |
| 258 | case '0': |
| 259 | buffer.append((char) (c - '0' + '\u2070')); |
| 260 | break; |
| 261 | case '1': |
| 262 | buffer.append((char) (c - '0' + '\u00B9')); |
| 263 | break; |
| 264 | case '2': |
| 265 | buffer.append((char) (c - '0' + '\u00B2')); |
| 266 | break; |
| 267 | case '3': |
| 268 | buffer.append((char) (c - '0' + '\u00B3')); |
| 269 | break; |
| 270 | case '4': |
| 271 | case '5': |
| 272 | case '6': |
| 273 | case '7': |
| 274 | case '8': |
| 275 | case '9': |
| 276 | buffer.append((char) (c - '4' + '\u2074')); |
| 277 | break; |
| 278 | case '+': |
| 279 | buffer.append('\u207A'); |
| 280 | break; |
| 281 | case '-': |
| 282 | buffer.append('\u207B'); |
| 283 | break; |
| 284 | case '=': |
| 285 | buffer.append('\u207C'); |
| 286 | break; |
| 287 | case '(': |
| 288 | buffer.append('\u207D'); |
| 289 | break; |
| 290 | case ')': |
| 291 | buffer.append('\u207E'); |
| 292 | break; |
| 293 | case 'n': |
| 294 | buffer.append('\u207F'); |
| 295 | break; |
| 296 | default: |
| 297 | buffer.append(c); |
| 298 | } |
| 299 | } |
| 300 | } |
| 301 | return buffer.toString(); |
| 302 | } |
| 303 | |
| 304 | /** |
| 305 | * Transform into emph characters. |
| 306 | * |
| 307 | * @param token String to transform. |
| 308 | * @return Result of transformation. |
| 309 | */ |
| 310 | public static String transform2Emph(final String token) { |
| 311 | final StringBuffer buffer = new StringBuffer(); |
| 312 | for (int i = 0; i < token.length(); i++) { |
| 313 | // buffer.append('\u2006'); |
| 314 | buffer.append(' '); |
| 315 | buffer.append(token.charAt(i)); |
| 316 | } |
| 317 | return buffer.toString(); |
| 318 | } |
| 319 | } |