loncom/interface/entities.pm - view

File: [LON-CAPA] / loncom / interface / entities.pm
Revision 1.1: download - view: text, annotated - select for diffs
Mon Feb 11 11:35:46 2008 UTC (16 years, 3 months ago) by foxr
Branches: MAIN
CVS tags: HEAD

Building up hash of entity -> latex translations to sanitize
lonprintout.pm's character_table sub and to
1. Make it easy to add new entities.
2. Add some entities that are not in the table.
3. I think this version will also run faster.

1: # The LearningOnline Network 2: # entity -> tex. 3: # 4: # $Id: 5: # 6: # Copyright Michigan State University Board of Trustees 7: # 8: # This file is part of the LearningOnline Network with CAPA (LON-CAPA). 9: # 10: # LON-CAPA is free software; you can redistribute it and/or modify 11: # it under the terms of the GNU General Public License as published by 12: # the Free Software Foundation; either version 2 of the License, or 13: # (at your option) any later version. 14: # 15: # LON-CAPA is distributed in the hope that it will be useful, 16: # but WITHOUT ANY WARRANTY; without even the implied warranty of 17: # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 18: # GNU General Public License for more details. 19: # 20: # You should have received a copy of the GNU General Public License 21: # along with LON-CAPA; if not, write to the Free Software 22: # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA 23: # 24: # /home/httpd/html/adm/gpl.txt 25: # http://www.lon-capa.org/ 26: # 27: # 28: package Apache::entities; 29: use strict; 30: # 31: # This file contains a table driven entity-->latex converter. 32: # 33: # Assumptions: 34: # The number of entities in a resource is small compared with the 35: # number of possible entities that might be translated. 36: # Therefore the strategy is to match a general entity pattern 37: # &.+; over and over, pull out the match look it up in an entity -> tex hash 38: # and do the replacement. 39: # 40: # In order to simplify the hash, the following reductions are done: 41: # &#d+; have the &# and ; stripped and is converted to an int. 42: # &#.+; have the &#x and ; stripped and is converted to an int as a hex 43: # value. 44: # All others have the & and ; stripped. 45: 46: 47: # The hash: Add new conversions here; leave off the leading & and the trailing ; 48: # all numeric entities need only appear as their decimal versions 49: # (e.g. no need for 1234 is sufficient, no need for 0x4d2 as well. 50: # 51: # This entity table is mercilessly cribbed from the HTML pocket reference 52: # table starting at pg 82. In most cases the LaTeX equivalent codes come from 53: # the original massive regular expression replacements originally by 54: # A. Sakharuk in lonprintout.pm 55: # 56: # Note numerical entities are essentially unicode character codes. 57: # 58: my %entities = { 59: 60: # ---- ASCII code page: ---------------- 61: 62: # Translation to empty strings: 63: 64: 7 => "", 65: 9 => "", 66: 10 => "", 67: 13 => "", 68: 69: # Translations to simple characters: 70: 71: 32 => " ", 72: 33 => "!", 73: 34 => '"', 74: 'quot' => '"', 75: 35 => '\\\#', 76: 36 => '\\\$', 77: 37 => '\\%', 78: 38 => '\\&', 79: 'amp' => '\\&', 80: 39 => '\'', # Apostrophe 81: 40 => '(', 82: 41 => ')', 83: 42 => '\*', 84: 43 => '\+', 85: 44 => ',', # comma 86: 45 => '-', 87: 46 => '\.', 88: 47 => '\/', 89: 48 => '0', 90: 49 => '1', 91: 50 => '2', 92: 51 => '3', 93: 52 => '4', 94: 53 => '5', 95: 54 => '6', 96: 55 => '7', 97: 56 => '8', 98: 57 => '9', 99: 58 => ':', 100: 59 => ';', 101: 60 => '\\ensuremath\{<\}', 102: 'lt' => '\\ensuremath\{<\}', 103: 61 => '\\ensuremath\{=\}', 104: 62 => '\\ensuremath\{>\}', 105: 'gt' => '\\ensuremath\{>\}', 106: 63 => '\?', 107: 64 => '@', 108: 65 => 'A', 109: 66 => 'B', 110: 67 => 'C', 111: 68 => 'D', 112: 69 => 'E', 113: 70 => 'F', 114: 71 => 'G', 115: 72 => 'H', 116: 73 => 'I', 117: 74 => 'J', 118: 75 => 'K', 119: 76 => 'L', 120: 77 => 'M', 121: 78 => 'N', 122: 79 => 'O', 123: 80 => 'P', 124: 81 => 'Q', 125: 82 => 'R', 126: 83 => 'S', 127: 84 => 'T', 128: 85 => 'U', 129: 86 => 'V', 130: 87 => 'W', 131: 88 => 'X', 132: 89 => 'Y', 133: 90 => 'Z', 134: 91 => '[', 135: 92 => '\\ensuremath\{\\setminus\}', # \setminus is \ with special spacing. 136: 93 => ']', 137: 94 => '\\ensuremath\{\\wedge\}', 138: 95 => '\\underline\{\\makebox[2mm]\\{\\strut\}\}', # Underline 2mm of space for _ 139: 96 => '`', 140: 97 => 'a', 141: 98 => 'b', 142: 99 => 'c', 143: 100 => 'd', 144: 101 => 'e', 145: 102 => 'f', 146: 103 => 'g', 147: 104 => 'h', 148: 105 => 'i', 149: 106 => 'j', 150: 107 => 'k', 151: 108 => 'l', 152: 109 => 'm', 153: 110 => 'n', 154: 111 => 'o', 155: 112 => 'p', 156: 113 => 'q', 157: 114 => 'r', 158: 115 => 's', 159: 116 => 't', 160: 117 => 'u', 161: 118 => 'v', 162: 119 => 'w', 163: 120 => 'x', 164: 121 => 'y', 165: 122 => 'z', 166: 123 => '\\{', 167: 124 => '\|', 168: 125 => '\\}', 169: 126 => '\~', 170: 171: # Controls and Latin-1 supplement. Note that some entities that have 172: # visible effect are not printing unicode characters. Specifically 173: # -  174: 175: 130 => ',', 176: 131 => '\\textflorin ', 177: 132 => ',,', # Low double left quotes. 178: 133 => '\\ensuremat\{\\ldots\}', 179: 134 => '\\ensuremath\{\\dagger\}', 180: 135 => '\\ensuremath\{\\ddagger\}', 181: 136 => '\\ensuremath\{\\wedge\}', 182: 137 => '\\textperthousand ', 183: 138 => '\\v\{S\}', 184: 139 => '\\ensuremath\{<\}', 185: 140 => '\{\\OE\}', 186: 187: # There's a gap here in my entity table 188: 189: 145 => '\`', 190: 146 => '\'', 191: 147 => '\`\`', 192: 148 => '\'\'', 193: 149 => '\\ensuremath\{\\bullet\}', 194: 150 => '--', 195: 151 => '---', 196: 152 => '\\ensuremath\{\\sim\}', 197: 153 => '\\texttrademark', 198: 154 => '\\v\{s\}', 199: 155 => '\\ensuremath\{>\}', 200: 156 => '\\oe ', 201: 202: # Another short gap: 203: 204: 159 => '\\"Y', 205: 160 => '~', 206: 'nbsp' => '~', 207: 161 => '\\textexclamdown ', 208: 'iexcl' => '\\textexclamdown ', 209: 162 => '\\textcent ', 210: 'cent' => '\\textcent ', 211: 163 => '\\pounds ', 212: 'pound' => '\\pounds ', 213: 164 => '\\textcurrency ', 214: 'curren' => '\\textcurrency ', 215: 165 => '\\textyen ', 216: 'yen' => '\\textyen ', 217: 166 => '\\textbrokenbar ', 218: 'brvbar' => '\\textbrokenbar ', 219: 167 => '\\textsection ', 220: 'sect' => '\\textsection ', 221: 168 => '\\texthighdieresis ', 222: 'uml' => '\\texthighdieresis ', 223: 169 => '\\copyright ', 224: 'copy' => '\\copyright ', 225: 170 => '\\textordfeminine ', 226: 'ordf' => '\\textordfeminine ', 227: 171 => '\\ensuremath\{\ll\}', # approximation of left angle quote. 228: 'laquo' => '\\ensuremath\{\ll\}', # "" 229: 172 => '\\ensuremath\{\\neg\}', 230: 'not' => '\\ensuremath\{\\neg\}', 231: 173 => ' - ', 232: 'shy' => ' - ', 233: 174 => '\\textregistered ', 234: 'reg' => '\\textregistered ', 235: 175 => '\\ensuremath\{^\{-\}\}', 236: 'macr' => '\\ensuremath\{^\{-\}\}', 237: 176 => '\\ensuremath\{^\{\\circ\}\}', 238: 'deg' => '\\ensuremath\{^\{\\circ\}\}', 239: 177 => '\\ensuremath\{\\pm\}', 240: 'plusmn' => '\\ensuremath\{\\pm\}', 241: 178 => '\\ensuremath\{^2\}', 242: 'sup2' => '\\ensuremath\{^2\}', 243: 179 => '\\ensuremath\{^3\}', 244: 'sup3' => '\\ensuremath\{^3\}', 245: 180 => '\\textacute ', 246: 'acute' => '\\textacute ', 247: 181 => '\\ensuremath\{\\mu\}', 248: 'micro' => '\\ensuremath\{\\mu\}', 249: 182 => '\\P ', 250: para => '\\P ', 251: 183 => '\\ensuremath\{\\cdot\}', 252: 'middot' => '\\ensuremath\{\\cdot\}', 253: 184 => '\\c\{\\strut\}', 254: 'cedil' => '\\c\{\\strut\}', 255: 185 => '\\ensuremath\{^1\}', 256: sup1 => '\\ensuremath\{^1\}', 257: 186 => '\\textordmasculine ', 258: 'ordm' => '\\textordmasculine ', 259: 187 => '\\ensuremath\{\\gg\}', 260: 'raquo' => '\\ensuremath\{\\gg\}', 261: 188 => '\\textonequarter ', 262: 'frac14' => '\\textonequarter ', 263: 189 => '\\textonehalf' , 264: 'frac12' => '\\textonehalf' , 265: 190 => '\\textthreequarters ', 266: 'frac34' => '\\textthreequarters ', 267: 191 => '\\textquestiondown ', 268: 'iquest' => '\\textquestiondown ', 269: 192 => '\\\`\{A\}', 270: 'Agrave' => '\\\`\{A\}', 271: 193 => '\\\'\{A\}', 272: 'Aacute' => '\\\'\{A\}', 273: 194 => '\\^\{A\}', 274: 'Acirc' => '\\^\{A\}', 275: 195 => '\\~{A}', 276: 'Atilde'=> '\\~{A}', 277: 196 => '\\\"{A}', 278: 'Auml' => '\\\"{A}', 279: 197 => '{\\AA}', 280: 'Aring' => '{\\AA}', 281: 198 => '{\\AE}', 282: 'AElig' => '{\\AE}', 283: 199 => '\\c{c}', 284: 'Ccedil'=> '\\c{c}', 285: '200' => '\\\`{E}', 286: 'Egrave'=> '\\\`{E}', 287: 201 => '\\\'{E}', 288: 'Eacute'=> '\\\'{E}', 289: 202 => '\\\^{E}', 290: 'Ecirc' => '\\\^{E}', 291: 203 => '\\\"{E}', 292: 'Euml' => '\\\"{E}', 293: 204 => '\\\`{I}', 294: 'Igrave'=> '\\\`{I}', 295: 205 => '\\\'{I}', 296: 'Iacute'=> '\\\'{I}', 297: 206 => '\\\^{I}', 298: 'Icirc' => '\\\^{I}', 299: 207 => '\\\"{I}', 300: 'Iuml' => '\\\"{I}', 301: 208 => '\\OE', 302: 'ETH' => '\\OE', 303: 209 => '\\~{N}', 304: 'Ntilde'=> '\\~{N}', 305: 210 => '\\\`{O}', 306: 'Ograve'=> '\\\`{O}', 307: 211 => '\\\'{O}', 308: 'Oacute'=> '\\\'{O}', 309: 212 => '\\\^{O}', 310: 'Ocirc' => '\\\^{O}', 311: 213 => '\\~{O}', 312: 'Otilde'=> '\\~{O}', 313: 214 => '\\\"{O}', 314: 'Ouml' => '\\\"{O}', 315: 215 => '\\ensuremath\{\\times\}', 316: 'times' => '\\ensuremath\{\\times\}', 317: 216 => '\\O', 318: 'Oslash'=> '\\O', 319: 217 => '\\\`{U}', 320: 'Ugrave'=> '\\\`{U}', 321: 218 => '\\\'{U}', 322: 'Uacute'=> '\\\'{U}', 323: 219 => '\\\^{U}', 324: 'Ucirc' => '\\\^{U}', 325: 220 => '\\\"{U}', 326: 'Uuml' => '\\\"{U}', 327: 221 => '\\\'{Y}', 328: 'Yacute'=> '\\\'{Y}', 329: 222 => '\\TH', 330: 'THORN' => '\\TH', 331: 223 => '{\\sz}', 332: 'szlig' => '{\\sz}', 333: 224 => '\\\`{a}', 334: 'agrave'=> '\\\`{a}', 335: 225 => '\\\'{a}', 336: 'aacute'=> '\\\'{a}', 337: 226 => '\\\^{a}', 338: 'acirc' => '\\\^{a}', 339: 227 => '\\\~{a}', 340: 'atilde'=> '\\\~{a}', 341: 228 => '\\\"{a}', 342: 'auml' => '\\\"{a}', 343: 229 => '\\aa', 344: 'aring' => '\\aa', 345: 230 => '\\ae', 346: 'aelig' => '\\ae', 347: 231 => '\\c{c}', 348: 'ccedil'=> '\\c{c}', 349: 232 => '\\\`{e}', 350: 'egrave'=> '\\\`{e}', 351: 233 => '\\\'{e}', 352: 'eacute'=> '\\\'{e}', 353: 234 => '\\\^{e}', 354: 'ecirc' => '\\\^{e}', 355: 235 => '\\\"{e}', 356: 'euml' => '\\\"{e}', 357: 236 => '\\\`{i}', 358: 'igrave'=> '\\\`{i}', 359: 237 => '\\\'{i}', 360: 'iacute'=> '\\\'{i}', 361: 238 => '\\\^{i}', 362: 'icirc' => '\\\^{i}', 363: 239 => '\\\"{i}', 364: 'iuml' => '\\\"{i}', 365: 240 => '\\dh', 366: 'eth' => '\\dh', 367: 241 => '\\\~{n}', 368: 'ntilde'=> '\\\~{n}', 369: 242 => '\\\`{o}', 370: 'ograve'=> '\\\`{o}', 371: 243 => '\\\'{o}', 372: 'oacute'=> '\\\'{o}', 373: 244 => '\\\^{o}', 374: 'ocirc' => '\\\^{o}', 375: 245 => '\\\~{o}', 376: 'otilde'=> '\\\~{o}', 377: 246 => '\\\"{o}', 378: 'ouml' => '\\\"{o}', 379: 247 => '\\ensuremath\{\\div\}', 380: 'divide'=> '\\ensuremath\{\\div\}', 381: 248 => '{\\o}', 382: 'oslash'=> '{\\o}', 383: 249 => '\\\`{u}', 384: 'ugrave'=> '\\\`{u}', 385: 250 => '\\\'{u}', 386: 'uacute'=> '\\\'{u}', 387: 251 => '\\\^{u}', 388: 'ucirc' => '\\\^{u}', 389: 252 => '\\\"{u}', 390: 'uuml' => '\\\"{u}', 391: 253 => '\\\'{y}', 392: 'yacute'=> '\\\'{y}', 393: 254 => '\\th', 394: 'thorn' => '\\th', 395: 255 => '\\\"{y}', 396: 'yuml' => '\\\"{y}', 397: 398: # hbar entity number comes from the unicode charater: 399: # see e.g. http://www.unicode.org/charts/PDF/U0100.pdf 400: # ISO also documents a 'planck' entity. 401: 402: 295 => '\\ensuremath\{\hbar\}', 403: 'plank' => '\\ensuremath\{\hbar\}', 404: 405: # Latin extended-A HTML 4.01 entities: 406: 407: 338 => '\\OE', 408: 'OElig' => '\\OE', 409: 339 => '\\oe', 410: 'oelig' => '\\oe', 411: 352 => '\\v{S}', 412: 'Scaron' => '\\v{S}', 413: 353 => '\\v{s}', 414: 'scaron' => '\\v{s}', 415: 376 => '\\\"{Y}', 416: 'Yuml' => '\\\"{Y}', 417: 418: 419: # Latin extended B HTML 4.01 entities 420: 421: 402 => '\\ensuremath{f}', 422: 'fnof' => '\\ensuremath{f}', 423: 424: # Spacing modifier letters: 425: 426: 710 => '\^{}', 427: 'circ' => '\^{}', 428: 732 => '\~{}', 429: 'tilde' => '\~{}', 430: 431: # Greek uppercase: 432: 433: 913 => '\\ensuremath\{\\mathrm\{A\}\}', 434: 'Alpha' => '\\ensuremath\{\\mathrm\{A\}\}', 435: 914 => '\\ensuremath\{\\mathrm\{B\}\}', 436: 'Beta' => '\\ensuremath\{\\mathrm\{B\}\}', 437: 915 => '\\ensuremath\{\\Gamma\}', 438: 'Gamma' => '\\ensuremath\{\\Gamma\}', 439: 916 => '\\ensuremath\{\\Delta\}', 440: 'Delta' => '\\ensuremath\{\\Delta\}', 441: 917 => '\\ensuremath\{\\mathrm\{E\}\}', 442: 'Epsilon'=> '\\ensuremath\{\\mathrm\{E\}\}', 443: 918 => '\\ensuremath\{\\mathrm\{Z\}\}', 444: 'Zeta' => '\\ensuremath\{\\mathrm\{Z\}\}', 445: 919 => '\\ensuremath\{\\mathrm\{H\}\}', 446: 'Eta' => '\\ensuremath\{\\mathrm\{H\}\}', 447: 920 => '\\ensuremath\{\\Theta\}', 448: 'Theta' => '\\ensuremath\{\\Theta\}', 449: 921 => '\\ensuremath\{\\mathrm\{I\}\}', 450: 'Iota' => '\\ensuremath\{\\mathrm\{I\}\}', 451: 922 => '\\ensuremath\{\\mathrm\{K\}\}', 452: 'Kappa' => '\\ensuremath\{\\mathrm\{K\}\}', 453: 923 => '\\ensuremath\{\\Lambda\}', 454: 'Lambda' => '\\ensuremath\{\\Lambda\}', 455: 924 => '\\ensuremath\{\\mathrm\{M\}\}', 456: 'Mu' => '\\ensuremath\{\\mathrm\{M\}\}', 457: 925 => '\\ensuremath\{\\mathrm\{N\}\}', 458: 'Nu' => '\\ensuremath\{\\mathrm\{N\}\}', 459: 926 => '\\ensuremath\{\\mathrm\{\\Xi\}', 460: 'Xi' => '\\ensuremath\{\\mathrm\{\\Xi\}', 461: 927 => '\\ensuremath\{\\mathrm\{O\}\}', 462: 'Omicron'=> '\\ensuremath\{\\mathrm\{O\}\}', 463: 928 => '\\ensuremath\{\\Pi\}', 464: 'Pi' => '\\ensuremath\{\\Pi\}', 465: 929 => '\\ensuremath\{\\mathrm\{P\}\}', 466: 'Rho' => '\\ensuremath\{\\mathrm\{P\}\}', 467: 468: # Skips 930 469: 470: 931 => '\\ensuremath\{\Sigma\}', 471: 'Sigma' => '\\ensuremath\{\Sigma\}', 472: 932 => '\\ensuremath\{\\mathrm\{T\}\}', 473: 'Tau' => '\\ensuremath\{\\mathrm\{T\}\}', 474: 933 => '\\ensuremath\{\\Upsilon\}', 475: 'Upsilon'=> '\\ensuremath\{\\Upsilon\}', 476: 934 => '\\ensuremath\{\\Phi\}', 477: 'Phi' => '\\ensuremath\{\\Phi\}', 478: 935 => '\\ensuremath\{\\mathrm\{X\}\}', 479: 'Chi' => '\\ensuremath\{\\mathrm\{X\}\}', 480: 936 => '\\ensuremath\{\\Psi\}', 481: 'Psi' => '\\ensuermath\{\\Psi\}', 482: 937 => '\\ensuremath\{\\Omega\}', 483: 'Omega' => '\\ensuremath\{\\Omega\}', 484: 485: 486: # Greek lowercase: 487: 488: 945 => '\\ensuremath\{\\alpha\}', 489: 'alpha' => '\\ensuremath\{\\alpha\}', 490: 946 => '\\ensuremath\{\\beta\}', 491: 'beta' => '\\ensuremath\{\\beta\}', 492: 947 => '\\ensuremath\{\\gamma\}', 493: 'gamma' => '\\ensuremath\{\\gamma\}', 494: 948 => '\\ensuremath\{\\delta\}', 495: 'delta' => '\\ensuremath\{\\delta\}', 496: 949 => '\\ensuremath\{\\epsilon\}', 497: 'epsilon'=> '\\ensuremath\{\\epsilon\}', 498: 950 => '\\ensuremath\{\\zeta\}', 499: 'zeta' => '\\ensuremath\{\\zeta\}', 500: 951 => '\\ensuremath\{\\eta\}', 501: 'eta' => '\\ensuremath\{\\eta\}', 502: 503: 504: };