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:
29: =pod
30:
31: =head1 NAME
32:
33: Apache::entities.pm
34:
35: =head1 SYNOPSIS
36:
37: This file contains a table driven entity-->latex converter.
38:
39: This is part of the LearningOnline Network with CAPA project
40: described at http://www.lon-capa.org.
41:
42: =head1 OVERVIEW
43:
44:
45: Assumptions:
46: The number of entities in a resource is small compared with the
47: number of possible entities that might be translated.
48: Therefore the strategy is to match a general entity pattern
49: &.+; over and over, pull out the match look it up in an entity -> tex hash
50: and do the replacement.
51:
52: In order to simplify the hash, the following reductions are done:
53: &#d+; have the &# and ; stripped and is converted to an int.
54: &#.+; have the &#x and ; stripped and is converted to an int as a hex
55: value.
56: All others have the & and ; stripped.
57:
58:
59: The hash: Add new conversions here; leave off the leading & and the trailing ;
60: all numeric entities need only appear as their decimal versions
61: (e.g. no need for 1234 is sufficient, no need for 0x4d2 as well.
62:
63: This entity table is mercilessly cribbed from the HTML pocket reference
64: table starting at pg 82. In most cases the LaTeX equivalent codes come from
65: the original massive regular expression replacements originally by
66: A. Sakharuk in lonprintout.pm
67:
68: I also want to acknowledge
69: ISO Character entities and their LaTeX equivalents by
70: Vidar Bronken Gundersen, and Rune Mathisen
71: http://www.bitjungle.com/isoent-ref.pdf
72:
73:
74: Note numerical entities are essentially unicode character codes.
75:
76:
77: =head1 SUBROUTINES
78:
79: =over
80:
81: =item entity_to_utf8()
82:
83:
84: Convert a numerical entity (that does not exist in our hash)
85: to its UTF-8 equivalent representation.
86: This allows us to support, to some extent, any entity for which
87: dvipdf can find a gylph (given that LaTeX is now UTF-8 clean).
88:
89: Parameters:
90: unicode - The unicode for the character. This is assumed to
91: be a decimal value
92: Returns:
93: The UTF-8 equiavalent of the value.
94:
95: =item entity_to_latex()
96:
97: Convert an entity to the corresponding LateX if possible.
98: If not possible, and the entity is numeric,
99: the entity is treated like a Unicode character and converted
100: to UTF-8 which should display as long as dvipdf can find the
101: appropriate glyph.
102:
103: The entity is assumed to have already had the
104: &; or & ; removed
105:
106: Parameters:
107: entity - Name of entity to convert.
108: Returns:
109: One of the following:
110: - Latex string that produces the entity.
111: - UTF-8 equivalent of a numeric entity for which we don't have a latex string.
112: - ' ' for text entities for which there's no latex equivalent.
113:
114:
115: =item replace_entities()
116:
117: Convert all the entities in a string.
118: We locate all the entities, pass them into entity_to_latex and
119: and replace occurences in the input string.
120: The assumption is that there are few entities in any string/document
121: so this looping is not too bad. The advantage of looping vs. regexping is
122: that we now can use lookup tables for the translation in entity_to_latex above.
123:
124: Parameters:
125: input - Input string/document
126: Returns
127: input with entities replaced by latexable stuff (UTF-8 encodings or
128: latex control strings to produce the entity.
129:
130: =back
131:
132: =head1 TABLES ASCII code page
133:
134: =cut
135:
136: package Apache::entities;
137: use strict;
138:
139: package Apache::entities;
140:
141: my %entities = (
142:
143: =pod
144:
145: =over
146:
147: =item (7-13)
148:
149: # Translation to empty strings:
150: =cut
151:
152: 7 => "",
153: 9 => "",
154: 10 => "",
155: 13 => "",
156:
157: =pod
158:
159: =item (32-126)
160:
161: # Translations to simple characters:
162:
163: =cut
164:
165: 32 => " ",
166: 33 => "!",
167: 34 => '"',
168: 'quot' => '"',
169: 35 => '\\#',
170: 36 => '\\$',
171: 37 => '\%',
172: 38 => '\&',
173: 'amp' => '\&',
174: 39 => '\'', # Apostrophe
175: 40 => '(',
176: 41 => ')',
177: 42 => '*',
178: 43 => '+',
179: 44 => ',', # comma
180: 45 => '-',
181: 46 => '.',
182: 47 => '/',
183: 48 => '0',
184: 49 => '1',
185: 50 => '2',
186: 51 => '3',
187: 52 => '4',
188: 53 => '5',
189: 54 => '6',
190: 55 => '7',
191: 56 => '8',
192: 57 => '9',
193: 58 => ':',
194: 59 => ';',
195: 60 => '\ensuremath{<}',
196: 'lt' => '\ensuremath{<}',
197: 61 => '\ensuremath{=}',
198: 62 => '\ensuremath{>}',
199: 'gt' => '\ensuremath{>}',
200: 63 => '?',
201: 64 => '@',
202: 65 => 'A',
203: 66 => 'B',
204: 67 => 'C',
205: 68 => 'D',
206: 69 => 'E',
207: 70 => 'F',
208: 71 => 'G',
209: 72 => 'H',
210: 73 => 'I',
211: 74 => 'J',
212: 75 => 'K',
213: 76 => 'L',
214: 77 => 'M',
215: 78 => 'N',
216: 79 => 'O',
217: 80 => 'P',
218: 81 => 'Q',
219: 82 => 'R',
220: 83 => 'S',
221: 84 => 'T',
222: 85 => 'U',
223: 86 => 'V',
224: 87 => 'W',
225: 88 => 'X',
226: 89 => 'Y',
227: 90 => 'Z',
228: 91 => '[',
229: 92 => '\ensuremath{\setminus}', # \setminus is \ with special spacing.
230: 93 => ']',
231: 94 => '\ensuremath{\wedge}',
232: 95 => '\underline{\makebox[2mm]{\strut}}', # Underline 2mm of space for _
233: 96 => '`',
234: 97 => 'a',
235: 98 => 'b',
236: 99 => 'c',
237: 100 => 'd',
238: 101 => 'e',
239: 102 => 'f',
240: 103 => 'g',
241: 104 => 'h',
242: 105 => 'i',
243: 106 => 'j',
244: 107 => 'k',
245: 108 => 'l',
246: 109 => 'm',
247: 110 => 'n',
248: 111 => 'o',
249: 112 => 'p',
250: 113 => 'q',
251: 114 => 'r',
252: 115 => 's',
253: 116 => 't',
254: 117 => 'u',
255: 118 => 'v',
256: 119 => 'w',
257: 120 => 'x',
258: 121 => 'y',
259: 122 => 'z',
260: 123 => '\{',
261: 124 => '|',
262: 125 => '\}',
263: 126 => '\~',
264:
265: =pod
266:
267: =item (130-140)
268:
269: Controls and Latin-1 supplement. Note that some entities that have
270: visible effect are not printing unicode characters. Specifically
271: ‚- 
272:
273: =cut
274:
275: 130 => ',',
276: 131 => '\ensuremath{f}',
277: 132 => ',,', # Low double left quotes.
278: 133 => '\ensuremath{\ldots}',
279: 134 => '\ensuremath{\dagger}',
280: 135 => '\ensuremath{\ddagger}',
281: 136 => '\ensuremath{\wedge}',
282: 137 => '\textperthousand ',
283: 138 => '\v{S}',
284: 139 => '\ensuremath{<}',
285: 140 => '{\OE}',
286:
287: =pod
288:
289: =item (145-156)
290:
291: There's a gap here in my entity table
292:
293: =cut
294:
295: 145 => '`',
296: 146 => '\'',
297: 147 => '``',
298: 148 => '\'\'',
299: 149 => '\ensuremath{\bullet}',
300: 150 => '--',
301: 151 => '---',
302: 152 => '\ensuremath{\sim}',
303: 153 => '\texttrademark',
304: 154 => '\v{s}',
305: 155 => '\ensuremath{>}',
306: 156 => '\oe ',
307:
308: =pod
309:
310: =item (159-255)
311:
312: Another short gap:
313:
314: =cut
315:
316: 159 => '\"Y',
317: 160 => '~',
318: 'nbsp' => '~',
319: 161 => '\textexclamdown ',
320: 'iexcl' => '\textexclamdown ',
321: 162 => '\textcent ',
322: 'cent' => '\textcent ',
323: 163 => '\pounds ',
324: 'pound' => '\pounds ',
325: 164 => '\textcurrency ',
326: 'curren' => '\textcurrency ',
327: 165 => '\textyen ',
328: 'yen' => '\textyen ',
329: 166 => '\textbrokenbar ',
330: 'brvbar' => '\textbrokenbar ',
331: 167 => '\textsection ',
332: 'sect' => '\textsection ',
333: 168 => '\"{}',
334: 'uml' => '\"{}',
335: 169 => '\copyright ',
336: 'copy' => '\copyright ',
337: 170 => '\textordfeminine ',
338: 'ordf' => '\textordfeminine ',
339: 171 => '\ensuremath{\ll}', # approximation of left angle quote.
340: 'laquo' => '\ensuremath{\ll}', # ""
341: 172 => '\ensuremath{\neg}',
342: 'not' => '\ensuremath{\neg}',
343: 173 => ' - ',
344: 'shy' => ' - ',
345: 174 => '\textregistered ',
346: 'reg' => '\textregistered ',
347: 175 => '\ensuremath{^{-}}',
348: 'macr' => '\ensuremath{^{-}}',
349: 176 => '\ensuremath{^{\circ}}',
350: 'deg' => '\ensuremath{^{\circ}}',
351: 177 => '\ensuremath{\pm}',
352: 'plusmn' => '\ensuremath{\pm}',
353: 178 => '\ensuremath{^2}',
354: 'sup2' => '\ensuremath{^2}',
355: 179 => '\ensuremath{^3}',
356: 'sup3' => '\ensuremath{^3}',
357: 180 => "\\'{}",
358: 'acute' => "\\'{}",
359: 181 => '\ensuremath{\mu}',
360: 'micro' => '\ensuremath{\mu}',
361: 182 => '\P ',
362: para => '\P ',
363: 183 => '\ensuremath{\cdot}',
364: 'middot' => '\ensuremath{\cdot}',
365: 184 => '\c{\strut}',
366: 'cedil' => '\c{\strut}',
367: 185 => '\ensuremath{^1}',
368: sup1 => '\ensuremath{^1}',
369: 186 => '\textordmasculine ',
370: 'ordm' => '\textordmasculine ',
371: 187 => '\ensuremath{\gg}',
372: 'raquo' => '\ensuremath{\gg}',
373: 188 => '\textonequarter ',
374: 'frac14' => '\textonequarter ',
375: 189 => '\textonehalf' ,
376: 'frac12' => '\textonehalf' ,
377: 190 => '\textthreequarters ',
378: 'frac34' => '\textthreequarters ',
379: 191 => '\textquestiondown ',
380: 'iquest' => '\textquestiondown ',
381: 192 => '\\`{A}',
382: 'Agrave' => '\\`{A}',
383: 193 => "\\'{A}",
384: 'Aacute' => "\\'{A}",
385: 194 => '\^{A}',
386: 'Acirc' => '\^{A}',
387: 195 => '\~{A}',
388: 'Atilde'=> '\~{A}',
389: 196 => '\\"{A}',
390: 'Auml' => '\\"{A}',
391: 197 => '{\AA}',
392: 'Aring' => '{\AA}',
393: 198 => '{\AE}',
394: 'AElig' => '{\AE}',
395: 199 => '\c{c}',
396: 'Ccedil'=> '\c{c}',
397: 200 => '\\`{E}',
398: 'Egrave'=> '\\`{E}',
399: 201 => "\\'{E}",
400: 'Eacute'=> "\\'{E}",
401: 202 => '\\^{E}',
402: 'Ecirc' => '\\^{E}',
403: 203 => '\\"{E}',
404: 'Euml' => '\\"{E}',
405: 204 => '\\`{I}',
406: 'Igrave'=> '\\`{I}',
407: 205 => "\\'{I}",
408: 'Iacute'=> "\\'{I}",
409: 206 => '\\^{I}',
410: 'Icirc' => '\\^{I}',
411: 207 => '\\"{I}',
412: 'Iuml' => '\\"{I}',
413: 208 => '\DH',
414: 'ETH' => '\DH',
415: 209 => '\~{N}',
416: 'Ntilde'=> '\~{N}',
417: 210 => '\\`{O}',
418: 'Ograve'=> '\\`{O}',
419: 211 => "\\'{O}",
420: 'Oacute'=> "\\'{O}",
421: 212 => '\\^{O}',
422: 'Ocirc' => '\\^{O}',
423: 213 => '\~{O}',
424: 'Otilde'=> '\~{O}',
425: 214 => '\\"{O}',
426: 'Ouml' => '\\"{O}',
427: 215 => '\ensuremath{\times}',
428: 'times' => '\ensuremath{\times}',
429: 216 => '\O',
430: 'Oslash'=> '\O',
431: 217 => '\\`{U}',
432: 'Ugrave'=> '\\`{U}',
433: 218 => "\\'{U}",
434: 'Uacute'=> "\\'{U}",
435: 219 => '\\^{U}',
436: 'Ucirc' => '\\^{U}',
437: 220 => '\\"{U}',
438: 'Uuml' => '\\"{U}',
439: 221 => "\\'{Y}",
440: 'Yacute'=> "\\'{Y}",
441: 223 => '{\ss}',
442: 'szlig' => '{\ss}',
443: 224 => '\\`{a}',
444: 'agrave'=> '\\`{a}',
445: 225 => "\\'{a}",
446: 'aacute'=> "\\'{a}",
447: 226 => '\\^{a}',
448: 'acirc' => '\\^{a}',
449: 227 => '\\~{a}',
450: 'atilde'=> '\\~{a}',
451: 228 => '\\"{a}',
452: 'auml' => '\\"{a}',
453: 229 => '\aa',
454: 'aring' => '\aa',
455: 230 => '\ae',
456: 'aelig' => '\ae',
457: 231 => '\c{c}',
458: 'ccedil'=> '\c{c}',
459: 232 => '\\`{e}',
460: 'egrave'=> '\\`{e}',
461: 233 => "\\'{e}",
462: 'eacute'=> "\\'{e}",
463: 234 => '\\^{e}',
464: 'ecirc' => '\\^{e}',
465: 235 => '\\"{e}',
466: 'euml' => '\\"{e}',
467: 236 => '\\`{i}',
468: 'igrave'=> '\\`{i}',
469: 237 => "\\'{i}",
470: 'iacute'=> "\\'{i}",
471: 238 => '\\^{i}',
472: 'icirc' => '\\^{i}',
473: 239 => '\\"{i}',
474: 'iuml' => '\\"{i}',
475: 241 => '\\~{n}',
476: 'ntilde'=> '\\~{n}',
477: 242 => '\\`{o}',
478: 'ograve'=> '\\`{o}',
479: 243 => "\\'{o}",
480: 'oacute'=> "\\'{o}",
481: 244 => '\\^{o}',
482: 'ocirc' => '\\^{o}',
483: 245 => '\\~{o}',
484: 'otilde'=> '\\~{o}',
485: 246 => '\\"{o}',
486: 'ouml' => '\\"{o}',
487: 247 => '\ensuremath{\div}',
488: 'divide'=> '\ensuremath{\div}',
489: 248 => '{\o}',
490: 'oslash'=> '{\o}',
491: 249 => '\\`{u}',
492: 'ugrave'=> '\\`{u}',
493: 250 => "\\'{u}",
494: 'uacute'=> "\\'{u}",
495: 251 => '\\^{u}',
496: 'ucirc' => '\\^{u}',
497: 252 => '\\"{u}',
498: 'uuml' => '\\"{u}',
499: 253 => "\\'{y}",
500: 'yacute'=> "\\'{y}",
501: 255 => '\\"{y}',
502: 'yuml' => '\\"{y}',
503:
504:
505: =pod
506:
507: =item (295)
508:
509: hbar entity number comes from the unicode charater:
510: see e.g. http://www.unicode.org/charts/PDF/U0100.pdf
511: ISO also documents a 'planck' entity.
512:
513: =cut
514:
515: 295 => '\ensuremath{\hbar}',
516: 'planck' => '\ensuremath{\hbar}',
517:
518: =pod
519:
520: =item (338-376)
521:
522: Latin extended-A HTML 4.01 entities:
523:
524: =cut
525:
526: 338 => '\OE',
527: 'OElig' => '\OE',
528: 339 => '\oe',
529: 'oelig' => '\oe',
530: 352 => '\v{S}',
531: 'Scaron' => '\v{S}',
532: 353 => '\v{s}',
533: 'scaron' => '\v{s}',
534: 376 => '\\"{Y}',
535: 'Yuml' => '\\"{Y}',
536:
537: =pod
538:
539: =item (402)
540:
541: Latin extended B HTML 4.01 entities
542:
543: =cut
544:
545: 402 => '\ensuremath{f}',
546: 'fnof' => '\ensuremath{f}',
547:
548: =pod
549:
550: =item (710 & 732)
551:
552: Spacing modifier letters:
553:
554: =cut
555:
556: 710 => '\^{}',
557: 'circ' => '\^{}',
558: 732 => '\~{}',
559: 'tilde' => '\~{}',
560:
561: =pod
562:
563: =item (913-929)
564:
565: Greek uppercase:
566:
567: =cut
568:
569: 913 => '\ensuremath{\mathrm{A}}',
570: 'Alpha' => '\ensuremath{\mathrm{A}}',
571: 914 => '\ensuremath{\mathrm{B}}',
572: 'Beta' => '\ensuremath{\mathrm{B}}',
573: 915 => '\ensuremath{\Gamma}',
574: 'Gamma' => '\ensuremath{\Gamma}',
575: 916 => '\ensuremath{\Delta}',
576: 'Delta' => '\ensuremath{\Delta}',
577: 917 => '\ensuremath{\mathrm{E}}',
578: 'Epsilon'=> '\ensuremath{\mathrm{E}}',
579: 918 => '\ensuremath{\mathrm{Z}}',
580: 'Zeta' => '\ensuremath{\mathrm{Z}}',
581: 919 => '\ensuremath{\mathrm{H}}',
582: 'Eta' => '\ensuremath{\mathrm{H}}',
583: 920 => '\ensuremath{\Theta}',
584: 'Theta' => '\ensuremath{\Theta}',
585: 921 => '\ensuremath{\mathrm{I}}',
586: 'Iota' => '\ensuremath{\mathrm{I}}',
587: 922 => '\ensuremath{\mathrm{K}}',
588: 'Kappa' => '\ensuremath{\mathrm{K}}',
589: 923 => '\ensuremath{\Lambda}',
590: 'Lambda' => '\ensuremath{\Lambda}',
591: 924 => '\ensuremath{\mathrm{M}}',
592: 'Mu' => '\ensuremath{\mathrm{M}}',
593: 925 => '\ensuremath{\mathrm{N}}',
594: 'Nu' => '\ensuremath{\mathrm{N}}',
595: 926 => '\ensuremath{\mathrm{\Xi}}',
596: 'Xi' => '\ensuremath{\mathrm{\Xi}}',
597: 927 => '\ensuremath{\mathrm{O}}',
598: 'Omicron'=> '\ensuremath{\mathrm{O}}',
599: 928 => '\ensuremath{\Pi}',
600: 'Pi' => '\ensuremath{\Pi}',
601: 929 => '\ensuremath{\mathrm{P}}',
602: 'Rho' => '\ensuremath{\mathrm{P}}',
603:
604:
605: =pod
606:
607: =item (931-937)
608:
609: Skips 930
610:
611: =cut
612:
613: 931 => '\ensuremath{\Sigma}',
614: 'Sigma' => '\ensuremath{\Sigma}',
615: 932 => '\ensuremath{\mathrm{T}}',
616: 'Tau' => '\ensuremath{\mathrm{T}}',
617: 933 => '\ensuremath{\Upsilon}',
618: 'Upsilon'=> '\ensuremath{\Upsilon}',
619: 934 => '\ensuremath{\Phi}',
620: 'Phi' => '\ensuremath{\Phi}',
621: 935 => '\ensuremath{\mathrm{X}}',
622: 'Chi' => '\ensuremath{\mathrm{X}}',
623: 936 => '\ensuremath{\Psi}',
624: 'Psi' => '\ensuremath{\Psi}',
625: 937 => '\ensuremath{\Omega}',
626: 'Omega' => '\ensuremath{\Omega}',
627:
628: =pod
629:
630: =item (945-982)
631:
632: Greek lowercase:
633:
634: =cut
635:
636: 945 => '\ensuremath{\alpha}',
637: 'alpha' => '\ensuremath{\alpha}',
638: 946 => '\ensuremath{\beta}',
639: 'beta' => '\ensuremath{\beta}',
640: 947 => '\ensuremath{\gamma}',
641: 'gamma' => '\ensuremath{\gamma}',
642: 948 => '\ensuremath{\delta}',
643: 'delta' => '\ensuremath{\delta}',
644: 949 => '\ensuremath{\epsilon}',
645: 'epsilon'=> '\ensuremath{\epsilon}',
646: 950 => '\ensuremath{\zeta}',
647: 'zeta' => '\ensuremath{\zeta}',
648: 951 => '\ensuremath{\eta}',
649: 'eta' => '\ensuremath{\eta}',
650: 952 => '\ensuremath{\theta}',
651: 'theta' => '\ensuremath{\theta}',
652: 953 => '\ensuremath{\iota}',
653: 'iota' => '\ensuremath{\iota}',
654: 954 => '\ensuremath{\kappa}',
655: 'kappa' => '\ensuremath{\kappa}',
656: 955 => '\ensuremath{\lambda}',
657: 'lambda' => '\ensuremath{\lambda}',
658: 956 => '\ensuremath{\mu}',
659: 'mu' => '\ensuremath{\mu}',
660: 957 => '\ensuremath{\nu}',
661: 'nu' => '\ensuremath{\nu}',
662: 958 => '\ensuremath{\xi}',
663: 'xi' => '\ensuremath{\xi}',
664: 959 => '\ensuremath{o}',
665: 'omicron'=> '\ensuremath{o}',
666: 960 => '\ensuremath{\pi}',
667: 'pi' => '\ensuremath{\pi}',
668: 961 => '\ensuremath{\rho}',
669: 'rho' => '\ensuremath{\rho}',
670: 962 => '\ensuremath{\varsigma}',
671: 'sigmaf' => '\ensuremath{\varsigma}',
672: 963 => '\ensuremath{\sigma}',
673: 'sigma' => '\ensuremath{\sigma}',
674: 964 => '\ensuremath{\tau}',
675: 'tau' => '\ensuremath{\tau}',
676: 965 => '\ensuremath{\upsilon}',
677: 'upsilon'=> '\ensuremath{\upsilon}',
678: 966 => '\ensuremath{\phi}',
679: 'phi' => '\ensuremath{\phi}',
680: 967 => '\ensuremath{\chi}',
681: 'chi' => '\ensuremath{\chi}',
682: 968 => '\ensuremath{\psi}',
683: 'psi' => '\ensuremath{\psi}',
684: 969 => '\ensuremath{\omega}',
685: 'omega' => '\ensuremath{\omega}',
686: 977 => '\ensuremath{\vartheta}',
687: 'thetasym'=>'\ensuremath{\vartheta}',
688: 978 => '\ensuremath{\mathit{\Upsilon}}',
689: 'upsih' => '\ensuremath{\mathit{\Upsilon}}',
690: 982 => '\ensuremath{\varpi}',
691: 'piv' => '\ensuremath{\varpi}',
692:
693: =pod
694:
695: =item (8194-8364)
696:
697: The general punctuation set:
698:
699: =cut
700:
701: 8194, => '\hspace{.5em}',
702: 'enspc' => '\hspace{.5em}',
703: 8195 => '\hspace{1.0em}',
704: 'emspc' => '\hspace{1.0em}',
705: 8201 => '\hspace{0.167em}',
706: 'thinsp' => '\hspace{0.167em}',
707: 8204 => '{}',
708: 'zwnj' => '{}',
709: 8205 => '',
710: 'zwj' => '',
711: 8206 => '',
712: 'lrm' => '',
713: 8207 => '',
714: 'rlm' => '',
715: 8211 => '--',
716: 'ndash' => '--',
717: 8212 => '---',
718: 'mdash' => '---',
719: 8216 => '`',
720: 'lsquo' => '`',
721: 8217 => "'",
722: 'rsquo' => "'",
723: 8218 => '\quotesinglbase',
724: 'sbquo' => '\quotesinglbase',
725: 8220 => '``',
726: 'ldquo' => '``',
727: 8221 => "''",
728: 'rdquo' => "''",
729: 8222 => '\quotedblbase',
730: 'bdquo' => '\quotedblbase',
731: 8224 => '\ensuremath{\dagger}',
732: 'dagger' => '\ensuremath{\dagger}',
733: '8225' => '\ensuremath{\ddag}',
734: 'Dagger' => '\ensuremath{\ddag}',
735: 8226 => '\textbullet',
736: 'bull' => '\textbullet',
737: 8230 => '\textellipsis',
738: 'hellep' => '\textellipsis',
739: 8240 => '\textperthousand',
740: permil => '\textperthousand',
741: 8242 => '\textquotesingle',
742: 'prime' => '\textquotesingle',
743: 8243 => '\textquotedbl',
744: 'Prime' => '\textquotedbl',
745: 8249 => '\guilsinglleft',
746: 'lsaquo' => '\guilsinglleft',
747: 8250 => '\guilsinglright',
748: 'rsaquo' => '\guilsinglright',
749: 8254 => '\textasciimacron',
750: oline => '\textasciimacron',
751: 8260 => '\textfractionsolidus',
752: 'frasl' => '\textfractionsolidus',
753: 8364 => '\texteuro',
754: 'euro' => '\texteuro',
755:
756: =pod
757:
758: =item (8472-8501)
759:
760: Letter like symbols
761:
762: =cut
763:
764:
765: 8472 => '\ensuremath{\wp}',
766: 'weierp' => '\ensuremath{\wp}',
767: 8465 => '\ensuremath{\Im}',
768: 'image' => '\ensuremath{\Im}',
769: 8476 => '\ensuremath{\Re}',
770: 'real' => '\ensuremath{\Re}',
771: 8482 => '\texttrademark',
772: 'trade' => '\texttrademark',
773: 8501 => '\ensuremath{\aleph}',
774: 'alefsym'=> '\ensuremath{\aleph}',
775:
776: =pod
777:
778: =item (8592-8669)
779:
780: Arrows and then some (harpoons from Hon Kie).
781:
782: =cut
783:
784: 8592 => '\textleftarrow',
785: 'larr' => '\textleftarrow',
786: 8593 => '\textuparrow',
787: 'uarr' => '\textuparrow',
788: 8594 => '\textrightarrow',
789: 'rarr' => '\textrightarrow',
790: 8595 => '\textdownarrow',
791: 'darr' => '\textdownarrow',
792: 8596 => '\ensuremath{\leftrightarrow}',
793: 'harr' => '\ensuremath{\leftrightarrow}',
794: 8598 => '\ensuremath{\nwarrow}',
795: 8599 => '\ensuremath{\nearrow}',
796: 8600 => '\ensuremath{\searrow}',
797: 8601 => '\ensuremath{\swarrow}',
798: 8605 => '\ensuremath{\leadsto}',
799: 8614 => '\ensuremath{\mapsto}',
800: 8617 => '\ensuremath{\hookleftarrow}',
801: 8618 => '\ensuremath{\hookrightarrow}',
802: 8629 => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
803: 'crarr' => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
804: 8636 => '\ensuremath{\leftharpoonup}',
805: 8637 => '\ensuremath{\leftharpoondown}',
806: 8640 => '\ensuremath{\rightharpoonup}',
807: 8641 => '\ensuremath{\rightharpoondown}',
808: 8652 => '\ensuremath{\rightleftharpoons}',
809: 8656 => '\ensuremath{\Leftarrow}',
810: 'lArr' => '\ensuremath{\Leftarrow}',
811: 8657 => '\ensuremath{\Uparrow}',
812: 'uArr' => '\ensuremath{\Uparrow}',
813: 8658 => '\ensuremath{\Rightarrow}',
814: 'rArr' => '\ensuremath{\Rightarrow}',
815: 8659 => '\ensuremath{\Downarrow}',
816: 'dArr' => '\ensuremath{\Downarrow}',
817: 8660 => '\ensuremath{\Leftrightarrow}',
818: 'hArr' => '\ensuremath{\Leftrightarrow}',
819: 8661 => '\ensuremath{\Updownarrow}',
820: 'vArr' => '\ensuremath{\Updownarrow}',
821: 8666 => '\ensuremath{\Lleftarrow}',
822: 'lAarr' => '\ensuremath{\Lleftarrow}',
823: 8667 => '\ensuremath{\Rrightarrow}',
824: 'rAarr' => '\ensuremath{\Rrightarrow}',
825: 8669 => '\ensuremath{\rightsquigarrow}',
826: 'rarrw' => '\ensuremath{\rightsquigarrow}',
827:
828: =pod
829:
830: =item (8704-8734)
831:
832: Mathematical operators.
833:
834: =cut
835:
836:
837: 'forall' => '\ensuremath{\forall}',
838: 8704 => '\ensuremath{\forall}',
839: 'comp' => '\ensuremath{\complement}',
840: 8705 => '\ensuremath{\complement}',
841: 'part' => '\ensuremath{\partial}',
842: 8706 => '\ensuremath{\partial}',
843: 'exist' => '\ensuremath{\exists}',
844: 8707 => '\ensuremath{\exists}',
845: 'nexist' => '\ensuremath{\nexists}',
846: 8708 => '\ensuremath{\nexists}',
847: 'empty' => '\ensuremath{\emptyset}',
848: 8709 => '\ensuremath{\emptyset}',
849: 8710 => '\ensuremath{\Delta}',
850: 'nabla' => '\ensuremath{\nabla}',
851: 8711 => '\ensuremath{\nabla}',
852: 'isin' => '\ensuremath{\in}',
853: 8712 => '\ensuremath{\in}',
854: 'notin' => '\ensuremath{\notin}',
855: 8713 => '\ensuremath{\notin}',
856: ni => '\ensuremath{\ni}',
857: 8715 => '\ensuremath{\ni}',
858: 8716 => '\ensuremath{\not\ni}',
859: 'prod' => '\ensuremath{\prod}',
860: 8719 => '\ensuremath{\prod}',
861: 8720 => '\ensuremath{\coprod}',
862: 'sum' => '\ensuremath{\sum}',
863: 8721 => '\ensuremath{\sum}',
864: 'minus' => '\ensuremath{-}',
865: 8722 => '\ensuremath{-}',
866: 8723 => '\ensuremath{\mp}',
867: 8724 => '\ensuremath{\dotplus}',
868: 8725 => '\ensuremath{\diagup}',
869: 8726 => '\ensuremath{\smallsetminus}',
870: 'lowast' => '\ensuremath{*}',
871: 8727 => '\ensuremath{*}',
872: 8728 => '\ensuremath{\circ}',
873: 8729 => '\ensuremath{\bullet}',
874: 'radic' => '\ensuremath{\surd}',
875: 8730 => '\ensuremath{\surd}',
876: 8731 => '\ensuremath{\sqrt[3]{}}',
877: 8732 => '\ensuremath{\sqrt[4]{}}',
878: 'prop' => '\ensuremath{\propto}',
879: 8733 => '\ensuremath{\propto}',
880: 'infin' => '\ensuremath{\infty}',
881: 8734 => '\ensuremath{\infty}',
882:
883:
884: =pod
885:
886: =item (8735-9830)
887:
888:
889: The items below require the isoent latex package which I can't find at least for FC5.
890: Temporarily commented out.
891:
892: 'ang90' => '\ensuremath{\sqangle}',
893: 8735 => '\ensuremath{\sqangle}',
894:
895: =cut
896:
897: 'ang' => '\ensuremath{\angle}',
898: 8736 => '\ensuremath{\angle}',
899: 'angmsd' => '\ensuremath{\measuredangle}',
900: 8737 => '\ensuremath{\measuredangle}',
901: 'angsph' => '\ensuremath{\sphericalangle}',
902: 8738 => '\ensuremath{\sphericalangle}',
903: 8739 => '\ensuremath{\vert}',
904: 8740 => '\ensuremath{\Vert}',
905: 'and' => '\ensuremath{\land}',
906: 8743 => '\ensuremath{\land}',
907: 'or' => '\ensuremath{\lor}',
908: 8744 => '\ensuremath{\lor}',
909: 'cap' => '\ensuremath{\cap}',
910: 8745 => '\ensuremath{\cap}',
911: 'cup' => '\ensuremath{\cup}',
912: 8746 => '\ensuremath{\cup}',
913: 'int' => '\ensuremath{\int}',
914: 8747 => '\ensuremath{\int}',
915: 'conint' => '\ensuremath{\oint}',
916: 8750 => '\ensuremath{\oint}',
917: 'there4' => '\ensuremath{\therefore}',
918: 8756 => '\ensuremath{\therefore}',
919: 'becaus' => '\ensuremath{\because}',
920: 8757 => '\ensuremath{\because}',
921: 8758 => '\ensuremath{:}',
922: 8759 => '\ensuremath{::}',
923: 'sim' => '\ensuremath{\sim}',
924: 8764 => '\ensuremath{\sim}',
925: 8765 => '\ensuremath{\backsim}',
926: 'wreath' => '\ensuremath{\wr}',
927: 8768 => '\ensuremath{\wr}',
928: 'nsim' => '\ensuremath{\not\sim}',
929: 8769 => '\ensuremath{\not\sim}',
930: # 'asymp' => '\ensuremath{\asymp}', ≈ is actually a different glyph.
931: 8771 => '\ensuremath{\asymp}',
932: 8772 => '\ensuremath{\not\asymp}',
933: 'cong' => '\ensuremath{\cong}',
934: 8773 => '\ensuremath{\cong}',
935: 8775 => '\ensuremath{\ncong}',
936: 8778 => '\ensuremath{\approxeq}',
937: 8784 => '\ensuremath{\doteq}',
938: 8785 => '\ensuremath{\doteqdot}',
939: 8786 => '\ensuremath{\fallingdotseq}',
940: 8787 => '\ensuremath{\risingdotseq}',
941: 8788 => '\ensuremath{:=}',
942: 8789 => '\ensuremath{=:}',
943: 8790 => '\ensuremath{\eqcirc}',
944: 8791 => '\ensuremath{\circeq}',
945: 'wedgeq' => '\ensuremath{\stackrel{\wedge}{=}}',
946: 8792 => '\ensuremath{\stackrel{\wedge}{=}}',
947: 8794 => '\ensuremath{\stackrel{\vee}{=}}',
948: 8795 => '\ensuremath{\stackrel{\star}{=}}',
949: 8796 => '\ensuremath{\triangleq}',
950: 8797 => '\ensuremath{\stackrel{def}{=}}',
951: 8798 => '\ensuremath{\stackrel{m}{=}}',
952: 8799 => '\ensuremath{\stackrel{?}{=}}',
953: 'ne' => '\ensuremath{\neq}',
954: 8800 => '\ensuremath{\neq}',
955: 'equiv' => '\ensuremath{\equiv}',
956: 8801 => '\ensuremath{\equiv}',
957: 8802 => '\ensuremath{\not\equiv}',
958: 'le' => '\ensuremath{\leq}',
959: 8804 => '\ensuremath{\leq}',
960: 'ge' => '\ensuremath{\geq}',
961: 8805 => '\ensuremath{\geq}',
962: 8806 => '\ensuremath{\leqq}',
963: 8807 => '\ensuremath{\geqq}',
964: 8810 => '\ensuremath{\ll}',
965: 8811 => '\ensuremath{\gg}',
966: 'twixt' => '\ensuremath{\between}',
967: 8812 => '\ensuremath{\between}',
968: 8813 => '\ensuremath{\not\asymp}',
969: 8814 => '\ensuremath{\not<}',
970: 8815 => '\ensuremath{\not>}',
971: 8816 => '\ensuremath{\not\leqslant}',
972: 8817 => '\ensuremath{\not\geqslant}',
973: 8818 => '\ensuremath{\lesssim}',
974: 8819 => '\ensuremath{\gtrsim}',
975: 8820 => '\ensuremath{\stackrel{<}{>}}',
976: 8821 => '\ensuremath{\stackrel{>}{<}}',
977: 8826 => '\ensuremath{\prec}',
978: 8827 => '\ensuremath{\succ}',
979: 8828 => '\ensuremath{\preceq}',
980: 8829 => '\ensuremath{\succeq}',
981: 8830 => '\ensuremath{\not\prec}',
982: 8831 => '\ensuremath{\not\succ}',
983: 'sub' => '\ensuremath{\subset}',
984: 8834 => '\ensuremath{\subset}',
985: 'sup' => '\ensuremath{\supset}',
986: 8835 => '\ensuremath{\supset}',
987: 'nsub' => '\ensuremath{\not\subset}',
988: 8836 => '\ensuremath{\not\subset}',
989: 8837 => '\ensuremath{\not\supset}',
990: 'sube' => '\ensuremath{\subseteq}',
991: 8838 => '\ensuremath{\subseteq}',
992: 'supe' => '\ensuremath{\supseteq}',
993: 8839 => '\ensuremath{\supseteq}',
994: 8840 => '\ensuremath{\nsubseteq}',
995: 8841 => '\ensuremath{\nsupseteq}',
996: 8842 => '\ensuremath{\subsetneq}',
997: 8843 => '\ensuremath{\supsetneq}',
998: 8847 => '\ensuremath{\sqsubset}',
999: 8848 => '\ensuremath{\sqsupset}',
1000: 8849 => '\ensuremath{\sqsubseteq}',
1001: 8850 => '\ensuremath{\sqsupseteq}',
1002: 8851 => '\ensuremath{\sqcap}',
1003: 8852 => '\ensuremath{\sqcup}',
1004: 'oplus' => '\ensuremath{\oplus}',
1005: 8853 => '\ensuremath{\oplus}',
1006: 8854 => '\ensuremath{\ominus}',
1007: 'otimes' => '\ensuremath{\otimes}',
1008: 8855 => '\ensuremath{\otimes}',
1009: 8856 => '\ensuremath{\oslash}',
1010: 8857 => '\ensuremath{\odot}',
1011: 8858 => '\ensuremath{\circledcirc}',
1012: 8859 => '\ensuremath{\circledast}',
1013: 8861 => '\ensuremath{\ominus}', # Close enough for government work.
1014: 8862 => '\ensuremath{\boxplus}',
1015: 8863 => '\ensuremath{\boxminus}',
1016: 8864 => '\ensuremath{\boxtimes}',
1017: 8865 => '\ensuremath{\boxdot}',
1018: 'vdash' => '\ensuremath{\vdash}',
1019: 8866 => '\ensuremath{\vdash}',
1020: 'dashv' => '\ensuremath{\dashv}',
1021: 8867 => '\ensuremath{\dashv}',
1022: 'perp' => '\ensuremath{\perp}',
1023: 8869 => '\ensuremath{\perp}',
1024: 8871 => '\ensuremath{\models}',
1025: 8872 => '\ensuremath{\vDash}',
1026: 8873 => '\ensuremath{\Vdash}',
1027: 8874 => '\ensuremath{\Vvdash}',
1028: 8876 => '\ensuremath{\nvdash}',
1029: 8877 => '\ensuremath{\nvDash}',
1030: 8878 => '\ensuremath{\nVdash}',
1031: 8880 => '\ensuremath{\prec}',
1032: 8881 => '\ensuremath{\succ}',
1033: 8882 => '\ensuremath{\vartriangleleft}',
1034: 8883 => '\ensuremath{\vartriangleright}',
1035: 8884 => '\ensuremath{\trianglelefteq}',
1036: 8885 => '\ensuremath{\trianglerighteq}',
1037: 8891 => '\ensuremath{\veebar}',
1038: 8896 => '\ensuremath{\land}',
1039: 8897 => '\ensuremath{\lor}',
1040: 8898 => '\ensuremath{\cap}',
1041: 8899 => '\ensuremath{\cup}',
1042: 8900 => '\ensuremath{\diamond}',
1043: 'sdot' => '\ensuremath{\cdot}',
1044: 8901 => '\ensuremath{\cdot}',
1045: 8902 => '\ensuremath{\star}',
1046: 8903 => '\ensuremath{\divideontimes}',
1047: 8904 => '\ensuremath{\bowtie}',
1048: 8905 => '\ensuremath{\ltimes}',
1049: 8906 => '\ensuremath{\rtimes}',
1050: 8907 => '\ensuremath{\leftthreetimes}',
1051: 8908 => '\ensuremath{\rightthreetimes}',
1052: 8909 => '\ensuremath{\simeq}',
1053: 8910 => '\ensuremath{\curlyvee}',
1054: 8911 => '\ensuremath{\curlywedge}',
1055: 8912 => '\ensuremath{\Subset}',
1056: 8913 => '\ensuremath{\Supset}',
1057: 8914 => '\ensuremath{\Cap}',
1058: 8915 => '\ensuremath{\Cup}',
1059: 8916 => '\ensuremath{\pitchfork}',
1060: 8918 => '\ensuremath{\lessdot}',
1061: 8919 => '\ensuremath{\gtrdot}',
1062: 8920 => '\ensuremath{\lll}',
1063: 8921 => '\ensuremath{\ggg}',
1064: 8922 => '\ensuremath{\gtreqless}',
1065: 8923 => '\ensuremath{\lesseqgtr}',
1066: 8924 => '\ensuremath{\eqslantless}',
1067: 8925 => '\ensuremath{\eqslantgtr}',
1068: 8926 => '\ensuremath{\curlyeqprec}',
1069: 8927 => '\ensuremath{\curlyeqsucc}',
1070: 8928 => '\ensuremath{\not\preccurlyeq}',
1071: 8929 => '\ensuremath{\not\succcurlyeq}',
1072: 8930 => '\ensuremath{\not\sqsupseteq}',
1073: 8931 => '\ensuremath{\not\sqsubseteq}',
1074: 8938 => '\ensuremath{\not\vartriangleleft}',
1075: 8939 => '\ensuremath{\not\vartriangleright}',
1076: 8940 => '\ensuremath{\not\trianglelefteq}',
1077: 8941 => '\ensuremath{\not\trianglerighteq}',
1078: 8942 => '\ensuremath{\vdots}',
1079: 8960 => '\ensuremath{\varnothing}',
1080: 'lceil' => '\ensuremath{\lceil}',
1081: 8968 => '\ensuremath{\lceil}',
1082: 'rceil' => '\ensuremath{\rceil}',
1083: 8969 => '\ensuremath{\rceil}',
1084: 'lfloor' => '\ensuremath{\lfloor}',
1085: 8970 => '\ensuremath{\lfloor}',
1086: 'rfloor' => '\ensuremath{\rfloor}',
1087: 8971 => '\ensuremath{\rfloor}',
1088: 'lang' => '\ensuremath{\langle}',
1089: 9001 => '\ensuremath{\langle}',
1090: 'rang' => '\ensuremath{\rangle}',
1091: 9002 => '\ensuremath{\rangle}',
1092: 'loz' => '\ensuremath{\lozenge}',
1093: 9674 => '\ensuremath{\lozenge}',
1094: 'spades' => '\ensuremath{\spadesuit}',
1095: 9824 => '\ensuremath{\spadesuit}',
1096: 9825 => '\ensuremath{\heartsuit}',
1097: 9826 => '\ensuremath{\diamondsuit}',
1098: 'clubs' => '\ensuremath{\clubsuit}',
1099: 9827 => '\ensuremath{\clubsuit}',
1100: 'diams' => '\ensuremath{\blacklozenge}',
1101: 9830 => '\ensuremath{\blacklozenge}'
1102:
1103: );
1104:
1105: =pod
1106:
1107: =item *
1108:
1109: There are some named entities that don't have a good
1110: latex equivalent, these are converted to utf-8 via this table
1111: of entity name -> unicode number.
1112:
1113: =back
1114:
1115: =cut
1116:
1117: my %utf_table = (
1118: 'THORN' => 222,
1119: 'thorn' => 254,
1120: 'eth' => 240,
1121: 'hearts' => 9829
1122: );
1123:
1124: sub entity_to_utf8 {
1125: my ($unicode) = @_;
1126: my $result = pack("U", $unicode);
1127: return $result;
1128: }
1129:
1130:
1131:
1132: sub entity_to_latex {
1133: my ($entity) = @_;
1134:
1135: # Try to look up the entity (text or numeric) in the hash:
1136:
1137:
1138:
1139: my $latex = $entities{"$entity"};
1140: if (defined $latex) {
1141: return $latex;
1142: }
1143: # If the text is purely numeric we can do the UTF-8 conversion:
1144: # Otherwise there are a few textual entities that don't have good latex
1145: # which can be converted to unicode:
1146: #
1147: if ($entity =~ /^\d+$/) {
1148: return &entity_to_utf8($entity);
1149: } else {
1150: my $result = $utf_table{"$entity"};
1151: if (defined $result) {
1152: return &entity_to_utf8($result);
1153: }
1154: }
1155: # Can't do the conversion`< ...
1156:
1157: return " ";
1158: }
1159:
1160:
1161: sub replace_entities {
1162: my ($input) = @_;
1163: my $start;
1164: my $end;
1165: my $entity;
1166: my $latex;
1167:
1168: # First the &#nnn; entities:
1169:
1170: while ($input =~ /(&\#\d+;)/) {
1171: ($start) = @-;
1172: ($end) = @+;
1173: $entity = substr($input, $start+2, $end-$start-3);
1174: $latex = &entity_to_latex($entity);
1175: substr($input, $start, $end-$start) = $latex;
1176: }
1177:
1178: # Hexadecimal entities:
1179:
1180: while ($input =~ /&\#x(\d|[a-f,A-f])+;/) {
1181: ($start) = @-;
1182: ($end) = @+;
1183: $entity = "0" . substr($input, $start+2, $end-$start-3); # 0xhexnumber
1184: $latex = &entity_to_latex(hex($entity));
1185: substr($input, $start, $end-$start) = $latex;
1186: }
1187:
1188:
1189: # Now the &text; entites;
1190:
1191: while ($input =~/(&\w+;)/) {
1192: ($start) = @-;
1193: ($end) = @+;
1194: $entity = substr($input, $start+1, $end-$start-2);
1195: $latex = &entity_to_latex($entity);
1196: substr($input, $start, $end-$start) = $latex;
1197:
1198: }
1199: return $input;
1200: }
1201:
1202: 1;
1203:
1204: __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