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: # I also want to acknowledge
57: # ISO Character entities and their LaTeX equivalents by
58: # Vidar Bronken Gundersen, and Rune Mathisen
59: # http://www.bitjungle.com/isoent-ref.pdf
60: #
61:
62: # Note numerical entities are essentially unicode character codes.
63: #
64: package Apache::entities;
65:
66: my %entities = (
67:
68: # ---- ASCII code page: ----------------
69:
70: # Translation to empty strings:
71:
72: 7 => "",
73: 9 => "",
74: 10 => "",
75: 13 => "",
76:
77: # Translations to simple characters:
78:
79: 32 => " ",
80: 33 => "!",
81: 34 => '"',
82: 'quot' => '"',
83: 35 => '\\#',
84: 36 => '\\$',
85: 37 => '\%',
86: 38 => '\&',
87: 'amp' => '\&',
88: 39 => '\'', # Apostrophe
89: 40 => '(',
90: 41 => ')',
91: 42 => '*',
92: 43 => '+',
93: 44 => ',', # comma
94: 45 => '-',
95: 46 => '.',
96: 47 => '/',
97: 48 => '0',
98: 49 => '1',
99: 50 => '2',
100: 51 => '3',
101: 52 => '4',
102: 53 => '5',
103: 54 => '6',
104: 55 => '7',
105: 56 => '8',
106: 57 => '9',
107: 58 => ':',
108: 59 => ';',
109: 60 => '\ensuremath{<}',
110: 'lt' => '\ensuremath{<}',
111: 61 => '\ensuremath{=}',
112: 62 => '\ensuremath{>}',
113: 'gt' => '\ensuremath{>}',
114: 63 => '?',
115: 64 => '@',
116: 65 => 'A',
117: 66 => 'B',
118: 67 => 'C',
119: 68 => 'D',
120: 69 => 'E',
121: 70 => 'F',
122: 71 => 'G',
123: 72 => 'H',
124: 73 => 'I',
125: 74 => 'J',
126: 75 => 'K',
127: 76 => 'L',
128: 77 => 'M',
129: 78 => 'N',
130: 79 => 'O',
131: 80 => 'P',
132: 81 => 'Q',
133: 82 => 'R',
134: 83 => 'S',
135: 84 => 'T',
136: 85 => 'U',
137: 86 => 'V',
138: 87 => 'W',
139: 88 => 'X',
140: 89 => 'Y',
141: 90 => 'Z',
142: 91 => '[',
143: 92 => '\ensuremath{\setminus}', # \setminus is \ with special spacing.
144: 93 => ']',
145: 94 => '\ensuremath{\wedge}',
146: 95 => '\underline{\makebox[2mm]{\strut}}', # Underline 2mm of space for _
147: 96 => '`',
148: 97 => 'a',
149: 98 => 'b',
150: 99 => 'c',
151: 100 => 'd',
152: 101 => 'e',
153: 102 => 'f',
154: 103 => 'g',
155: 104 => 'h',
156: 105 => 'i',
157: 106 => 'j',
158: 107 => 'k',
159: 108 => 'l',
160: 109 => 'm',
161: 110 => 'n',
162: 111 => 'o',
163: 112 => 'p',
164: 113 => 'q',
165: 114 => 'r',
166: 115 => 's',
167: 116 => 't',
168: 117 => 'u',
169: 118 => 'v',
170: 119 => 'w',
171: 120 => 'x',
172: 121 => 'y',
173: 122 => 'z',
174: 123 => '\{',
175: 124 => '|',
176: 125 => '\}',
177: 126 => '\~',
178:
179: # Controls and Latin-1 supplement. Note that some entities that have
180: # visible effect are not printing unicode characters. Specifically
181: # ‚- 
182:
183: 130 => ',',
184: 131 => '\ensuremath{f}',
185: 132 => ',,', # Low double left quotes.
186: 133 => '\ensuremath{\ldots}',
187: 134 => '\ensuremath{\dagger}',
188: 135 => '\ensuremath{\ddagger}',
189: 136 => '\ensuremath{\wedge}',
190: 137 => '\textperthousand ',
191: 138 => '\v{S}',
192: 139 => '\ensuremath{<}',
193: 140 => '{\OE}',
194:
195: # There's a gap here in my entity table
196:
197: 145 => '`',
198: 146 => '\'',
199: 147 => '``',
200: 148 => '\'\'',
201: 149 => '\ensuremath{\bullet}',
202: 150 => '--',
203: 151 => '---',
204: 152 => '\ensuremath{\sim}',
205: 153 => '\texttrademark',
206: 154 => '\v{s}',
207: 155 => '\ensuremath{>}',
208: 156 => '\oe ',
209:
210: # Another short gap:
211:
212: 159 => '\"Y',
213: 160 => '~',
214: 'nbsp' => '~',
215: 161 => '\textexclamdown ',
216: 'iexcl' => '\textexclamdown ',
217: 162 => '\textcent ',
218: 'cent' => '\textcent ',
219: 163 => '\pounds ',
220: 'pound' => '\pounds ',
221: 164 => '\textcurrency ',
222: 'curren' => '\textcurrency ',
223: 165 => '\textyen ',
224: 'yen' => '\textyen ',
225: 166 => '\textbrokenbar ',
226: 'brvbar' => '\textbrokenbar ',
227: 167 => '\textsection ',
228: 'sect' => '\textsection ',
229: 168 => '\"{}',
230: 'uml' => '\"{}',
231: 169 => '\copyright ',
232: 'copy' => '\copyright ',
233: 170 => '\textordfeminine ',
234: 'ordf' => '\textordfeminine ',
235: 171 => '\ensuremath{\ll}', # approximation of left angle quote.
236: 'laquo' => '\ensuremath{\ll}', # ""
237: 172 => '\ensuremath{\neg}',
238: 'not' => '\ensuremath{\neg}',
239: 173 => ' - ',
240: 'shy' => ' - ',
241: 174 => '\textregistered ',
242: 'reg' => '\textregistered ',
243: 175 => '\ensuremath{^{-}}',
244: 'macr' => '\ensuremath{^{-}}',
245: 176 => '\ensuremath{^{\circ}}',
246: 'deg' => '\ensuremath{^{\circ}}',
247: 177 => '\ensuremath{\pm}',
248: 'plusmn' => '\ensuremath{\pm}',
249: 178 => '\ensuremath{^2}',
250: 'sup2' => '\ensuremath{^2}',
251: 179 => '\ensuremath{^3}',
252: 'sup3' => '\ensuremath{^3}',
253: 180 => "\\'{}",
254: 'acute' => "\\'{}",
255: 181 => '\ensuremath{\mu}',
256: 'micro' => '\ensuremath{\mu}',
257: 182 => '\P ',
258: para => '\P ',
259: 183 => '\ensuremath{\cdot}',
260: 'middot' => '\ensuremath{\cdot}',
261: 184 => '\c{\strut}',
262: 'cedil' => '\c{\strut}',
263: 185 => '\ensuremath{^1}',
264: sup1 => '\ensuremath{^1}',
265: 186 => '\textordmasculine ',
266: 'ordm' => '\textordmasculine ',
267: 187 => '\ensuremath{\gg}',
268: 'raquo' => '\ensuremath{\gg}',
269: 188 => '\textonequarter ',
270: 'frac14' => '\textonequarter ',
271: 189 => '\textonehalf' ,
272: 'frac12' => '\textonehalf' ,
273: 190 => '\textthreequarters ',
274: 'frac34' => '\textthreequarters ',
275: 191 => '\textquestiondown ',
276: 'iquest' => '\textquestiondown ',
277: 192 => '\\`{A}',
278: 'Agrave' => '\\`{A}',
279: 193 => "\\'{A}",
280: 'Aacute' => "\\'{A}",
281: 194 => '\^{A}',
282: 'Acirc' => '\^{A}',
283: 195 => '\~{A}',
284: 'Atilde'=> '\~{A}',
285: 196 => '\\"{A}',
286: 'Auml' => '\\"{A}',
287: 197 => '{\AA}',
288: 'Aring' => '{\AA}',
289: 198 => '{\AE}',
290: 'AElig' => '{\AE}',
291: 199 => '\c{c}',
292: 'Ccedil'=> '\c{c}',
293: 200 => '\\`{E}',
294: 'Egrave'=> '\\`{E}',
295: 201 => "\\'{E}",
296: 'Eacute'=> "\\'{E}",
297: 202 => '\\^{E}',
298: 'Ecirc' => '\\^{E}',
299: 203 => '\\"{E}',
300: 'Euml' => '\\"{E}',
301: 204 => '\\`{I}',
302: 'Igrave'=> '\\`{I}',
303: 205 => "\\'{I}",
304: 'Iacute'=> "\\'{I}",
305: 206 => '\\^{I}',
306: 'Icirc' => '\\^{I}',
307: 207 => '\\"{I}',
308: 'Iuml' => '\\"{I}',
309: 208 => '\DH',
310: 'ETH' => '\DH',
311: 209 => '\~{N}',
312: 'Ntilde'=> '\~{N}',
313: 210 => '\\`{O}',
314: 'Ograve'=> '\\`{O}',
315: 211 => "\\'{O}",
316: 'Oacute'=> "\\'{O}",
317: 212 => '\\^{O}',
318: 'Ocirc' => '\\^{O}',
319: 213 => '\~{O}',
320: 'Otilde'=> '\~{O}',
321: 214 => '\\"{O}',
322: 'Ouml' => '\\"{O}',
323: 215 => '\ensuremath{\times}',
324: 'times' => '\ensuremath{\times}',
325: 216 => '\O',
326: 'Oslash'=> '\O',
327: 217 => '\\`{U}',
328: 'Ugrave'=> '\\`{U}',
329: 218 => "\\'{U}",
330: 'Uacute'=> "\\'{U}",
331: 219 => '\\^{U}',
332: 'Ucirc' => '\\^{U}',
333: 220 => '\\"{U}',
334: 'Uuml' => '\\"{U}',
335: 221 => "\\'{Y}",
336: 'Yacute'=> "\\'{Y}",
337: 223 => '{\ss}',
338: 'szlig' => '{\ss}',
339: 224 => '\\`{a}',
340: 'agrave'=> '\\`{a}',
341: 225 => "\\'{a}",
342: 'aacute'=> "\\'{a}",
343: 226 => '\\^{a}',
344: 'acirc' => '\\^{a}',
345: 227 => '\\~{a}',
346: 'atilde'=> '\\~{a}',
347: 228 => '\\"{a}',
348: 'auml' => '\\"{a}',
349: 229 => '\aa',
350: 'aring' => '\aa',
351: 230 => '\ae',
352: 'aelig' => '\ae',
353: 231 => '\c{c}',
354: 'ccedil'=> '\c{c}',
355: 232 => '\\`{e}',
356: 'egrave'=> '\\`{e}',
357: 233 => "\\'{e}",
358: 'eacute'=> "\\'{e}",
359: 234 => '\\^{e}',
360: 'ecirc' => '\\^{e}',
361: 235 => '\\"{e}',
362: 'euml' => '\\"{e}',
363: 236 => '\\`{i}',
364: 'igrave'=> '\\`{i}',
365: 237 => "\\'{i}",
366: 'iacute'=> "\\'{i}",
367: 238 => '\\^{i}',
368: 'icirc' => '\\^{i}',
369: 239 => '\\"{i}',
370: 'iuml' => '\\"{i}',
371: 241 => '\\~{n}',
372: 'ntilde'=> '\\~{n}',
373: 242 => '\\`{o}',
374: 'ograve'=> '\\`{o}',
375: 243 => "\\'{o}",
376: 'oacute'=> "\\'{o}",
377: 244 => '\\^{o}',
378: 'ocirc' => '\\^{o}',
379: 245 => '\\~{o}',
380: 'otilde'=> '\\~{o}',
381: 246 => '\\"{o}',
382: 'ouml' => '\\"{o}',
383: 247 => '\ensuremath{\div}',
384: 'divide'=> '\ensuremath{\div}',
385: 248 => '{\o}',
386: 'oslash'=> '{\o}',
387: 249 => '\\`{u}',
388: 'ugrave'=> '\\`{u}',
389: 250 => "\\'{u}",
390: 'uacute'=> "\\'{u}",
391: 251 => '\\^{u}',
392: 'ucirc' => '\\^{u}',
393: 252 => '\\"{u}',
394: 'uuml' => '\\"{u}',
395: 253 => "\\'{y}",
396: 'yacute'=> "\\'{y}",
397: 255 => '\\"{y}',
398: 'yuml' => '\\"{y}',
399:
400: # hbar entity number comes from the unicode charater:
401: # see e.g. http://www.unicode.org/charts/PDF/U0100.pdf
402: # ISO also documents a 'planck' entity.
403:
404: 295 => '\ensuremath{\hbar}',
405: 'planck' => '\ensuremath{\hbar}',
406:
407: # Latin extended-A HTML 4.01 entities:
408:
409: 338 => '\OE',
410: 'OElig' => '\OE',
411: 339 => '\oe',
412: 'oelig' => '\oe',
413: 352 => '\v{S}',
414: 'Scaron' => '\v{S}',
415: 353 => '\v{s}',
416: 'scaron' => '\v{s}',
417: 376 => '\\"{Y}',
418: 'Yuml' => '\\"{Y}',
419:
420:
421: # Latin extended B HTML 4.01 entities
422:
423: 402 => '\ensuremath{f}',
424: 'fnof' => '\ensuremath{f}',
425:
426: # Spacing modifier letters:
427:
428: 710 => '\^{}',
429: 'circ' => '\^{}',
430: 732 => '\~{}',
431: 'tilde' => '\~{}',
432:
433: # Greek uppercase:
434:
435: 913 => '\ensuremath{\mathrm{A}}',
436: 'Alpha' => '\ensuremath{\mathrm{A}}',
437: 914 => '\ensuremath{\mathrm{B}}',
438: 'Beta' => '\ensuremath{\mathrm{B}}',
439: 915 => '\ensuremath{\Gamma}',
440: 'Gamma' => '\ensuremath{\Gamma}',
441: 916 => '\ensuremath{\Delta}',
442: 'Delta' => '\ensuremath{\Delta}',
443: 917 => '\ensuremath{\mathrm{E}}',
444: 'Epsilon'=> '\ensuremath{\mathrm{E}}',
445: 918 => '\ensuremath{\mathrm{Z}}',
446: 'Zeta' => '\ensuremath{\mathrm{Z}}',
447: 919 => '\ensuremath{\mathrm{H}}',
448: 'Eta' => '\ensuremath{\mathrm{H}}',
449: 920 => '\ensuremath{\Theta}',
450: 'Theta' => '\ensuremath{\Theta}',
451: 921 => '\ensuremath{\mathrm{I}}',
452: 'Iota' => '\ensuremath{\mathrm{I}}',
453: 922 => '\ensuremath{\mathrm{K}}',
454: 'Kappa' => '\ensuremath{\mathrm{K}}',
455: 923 => '\ensuremath{\Lambda}',
456: 'Lambda' => '\ensuremath{\Lambda}',
457: 924 => '\ensuremath{\mathrm{M}}',
458: 'Mu' => '\ensuremath{\mathrm{M}}',
459: 925 => '\ensuremath{\mathrm{N}}',
460: 'Nu' => '\ensuremath{\mathrm{N}}',
461: 926 => '\ensuremath{\mathrm{\Xi}}',
462: 'Xi' => '\ensuremath{\mathrm{\Xi}}',
463: 927 => '\ensuremath{\mathrm{O}}',
464: 'Omicron'=> '\ensuremath{\mathrm{O}}',
465: 928 => '\ensuremath{\Pi}',
466: 'Pi' => '\ensuremath{\Pi}',
467: 929 => '\ensuremath{\mathrm{P}}',
468: 'Rho' => '\ensuremath{\mathrm{P}}',
469:
470: # Skips 930
471:
472: 931 => '\ensuremath{\Sigma}',
473: 'Sigma' => '\ensuremath{\Sigma}',
474: 932 => '\ensuremath{\mathrm{T}}',
475: 'Tau' => '\ensuremath{\mathrm{T}}',
476: 933 => '\ensuremath{\Upsilon}',
477: 'Upsilon'=> '\ensuremath{\Upsilon}',
478: 934 => '\ensuremath{\Phi}',
479: 'Phi' => '\ensuremath{\Phi}',
480: 935 => '\ensuremath{\mathrm{X}}',
481: 'Chi' => '\ensuremath{\mathrm{X}}',
482: 936 => '\ensuremath{\Psi}',
483: 'Psi' => '\ensuremath{\Psi}',
484: 937 => '\ensuremath{\Omega}',
485: 'Omega' => '\ensuremath{\Omega}',
486:
487:
488: # Greek lowercase:
489:
490: 945 => '\ensuremath{\alpha}',
491: 'alpha' => '\ensuremath{\alpha}',
492: 946 => '\ensuremath{\beta}',
493: 'beta' => '\ensuremath{\beta}',
494: 947 => '\ensuremath{\gamma}',
495: 'gamma' => '\ensuremath{\gamma}',
496: 948 => '\ensuremath{\delta}',
497: 'delta' => '\ensuremath{\delta}',
498: 949 => '\ensuremath{\epsilon}',
499: 'epsilon'=> '\ensuremath{\epsilon}',
500: 950 => '\ensuremath{\zeta}',
501: 'zeta' => '\ensuremath{\zeta}',
502: 951 => '\ensuremath{\eta}',
503: 'eta' => '\ensuremath{\eta}',
504: 952 => '\ensuremath{\theta}',
505: 'theta' => '\ensuremath{\theta}',
506: 953 => '\ensuremath{\iota}',
507: 'iota' => '\ensuremath{\iota}',
508: 954 => '\ensuremath{\kappa}',
509: 'kappa' => '\ensuremath{\kappa}',
510: 955 => '\ensuremath{\lambda}',
511: 'lambda' => '\ensuremath{\lambda}',
512: 956 => '\ensuremath{\mu}',
513: 'mu' => '\ensuremath{\mu}',
514: 957 => '\ensuremath{\nu}',
515: 'nu' => '\ensuremath{\nu}',
516: 958 => '\ensuremath{\xi}',
517: 'xi' => '\ensuremath{\xi}',
518: 959 => '\ensuremath{o}',
519: 'omicron'=> '\ensuremath{o}',
520: 960 => '\ensuremath{\pi}',
521: 'pi' => '\ensuremath{\pi}',
522: 961 => '\ensuremath{\rho}',
523: 'rho' => '\ensuremath{\rho}',
524: 962 => '\ensuremath{\varsigma}',
525: 'sigmaf' => '\ensuremath{\varsigma}',
526: 963 => '\ensuremath{\sigma}',
527: 'sigma' => '\ensuremath{\sigma}',
528: 964 => '\ensuremath{\tau}',
529: 'tau' => '\ensuremath{\tau}',
530: 965 => '\ensuremath{\upsilon}',
531: 'upsilon'=> '\ensuremath{\upsilon}',
532: 966 => '\ensuremath{\phi}',
533: 'phi' => '\ensuremath{\phi}',
534: 967 => '\ensuremath{\chi}',
535: 'chi' => '\ensuremath{\chi}',
536: 968 => '\ensuremath{\psi}',
537: 'psi' => '\ensuremath{\psi}',
538: 969 => '\ensuremath{\omega}',
539: 'omega' => '\ensuremath{\omega}',
540: 977 => '\ensuremath{\vartheta}',
541: 'thetasym'=>'\ensuremath{\vartheta}',
542: 978 => '\ensuremath{\mathit{\Upsilon}}',
543: 'upsih' => '\ensuremath{\mathit{\Upsilon}}',
544: 982 => '\ensuremath{\varpi}',
545: 'piv' => '\ensuremath{\varpi}',
546:
547:
548: # The general punctuation set:
549:
550: 8194, => '\hspace{.5em}',
551: 'enspc' => '\hspace{.5em}',
552: 8195 => '\hspace{1.0em}',
553: 'emspc' => '\hspace{1.0em}',
554: 8201 => '\hspace{0.167em}',
555: 'thinsp' => '\hspace{0.167em}',
556: 8204 => '{}',
557: 'zwnj' => '{}',
558: 8205 => '',
559: 'zwj' => '',
560: 8206 => '',
561: 'lrm' => '',
562: 8207 => '',
563: 'rlm' => '',
564: 8211 => '--',
565: 'ndash' => '--',
566: 8212 => '---',
567: 'mdash' => '---',
568: 8216 => '`',
569: 'lsquo' => '`',
570: 8217 => "'",
571: 'rsquo' => "'",
572: 8218 => '\quotesinglbase',
573: 'sbquo' => '\quotesinglbase',
574: 8220 => '``',
575: 'ldquo' => '``',
576: 8221 => "''",
577: 'rdquo' => "''",
578: 8222 => '\quotedblbase',
579: 'bdquo' => '\quotedblbase',
580: 8224 => '\ensuremath{\dagger}',
581: 'dagger' => '\ensuremath{\dagger}',
582: '8225' => '\ensuremath{\ddag}',
583: 'Dagger' => '\ensuremath{\ddag}',
584: 8226 => '\textbullet',
585: 'bull' => '\textbullet',
586: 8230 => '\textellipsis',
587: 'hellep' => '\textellipsis',
588: 8240 => '\textperthousand',
589: permil => '\textperthousand',
590: 8242 => '\textquotesingle',
591: 'prime' => '\textquotesingle',
592: 8243 => '\textquotedbl',
593: 'Prime' => '\textquotedbl',
594: 8249 => '\guilsinglleft',
595: 'lsaquo' => '\guilsinglleft',
596: 8250 => '\guilsinglright',
597: 'rsaquo' => '\guilsinglright',
598: 8254 => '\textasciimacron',
599: oline => '\textasciimacron',
600: 8260 => '\textfractionsolidus',
601: 'frasl' => '\textfractionsolidus',
602: 8364 => '\texteuro',
603: 'euro' => '\texteuro',
604:
605: # Letter like symbols
606:
607:
608: 8472 => '\ensuremath{\wp}',
609: 'weierp' => '\ensuremath{\wp}',
610: 8465 => '\ensuremath{\Im}',
611: 'image' => '\ensuremath{\Im}',
612: 8476 => '\ensuremath{\Re}',
613: 'real' => '\ensuremath{\Re}',
614: 8482 => '\texttrademark',
615: 'trade' => '\texttrademark',
616: 8501 => '\ensuremath{\aleph}',
617: 'alefsym'=> '\ensuremath{\aleph}',
618:
619: # Arrows and then some (harpoons from Hon Kie).
620:
621: 8592 => '\textleftarrow',
622: 'larr' => '\textleftarrow',
623: 8593 => '\textuparrow',
624: 'uarr' => '\textuparrow',
625: 8594 => '\textrightarrow',
626: 'rarr' => '\textrightarrow',
627: 8595 => '\textdownarrow',
628: 'darr' => '\textdownarrow',
629: 8596 => '\ensuremath{\leftrightarrow}',
630: 'harr' => '\ensuremath{\leftrightarrow}',
631: 8598 => '\ensuremath{\nwarrow}',
632: 8599 => '\ensuremath{\nearrow}',
633: 8600 => '\ensuremath{\searrow}',
634: 8601 => '\ensuremath{\swarrow}',
635: 8605 => '\ensuremath{\leadsto}',
636: 8614 => '\ensuremath{\mapsto}',
637: 8617 => '\ensuremath{\hookleftarrow}',
638: 8618 => '\ensuremath{\hookrightarrow}',
639: 8629 => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
640: 'crarr' => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
641: 8636 => '\ensuremath{\leftharpoonup}',
642: 8637 => '\ensuremath{\leftharpoondown}',
643: 8640 => '\ensuremath{\rightharpoonup}',
644: 8641 => '\ensuremath{\rightharpoondown}',
645: 8652 => '\ensuremath{\rightleftharpoons}',
646: 8656 => '\ensuremath{\Leftarrow}',
647: 'lArr' => '\ensuremath{\Leftarrow}',
648: 8657 => '\ensuremath{\Uparrow}',
649: 'uArr' => '\ensuremath{\Uparrow}',
650: 8658 => '\ensuremath{\Rightarrow}',
651: 'rArr' => '\ensuremath{\Rightarrow}',
652: 8659 => '\ensuremath{\Downarrow}',
653: 'dArr' => '\ensuremath{\Downarrow}',
654: 8660 => '\ensuremath{\Leftrightarrow}',
655: 'hArr' => '\ensuremath{\Leftrightarrow}',
656: 8661 => '\ensuremath{\Updownarrow}',
657: 'vArr' => '\ensuremath{\Updownarrow}',
658: 8666 => '\ensuremath{\Lleftarrow}',
659: 'lAarr' => '\ensuremath{\Lleftarrow}',
660: 8667 => '\ensuremath{\Rrightarrow}',
661: 'rAarr' => '\ensuremath{\Rrightarrow}',
662: 8669 => '\ensuremath{\rightsquigarrow}',
663: 'rarrw' => '\ensuremath{\rightsquigarrow}',
664:
665:
666: # Mathematical operators.
667:
668:
669: 'forall' => '\ensuremath{\forall}',
670: 8704 => '\ensuremath{\forall}',
671: 'comp' => '\ensuremath{\complement}',
672: 8705 => '\ensuremath{\complement}',
673: 'part' => '\ensuremath{\partial}',
674: 8706 => '\ensuremath{\partial}',
675: 'exist' => '\ensuremath{\exists}',
676: 8707 => '\ensuremath{\exists}',
677: 'nexist' => '\ensuremath{\nexists}',
678: 8708 => '\ensuremath{\nexists}',
679: 'empty' => '\ensuremath{\emptyset}',
680: 8709 => '\ensuremath{\emptyset}',
681: 8710 => '\ensuremath{\Delta}',
682: 'nabla' => '\ensuremath{\nabla}',
683: 8711 => '\ensuremath{\nabla}',
684: 'isin' => '\ensuremath{\in}',
685: 8712 => '\ensuremath{\in}',
686: 'notin' => '\ensuremath{\notin}',
687: 8713 => '\ensuremath{\notin}',
688: ni => '\ensuremath{\ni}',
689: 8715 => '\ensuremath{\ni}',
690: 8716 => '\ensuremath{\not\ni}',
691: 'prod' => '\ensuremath{\prod}',
692: 8719 => '\ensuremath{\prod}',
693: 8720 => '\ensuremath{\coprod}',
694: 'sum' => '\ensuremath{\sum}',
695: 8721 => '\ensuremath{\sum}',
696: 'minus' => '\ensuremath{-}',
697: 8722 => '\ensuremath{-}',
698: 8723 => '\ensuremath{\mp}',
699: 8724 => '\ensuremath{\dotplus}',
700: 8725 => '\ensuremath{\diagup}',
701: 8726 => '\ensuremath{\smallsetminus}',
702: 'lowast' => '\ensuremath{*}',
703: 8727 => '\ensuremath{*}',
704: 8728 => '\ensuremath{\circ}',
705: 8729 => '\ensuremath{\bullet}',
706: 'radic' => '\ensuremath{\surd}',
707: 8730 => '\ensuremath{\surd}',
708: 8731 => '\ensuremath{\sqrt[3]{}}',
709: 8732 => '\ensuremath{\sqrt[4]{}}',
710: 'prop' => '\ensuremath{\propto}',
711: 8733 => '\ensuremath{\propto}',
712: 'infin' => '\ensuremath{\infty}',
713: 8734 => '\ensuremath{\infty}',
714: #
715: # The items below require the isoent latex package which I can't find at least for FC5.
716: # Temporarily commented out.
717: #
718: # 'ang90' => '\ensuremath{\sqangle}',
719: # 8735 => '\ensuremath{\sqangle}',
720: 'ang' => '\ensuremath{\angle}',
721: 8736 => '\ensuremath{\angle}',
722: 'angmsd' => '\ensuremath{\measuredangle}',
723: 8737 => '\ensuremath{\measuredangle}',
724: 'angsph' => '\ensuremath{\sphericalangle}',
725: 8738 => '\ensuremath{\sphericalangle}',
726: 8739 => '\ensuremath{\vert}',
727: 8740 => '\ensuremath{\Vert}',
728: 'and' => '\ensuremath{\land}',
729: 8743 => '\ensuremath{\land}',
730: 'or' => '\ensuremath{\lor}',
731: 8744 => '\ensuremath{\lor}',
732: 'cap' => '\ensuremath{\cap}',
733: 8745 => '\ensuremath{\cap}',
734: 'cup' => '\ensuremath{\cup}',
735: 8746 => '\ensuremath{\cup}',
736: 'int' => '\ensuremath{\int}',
737: 8747 => '\ensuremath{\int}',
738: 'conint' => '\ensuremath{\oint}',
739: 8750 => '\ensuremath{\oint}',
740: 'there4' => '\ensuremath{\therefore}',
741: 8756 => '\ensuremath{\therefore}',
742: 'becaus' => '\ensuremath{\because}',
743: 8757 => '\ensuremath{\because}',
744: 8758 => '\ensuremath{:}',
745: 8759 => '\ensuremath{::}',
746: 'sim' => '\ensuremath{\sim}',
747: 8764 => '\ensuremath{\sim}',
748: 8765 => '\ensuremath{\backsim}',
749: 'wreath' => '\ensuremath{\wr}',
750: 8768 => '\ensuremath{\wr}',
751: 'nsim' => '\ensuremath{\not\sim}',
752: 8769 => '\ensuremath{\not\sim}',
753: # 'asymp' => '\ensuremath{\asymp}', ≈ is actually a different glyph.
754: 8771 => '\ensuremath{\asymp}',
755: 8772 => '\ensuremath{\not\asymp}',
756: 'cong' => '\ensuremath{\cong}',
757: 8773 => '\ensuremath{\cong}',
758: 8775 => '\ensuremath{\ncong}',
759: 8778 => '\ensuremath{\approxeq}',
760: 8784 => '\ensuremath{\doteq}',
761: 8785 => '\ensuremath{\doteqdot}',
762: 8786 => '\ensuremath{\fallingdotseq}',
763: 8787 => '\ensuremath{\risingdotseq}',
764: 8788 => '\ensuremath{:=}',
765: 8789 => '\ensuremath{=:}',
766: 8790 => '\ensuremath{\eqcirc}',
767: 8791 => '\ensuremath{\circeq}',
768: 'wedgeq' => '\ensuremath{\stackrel{\wedge}{=}}',
769: 8792 => '\ensuremath{\stackrel{\wedge}{=}}',
770: 8794 => '\ensuremath{\stackrel{\vee}{=}}',
771: 8795 => '\ensuremath{\stackrel{\star}{=}}',
772: 8796 => '\ensuremath{\triangleq}',
773: 8797 => '\ensuremath{\stackrel{def}{=}}',
774: 8798 => '\ensuremath{\stackrel{m}{=}}',
775: 8799 => '\ensuremath{\stackrel{?}{=}}',
776: 'ne' => '\ensuremath{\neq}',
777: 8800 => '\ensuremath{\neq}',
778: 'equiv' => '\ensuremath{\equiv}',
779: 8801 => '\ensuremath{\equiv}',
780: 8802 => '\ensuremath{\not\equiv}',
781: 'le' => '\ensuremath{\leq}',
782: 8804 => '\ensuremath{\leq}',
783: 'ge' => '\ensuremath{\geq}',
784: 8805 => '\ensuremath{\geq}',
785: 8806 => '\ensuremath{\leqq}',
786: 8807 => '\ensuremath{\geqq}',
787: 8810 => '\ensuremath{\ll}',
788: 8811 => '\ensuremath{\gg}',
789: 'twixt' => '\ensuremath{\between}',
790: 8812 => '\ensuremath{\between}',
791: 8813 => '\ensuremath{\not\asymp}',
792: 8814 => '\ensuremath{\not<}',
793: 8815 => '\ensuremath{\not>}',
794: 8816 => '\ensuremath{\not\leqslant}',
795: 8817 => '\ensuremath{\not\geqslant}',
796: 8818 => '\ensuremath{\lesssim}',
797: 8819 => '\ensuremath{\gtrsim}',
798: 8820 => '\ensuremath{\stackrel{<}{>}}',
799: 8821 => '\ensuremath{\stackrel{>}{<}}',
800: 8826 => '\ensuremath{\prec}',
801: 8827 => '\ensuremath{\succ}',
802: 8828 => '\ensuremath{\preceq}',
803: 8829 => '\ensuremath{\succeq}',
804: 8830 => '\ensuremath{\not\prec}',
805: 8831 => '\ensuremath{\not\succ}',
806: 'sub' => '\ensuremath{\subset}',
807: 8834 => '\ensuremath{\subset}',
808: 'sup' => '\ensuremath{\supset}',
809: 8835 => '\ensuremath{\supset}',
810: 'nsub' => '\ensuremath{\not\subset}',
811: 8836 => '\ensuremath{\not\subset}',
812: 8837 => '\ensuremath{\not\supset}',
813: 'sube' => '\ensuremath{\subseteq}',
814: 8838 => '\ensuremath{\subseteq}',
815: 'supe' => '\ensuremath{\supseteq}',
816: 8839 => '\ensuremath{\supseteq}',
817: 8840 => '\ensuremath{\nsubseteq}',
818: 8841 => '\ensuremath{\nsupseteq}',
819: 8842 => '\ensuremath{\subsetneq}',
820: 8843 => '\ensuremath{\supsetneq}',
821: 8847 => '\ensuremath{\sqsubset}',
822: 8848 => '\ensuremath{\sqsupset}',
823: 8849 => '\ensuremath{\sqsubseteq}',
824: 8850 => '\ensuremath{\sqsupseteq}',
825: 8851 => '\ensuremath{\sqcap}',
826: 8852 => '\ensuremath{\sqcup}',
827: 'oplus' => '\ensuremath{\oplus}',
828: 8853 => '\ensuremath{\oplus}',
829: 8854 => '\ensuremath{\ominus}',
830: 'otimes' => '\ensuremath{\otimes}',
831: 8855 => '\ensuremath{\otimes}',
832: 8856 => '\ensuremath{\oslash}',
833: 8857 => '\ensuremath{\odot}',
834: 8858 => '\ensuremath{\circledcirc}',
835: 8859 => '\ensuremath{\circledast}',
836: 8861 => '\ensuremath{\ominus}', # Close enough for government work.
837: 8862 => '\ensuremath{\boxplus}',
838: 8863 => '\ensuremath{\boxminus}',
839: 8864 => '\ensuremath{\boxtimes}',
840: 8865 => '\ensuremath{\boxdot}',
841: 'vdash' => '\ensuremath{\vdash}',
842: 8866 => '\ensuremath{\vdash}',
843: 'dashv' => '\ensuremath{\dashv}',
844: 8867 => '\ensuremath{\dashv}',
845: 'perp' => '\ensuremath{\perp}',
846: 8869 => '\ensuremath{\perp}',
847: 8871 => '\ensuremath{\models}',
848: 8872 => '\ensuremath{\vDash}',
849: 8873 => '\ensuremath{\Vdash}',
850: 8874 => '\ensuremath{\Vvdash}',
851: 8876 => '\ensuremath{\nvdash}',
852: 8877 => '\ensuremath{\nvDash}',
853: 8878 => '\ensuremath{\nVdash}',
854: 8880 => '\ensuremath{\prec}',
855: 8881 => '\ensuremath{\succ}',
856: 8882 => '\ensuremath{\vartriangleleft}',
857: 8883 => '\ensuremath{\vartriangleright}',
858: 8884 => '\ensuremath{\trianglelefteq}',
859: 8885 => '\ensuremath{\trianglerighteq}',
860: 8891 => '\ensuremath{\veebar}',
861: 8896 => '\ensuremath{\land}',
862: 8897 => '\ensuremath{\lor}',
863: 8898 => '\ensuremath{\cap}',
864: 8899 => '\ensuremath{\cup}',
865: 8900 => '\ensuremath{\diamond}',
866: 'sdot' => '\ensuremath{\cdot}',
867: 8901 => '\ensuremath{\cdot}',
868: 8902 => '\ensuremath{\star}',
869: 8903 => '\ensuremath{\divideontimes}',
870: 8904 => '\ensuremath{\bowtie}',
871: 8905 => '\ensuremath{\ltimes}',
872: 8906 => '\ensuremath{\rtimes}',
873: 8907 => '\ensuremath{\leftthreetimes}',
874: 8908 => '\ensuremath{\rightthreetimes}',
875: 8909 => '\ensuremath{\simeq}',
876: 8910 => '\ensuremath{\curlyvee}',
877: 8911 => '\ensuremath{\curlywedge}',
878: 8912 => '\ensuremath{\Subset}',
879: 8913 => '\ensuremath{\Supset}',
880: 8914 => '\ensuremath{\Cap}',
881: 8915 => '\ensuremath{\Cup}',
882: 8916 => '\ensuremath{\pitchfork}',
883: 8918 => '\ensuremath{\lessdot}',
884: 8919 => '\ensuremath{\gtrdot}',
885: 8920 => '\ensuremath{\lll}',
886: 8921 => '\ensuremath{\ggg}',
887: 8922 => '\ensuremath{\gtreqless}',
888: 8923 => '\ensuremath{\lesseqgtr}',
889: 8924 => '\ensuremath{\eqslantless}',
890: 8925 => '\ensuremath{\eqslantgtr}',
891: 8926 => '\ensuremath{\curlyeqprec}',
892: 8927 => '\ensuremath{\curlyeqsucc}',
893: 8928 => '\ensuremath{\not\preccurlyeq}',
894: 8929 => '\ensuremath{\not\succcurlyeq}',
895: 8930 => '\ensuremath{\not\sqsupseteq}',
896: 8931 => '\ensuremath{\not\sqsubseteq}',
897: 8938 => '\ensuremath{\not\vartriangleleft}',
898: 8939 => '\ensuremath{\not\vartriangleright}',
899: 8940 => '\ensuremath{\not\trianglelefteq}',
900: 8941 => '\ensuremath{\not\trianglerighteq}',
901: 8942 => '\ensuremath{\vdots}',
902: 8960 => '\ensuremath{\varnothing}',
903: 'lceil' => '\ensuremath{\lceil}',
904: 8968 => '\ensuremath{\lceil}',
905: 'rceil' => '\ensuremath{\rceil}',
906: 8969 => '\ensuremath{\rceil}',
907: 'lfloor' => '\ensuremath{\lfloor}',
908: 8970 => '\ensuremath{\lfloor}',
909: 'rfloor' => '\ensuremath{\rfloor}',
910: 8971 => '\ensuremath{\rfloor}',
911: 'lang' => '\ensuremath{\langle}',
912: 9001 => '\ensuremath{\langle}',
913: 'rang' => '\ensuremath{\rangle}',
914: 9002 => '\ensuremath{\rangle}',
915: 'loz' => '\ensuremath{\lozenge}',
916: 9674 => '\ensuremath{\lozenge}',
917: 'spades' => '\ensuremath{\spadesuit}',
918: 9824 => '\ensuremath{\spadesuit}',
919: 9825 => '\ensuremath{\heartsuit}',
920: 9826 => '\ensuremath{\diamondsuit}',
921: 'clubs' => '\ensuremath{\clubsuit}',
922: 9827 => '\ensuremath{\clubsuit}',
923: 'diams' => '\ensuremath{\blacklozenge}',
924: 9830 => '\ensuremath{\blacklozenge}'
925:
926: );
927:
928: # There are some named entities that don't have a good
929: # latex equivalent, these are converted to utf-8 via this table
930: # of entity name -> unicode number.
931:
932: my %utf_table = (
933: 'THORN' => 222,
934: 'thorn' => 254,
935: 'eth' => 240,
936: 'hearts' => 9829
937: );
938:
939: #
940: # Convert a numerical entity (that does not exist in our hash)
941: # to its UTF-8 equivalent representation.
942: # This allows us to support, to some extent, any entity for which
943: # dvipdf can find a gylph (given that LaTeX is now UTF-8 clean).
944: #
945: # Parameters:
946: # unicode - The unicode for the character. This is assumed to
947: # be a decimal value
948: # Returns:
949: # The UTF-8 equiavalent of the value.
950: #
951: sub entity_to_utf8 {
952: my ($unicode) = @_;
953: my $result = pack("U", $unicode);
954: return $result;
955: }
956:
957:
958: #
959: # Convert an entity to the corresponding LateX if possible.
960: # If not possible, and the entity is numeric,
961: # the entity is treated like a Unicode character and converted
962: # to UTF-8 which should display as long as dvipdf can find the
963: # appropriate glyph.
964: #
965: # The entity is assumed to have already had the
966: # &# ; or & ; removed
967: #
968: # Parameters:
969: # entity - Name of entity to convert.
970: # Returns:
971: # One of the following:
972: # - Latex string that produces the entity.
973: # - UTF-8 equivalent of a numeric entity for which we don't have a latex string.
974: # - ' ' for text entities for which there's no latex equivalent.
975: #
976: sub entity_to_latex {
977: my ($entity) = @_;
978:
979: # Try to look up the entity (text or numeric) in the hash:
980:
981:
982: my $latex = $entities{"$entity"};
983: if (defined $latex) {
984: return $latex;
985: }
986: # If the text is purely numeric we can do the UTF-8 conversion:
987: # Otherwise there are a few textual entities that don't have good latex
988: # which can be converted to unicode:
989: #
990: if ($entity =~ /^\d+$/) {
991: return &entity_to_utf8($entity);
992: } else {
993: my $result = $utf_table{"$entity"};
994: if (defined $result) {
995: return &entity_to_utf8($result);
996: }
997: }
998: # Can't do the conversion`< ...
999:
1000: return " ";
1001: }
1002:
1003: #
1004: # Convert all the entities in a string.
1005: # We locate all the entities, pass them into entity_to_latex and
1006: # and replace occurences in the input string.
1007: # The assumption is that there are few entities in any string/document
1008: # so this looping is not too bad. The advantage of looping vs. regexping is
1009: # that we now can use lookup tables for the translation in entity_to_latex above.
1010: #
1011: # Parameters:
1012: # input - Input string/document
1013: # Returns
1014: # input with entities replaced by latexable stuff (UTF-8 encodings or
1015: # latex control strings to produce the entity.
1016: #
1017: #
1018: sub replace_entities {
1019: my ($input) = @_;
1020: my $start;
1021: my $end;
1022: my $entity;
1023: my $latex;
1024:
1025: # First the &#nnn; entities:
1026:
1027: while ($input =~ /(&\#\d+;)/) {
1028: ($start) = @-;
1029: ($end) = @+;
1030: $entity = substr($input, $start+2, $end-$start-3);
1031: $latex = &entity_to_latex($entity);
1032: substr($input, $start, $end-$start) = $latex;
1033: }
1034: # Now the &text; entites;
1035:
1036: while ($input =~/(&\w+;)/) {
1037: ($start) = @-;
1038: ($end) = @+;
1039: $entity = substr($input, $start+1, $end-$start-2);
1040: $latex = &entity_to_latex($entity);
1041: substr($input, $start, $end-$start) = $latex;
1042:
1043: }
1044: return $input;
1045: }
1046:
1047: 1;
1048:
1049: __END__
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/back.gif){kind=icon}
Return to entities.pm CVS log ![[TXT]](/icons/text.gif){kind=icon}
![[DIR]](/icons/dir.gif){kind=icon}
Up to [LON-CAPA] / loncom / interface