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