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: =item entity_to_utf8()
80:
81:
82: Convert a numerical entity (that does not exist in our hash)
83: to its UTF-8 equivalent representation.
84: This allows us to support, to some extent, any entity for which
85: dvipdf can find a gylph (given that LaTeX is now UTF-8 clean).
86:
87: Parameters:
88: unicode - The unicode for the character. This is assumed to
89: be a decimal value
90: Returns:
91: The UTF-8 equiavalent of the value.
92:
93: =item entity_to_latex()
94:
95: Convert an entity to the corresponding LateX if possible.
96: If not possible, and the entity is numeric,
97: the entity is treated like a Unicode character and converted
98: to UTF-8 which should display as long as dvipdf can find the
99: appropriate glyph.
100:
101: The entity is assumed to have already had the
102: &; or & ; removed
103:
104: Parameters:
105: entity - Name of entity to convert.
106: Returns:
107: One of the following:
108: - Latex string that produces the entity.
109: - UTF-8 equivalent of a numeric entity for which we don't have a latex string.
110: - ' ' for text entities for which there's no latex equivalent.
111:
112:
113: =item replace_entities()
114:
115: Convert all the entities in a string.
116: We locate all the entities, pass them into entity_to_latex and
117: and replace occurences in the input string.
118: The assumption is that there are few entities in any string/document
119: so this looping is not too bad. The advantage of looping vs. regexping is
120: that we now can use lookup tables for the translation in entity_to_latex above.
121:
122: Parameters:
123: input - Input string/document
124: Returns
125: input with entities replaced by latexable stuff (UTF-8 encodings or
126: latex control strings to produce the entity.
127:
128: =head1 TABLES ASCII code page
129:
130: =cut
131:
132:
133: package Apache::entities;
134: use strict;
135:
136: package Apache::entities;
137:
138: my %entities = (
139:
140: =pod
141:
142: =out
143:
144: =item (7-13)
145:
146: # Translation to empty strings:
147: =cut
148:
149: 7 => "",
150: 9 => "",
151: 10 => "",
152: 13 => "",
153:
154: =pod
155:
156: =item (32-126)
157:
158: # Translations to simple characters:
159:
160: =cut
161:
162: 32 => " ",
163: 33 => "!",
164: 34 => '"',
165: 'quot' => '"',
166: 35 => '\\#',
167: 36 => '\\$',
168: 37 => '\%',
169: 38 => '\&',
170: 'amp' => '\&',
171: 39 => '\'', # Apostrophe
172: 40 => '(',
173: 41 => ')',
174: 42 => '*',
175: 43 => '+',
176: 44 => ',', # comma
177: 45 => '-',
178: 46 => '.',
179: 47 => '/',
180: 48 => '0',
181: 49 => '1',
182: 50 => '2',
183: 51 => '3',
184: 52 => '4',
185: 53 => '5',
186: 54 => '6',
187: 55 => '7',
188: 56 => '8',
189: 57 => '9',
190: 58 => ':',
191: 59 => ';',
192: 60 => '\ensuremath{<}',
193: 'lt' => '\ensuremath{<}',
194: 61 => '\ensuremath{=}',
195: 62 => '\ensuremath{>}',
196: 'gt' => '\ensuremath{>}',
197: 63 => '?',
198: 64 => '@',
199: 65 => 'A',
200: 66 => 'B',
201: 67 => 'C',
202: 68 => 'D',
203: 69 => 'E',
204: 70 => 'F',
205: 71 => 'G',
206: 72 => 'H',
207: 73 => 'I',
208: 74 => 'J',
209: 75 => 'K',
210: 76 => 'L',
211: 77 => 'M',
212: 78 => 'N',
213: 79 => 'O',
214: 80 => 'P',
215: 81 => 'Q',
216: 82 => 'R',
217: 83 => 'S',
218: 84 => 'T',
219: 85 => 'U',
220: 86 => 'V',
221: 87 => 'W',
222: 88 => 'X',
223: 89 => 'Y',
224: 90 => 'Z',
225: 91 => '[',
226: 92 => '\ensuremath{\setminus}', # \setminus is \ with special spacing.
227: 93 => ']',
228: 94 => '\ensuremath{\wedge}',
229: 95 => '\underline{\makebox[2mm]{\strut}}', # Underline 2mm of space for _
230: 96 => '`',
231: 97 => 'a',
232: 98 => 'b',
233: 99 => 'c',
234: 100 => 'd',
235: 101 => 'e',
236: 102 => 'f',
237: 103 => 'g',
238: 104 => 'h',
239: 105 => 'i',
240: 106 => 'j',
241: 107 => 'k',
242: 108 => 'l',
243: 109 => 'm',
244: 110 => 'n',
245: 111 => 'o',
246: 112 => 'p',
247: 113 => 'q',
248: 114 => 'r',
249: 115 => 's',
250: 116 => 't',
251: 117 => 'u',
252: 118 => 'v',
253: 119 => 'w',
254: 120 => 'x',
255: 121 => 'y',
256: 122 => 'z',
257: 123 => '\{',
258: 124 => '|',
259: 125 => '\}',
260: 126 => '\~',
261:
262: =pod
263:
264: =item (130-140)
265:
266: Controls and Latin-1 supplement. Note that some entities that have
267: visible effect are not printing unicode characters. Specifically
268: ‚- 
269:
270: =cut
271:
272: 130 => ',',
273: 131 => '\ensuremath{f}',
274: 132 => ',,', # Low double left quotes.
275: 133 => '\ensuremath{\ldots}',
276: 134 => '\ensuremath{\dagger}',
277: 135 => '\ensuremath{\ddagger}',
278: 136 => '\ensuremath{\wedge}',
279: 137 => '\textperthousand ',
280: 138 => '\v{S}',
281: 139 => '\ensuremath{<}',
282: 140 => '{\OE}',
283:
284: =pod
285:
286: =item (145-156)
287:
288: There's a gap here in my entity table
289:
290: =cut
291:
292: 145 => '`',
293: 146 => '\'',
294: 147 => '``',
295: 148 => '\'\'',
296: 149 => '\ensuremath{\bullet}',
297: 150 => '--',
298: 151 => '---',
299: 152 => '\ensuremath{\sim}',
300: 153 => '\texttrademark',
301: 154 => '\v{s}',
302: 155 => '\ensuremath{>}',
303: 156 => '\oe ',
304:
305: =pod
306:
307: =item (159-255)
308:
309: Another short gap:
310:
311: =cut
312:
313: 159 => '\"Y',
314: 160 => '~',
315: 'nbsp' => '~',
316: 161 => '\textexclamdown ',
317: 'iexcl' => '\textexclamdown ',
318: 162 => '\textcent ',
319: 'cent' => '\textcent ',
320: 163 => '\pounds ',
321: 'pound' => '\pounds ',
322: 164 => '\textcurrency ',
323: 'curren' => '\textcurrency ',
324: 165 => '\textyen ',
325: 'yen' => '\textyen ',
326: 166 => '\textbrokenbar ',
327: 'brvbar' => '\textbrokenbar ',
328: 167 => '\textsection ',
329: 'sect' => '\textsection ',
330: 168 => '\"{}',
331: 'uml' => '\"{}',
332: 169 => '\copyright ',
333: 'copy' => '\copyright ',
334: 170 => '\textordfeminine ',
335: 'ordf' => '\textordfeminine ',
336: 171 => '\ensuremath{\ll}', # approximation of left angle quote.
337: 'laquo' => '\ensuremath{\ll}', # ""
338: 172 => '\ensuremath{\neg}',
339: 'not' => '\ensuremath{\neg}',
340: 173 => ' - ',
341: 'shy' => ' - ',
342: 174 => '\textregistered ',
343: 'reg' => '\textregistered ',
344: 175 => '\ensuremath{^{-}}',
345: 'macr' => '\ensuremath{^{-}}',
346: 176 => '\ensuremath{^{\circ}}',
347: 'deg' => '\ensuremath{^{\circ}}',
348: 177 => '\ensuremath{\pm}',
349: 'plusmn' => '\ensuremath{\pm}',
350: 178 => '\ensuremath{^2}',
351: 'sup2' => '\ensuremath{^2}',
352: 179 => '\ensuremath{^3}',
353: 'sup3' => '\ensuremath{^3}',
354: 180 => "\\'{}",
355: 'acute' => "\\'{}",
356: 181 => '\ensuremath{\mu}',
357: 'micro' => '\ensuremath{\mu}',
358: 182 => '\P ',
359: para => '\P ',
360: 183 => '\ensuremath{\cdot}',
361: 'middot' => '\ensuremath{\cdot}',
362: 184 => '\c{\strut}',
363: 'cedil' => '\c{\strut}',
364: 185 => '\ensuremath{^1}',
365: sup1 => '\ensuremath{^1}',
366: 186 => '\textordmasculine ',
367: 'ordm' => '\textordmasculine ',
368: 187 => '\ensuremath{\gg}',
369: 'raquo' => '\ensuremath{\gg}',
370: 188 => '\textonequarter ',
371: 'frac14' => '\textonequarter ',
372: 189 => '\textonehalf' ,
373: 'frac12' => '\textonehalf' ,
374: 190 => '\textthreequarters ',
375: 'frac34' => '\textthreequarters ',
376: 191 => '\textquestiondown ',
377: 'iquest' => '\textquestiondown ',
378: 192 => '\\`{A}',
379: 'Agrave' => '\\`{A}',
380: 193 => "\\'{A}",
381: 'Aacute' => "\\'{A}",
382: 194 => '\^{A}',
383: 'Acirc' => '\^{A}',
384: 195 => '\~{A}',
385: 'Atilde'=> '\~{A}',
386: 196 => '\\"{A}',
387: 'Auml' => '\\"{A}',
388: 197 => '{\AA}',
389: 'Aring' => '{\AA}',
390: 198 => '{\AE}',
391: 'AElig' => '{\AE}',
392: 199 => '\c{c}',
393: 'Ccedil'=> '\c{c}',
394: 200 => '\\`{E}',
395: 'Egrave'=> '\\`{E}',
396: 201 => "\\'{E}",
397: 'Eacute'=> "\\'{E}",
398: 202 => '\\^{E}',
399: 'Ecirc' => '\\^{E}',
400: 203 => '\\"{E}',
401: 'Euml' => '\\"{E}',
402: 204 => '\\`{I}',
403: 'Igrave'=> '\\`{I}',
404: 205 => "\\'{I}",
405: 'Iacute'=> "\\'{I}",
406: 206 => '\\^{I}',
407: 'Icirc' => '\\^{I}',
408: 207 => '\\"{I}',
409: 'Iuml' => '\\"{I}',
410: 208 => '\DH',
411: 'ETH' => '\DH',
412: 209 => '\~{N}',
413: 'Ntilde'=> '\~{N}',
414: 210 => '\\`{O}',
415: 'Ograve'=> '\\`{O}',
416: 211 => "\\'{O}",
417: 'Oacute'=> "\\'{O}",
418: 212 => '\\^{O}',
419: 'Ocirc' => '\\^{O}',
420: 213 => '\~{O}',
421: 'Otilde'=> '\~{O}',
422: 214 => '\\"{O}',
423: 'Ouml' => '\\"{O}',
424: 215 => '\ensuremath{\times}',
425: 'times' => '\ensuremath{\times}',
426: 216 => '\O',
427: 'Oslash'=> '\O',
428: 217 => '\\`{U}',
429: 'Ugrave'=> '\\`{U}',
430: 218 => "\\'{U}",
431: 'Uacute'=> "\\'{U}",
432: 219 => '\\^{U}',
433: 'Ucirc' => '\\^{U}',
434: 220 => '\\"{U}',
435: 'Uuml' => '\\"{U}',
436: 221 => "\\'{Y}",
437: 'Yacute'=> "\\'{Y}",
438: 223 => '{\ss}',
439: 'szlig' => '{\ss}',
440: 224 => '\\`{a}',
441: 'agrave'=> '\\`{a}',
442: 225 => "\\'{a}",
443: 'aacute'=> "\\'{a}",
444: 226 => '\\^{a}',
445: 'acirc' => '\\^{a}',
446: 227 => '\\~{a}',
447: 'atilde'=> '\\~{a}',
448: 228 => '\\"{a}',
449: 'auml' => '\\"{a}',
450: 229 => '\aa',
451: 'aring' => '\aa',
452: 230 => '\ae',
453: 'aelig' => '\ae',
454: 231 => '\c{c}',
455: 'ccedil'=> '\c{c}',
456: 232 => '\\`{e}',
457: 'egrave'=> '\\`{e}',
458: 233 => "\\'{e}",
459: 'eacute'=> "\\'{e}",
460: 234 => '\\^{e}',
461: 'ecirc' => '\\^{e}',
462: 235 => '\\"{e}',
463: 'euml' => '\\"{e}',
464: 236 => '\\`{i}',
465: 'igrave'=> '\\`{i}',
466: 237 => "\\'{i}",
467: 'iacute'=> "\\'{i}",
468: 238 => '\\^{i}',
469: 'icirc' => '\\^{i}',
470: 239 => '\\"{i}',
471: 'iuml' => '\\"{i}',
472: 241 => '\\~{n}',
473: 'ntilde'=> '\\~{n}',
474: 242 => '\\`{o}',
475: 'ograve'=> '\\`{o}',
476: 243 => "\\'{o}",
477: 'oacute'=> "\\'{o}",
478: 244 => '\\^{o}',
479: 'ocirc' => '\\^{o}',
480: 245 => '\\~{o}',
481: 'otilde'=> '\\~{o}',
482: 246 => '\\"{o}',
483: 'ouml' => '\\"{o}',
484: 247 => '\ensuremath{\div}',
485: 'divide'=> '\ensuremath{\div}',
486: 248 => '{\o}',
487: 'oslash'=> '{\o}',
488: 249 => '\\`{u}',
489: 'ugrave'=> '\\`{u}',
490: 250 => "\\'{u}",
491: 'uacute'=> "\\'{u}",
492: 251 => '\\^{u}',
493: 'ucirc' => '\\^{u}',
494: 252 => '\\"{u}',
495: 'uuml' => '\\"{u}',
496: 253 => "\\'{y}",
497: 'yacute'=> "\\'{y}",
498: 255 => '\\"{y}',
499: 'yuml' => '\\"{y}',
500:
501:
502: =pod
503:
504: =item (295)
505:
506: hbar entity number comes from the unicode charater:
507: see e.g. http://www.unicode.org/charts/PDF/U0100.pdf
508: ISO also documents a 'planck' entity.
509:
510: =cut
511:
512: 295 => '\ensuremath{\hbar}',
513: 'planck' => '\ensuremath{\hbar}',
514:
515: =pod
516:
517: =item (338-376)
518:
519: Latin extended-A HTML 4.01 entities:
520:
521: =cut
522:
523: 338 => '\OE',
524: 'OElig' => '\OE',
525: 339 => '\oe',
526: 'oelig' => '\oe',
527: 352 => '\v{S}',
528: 'Scaron' => '\v{S}',
529: 353 => '\v{s}',
530: 'scaron' => '\v{s}',
531: 376 => '\\"{Y}',
532: 'Yuml' => '\\"{Y}',
533:
534: =pod
535:
536: =item (402)
537:
538: Latin extended B HTML 4.01 entities
539:
540: =cut
541:
542: 402 => '\ensuremath{f}',
543: 'fnof' => '\ensuremath{f}',
544:
545: =pod
546:
547: =item (710 & 732)
548:
549: Spacing modifier letters:
550:
551: =cut
552:
553: 710 => '\^{}',
554: 'circ' => '\^{}',
555: 732 => '\~{}',
556: 'tilde' => '\~{}',
557:
558: =pod
559:
560: =item (913-929)
561:
562: Greek uppercase:
563:
564: =cut
565:
566: 913 => '\ensuremath{\mathrm{A}}',
567: 'Alpha' => '\ensuremath{\mathrm{A}}',
568: 914 => '\ensuremath{\mathrm{B}}',
569: 'Beta' => '\ensuremath{\mathrm{B}}',
570: 915 => '\ensuremath{\Gamma}',
571: 'Gamma' => '\ensuremath{\Gamma}',
572: 916 => '\ensuremath{\Delta}',
573: 'Delta' => '\ensuremath{\Delta}',
574: 917 => '\ensuremath{\mathrm{E}}',
575: 'Epsilon'=> '\ensuremath{\mathrm{E}}',
576: 918 => '\ensuremath{\mathrm{Z}}',
577: 'Zeta' => '\ensuremath{\mathrm{Z}}',
578: 919 => '\ensuremath{\mathrm{H}}',
579: 'Eta' => '\ensuremath{\mathrm{H}}',
580: 920 => '\ensuremath{\Theta}',
581: 'Theta' => '\ensuremath{\Theta}',
582: 921 => '\ensuremath{\mathrm{I}}',
583: 'Iota' => '\ensuremath{\mathrm{I}}',
584: 922 => '\ensuremath{\mathrm{K}}',
585: 'Kappa' => '\ensuremath{\mathrm{K}}',
586: 923 => '\ensuremath{\Lambda}',
587: 'Lambda' => '\ensuremath{\Lambda}',
588: 924 => '\ensuremath{\mathrm{M}}',
589: 'Mu' => '\ensuremath{\mathrm{M}}',
590: 925 => '\ensuremath{\mathrm{N}}',
591: 'Nu' => '\ensuremath{\mathrm{N}}',
592: 926 => '\ensuremath{\mathrm{\Xi}}',
593: 'Xi' => '\ensuremath{\mathrm{\Xi}}',
594: 927 => '\ensuremath{\mathrm{O}}',
595: 'Omicron'=> '\ensuremath{\mathrm{O}}',
596: 928 => '\ensuremath{\Pi}',
597: 'Pi' => '\ensuremath{\Pi}',
598: 929 => '\ensuremath{\mathrm{P}}',
599: 'Rho' => '\ensuremath{\mathrm{P}}',
600:
601:
602: =pod
603:
604: =item (931-937)
605:
606: Skips 930
607:
608: =cut
609:
610: 931 => '\ensuremath{\Sigma}',
611: 'Sigma' => '\ensuremath{\Sigma}',
612: 932 => '\ensuremath{\mathrm{T}}',
613: 'Tau' => '\ensuremath{\mathrm{T}}',
614: 933 => '\ensuremath{\Upsilon}',
615: 'Upsilon'=> '\ensuremath{\Upsilon}',
616: 934 => '\ensuremath{\Phi}',
617: 'Phi' => '\ensuremath{\Phi}',
618: 935 => '\ensuremath{\mathrm{X}}',
619: 'Chi' => '\ensuremath{\mathrm{X}}',
620: 936 => '\ensuremath{\Psi}',
621: 'Psi' => '\ensuremath{\Psi}',
622: 937 => '\ensuremath{\Omega}',
623: 'Omega' => '\ensuremath{\Omega}',
624:
625: =pod
626:
627: =item (945-982)
628:
629: Greek lowercase:
630:
631: =cut
632:
633: 945 => '\ensuremath{\alpha}',
634: 'alpha' => '\ensuremath{\alpha}',
635: 946 => '\ensuremath{\beta}',
636: 'beta' => '\ensuremath{\beta}',
637: 947 => '\ensuremath{\gamma}',
638: 'gamma' => '\ensuremath{\gamma}',
639: 948 => '\ensuremath{\delta}',
640: 'delta' => '\ensuremath{\delta}',
641: 949 => '\ensuremath{\epsilon}',
642: 'epsilon'=> '\ensuremath{\epsilon}',
643: 950 => '\ensuremath{\zeta}',
644: 'zeta' => '\ensuremath{\zeta}',
645: 951 => '\ensuremath{\eta}',
646: 'eta' => '\ensuremath{\eta}',
647: 952 => '\ensuremath{\theta}',
648: 'theta' => '\ensuremath{\theta}',
649: 953 => '\ensuremath{\iota}',
650: 'iota' => '\ensuremath{\iota}',
651: 954 => '\ensuremath{\kappa}',
652: 'kappa' => '\ensuremath{\kappa}',
653: 955 => '\ensuremath{\lambda}',
654: 'lambda' => '\ensuremath{\lambda}',
655: 956 => '\ensuremath{\mu}',
656: 'mu' => '\ensuremath{\mu}',
657: 957 => '\ensuremath{\nu}',
658: 'nu' => '\ensuremath{\nu}',
659: 958 => '\ensuremath{\xi}',
660: 'xi' => '\ensuremath{\xi}',
661: 959 => '\ensuremath{o}',
662: 'omicron'=> '\ensuremath{o}',
663: 960 => '\ensuremath{\pi}',
664: 'pi' => '\ensuremath{\pi}',
665: 961 => '\ensuremath{\rho}',
666: 'rho' => '\ensuremath{\rho}',
667: 962 => '\ensuremath{\varsigma}',
668: 'sigmaf' => '\ensuremath{\varsigma}',
669: 963 => '\ensuremath{\sigma}',
670: 'sigma' => '\ensuremath{\sigma}',
671: 964 => '\ensuremath{\tau}',
672: 'tau' => '\ensuremath{\tau}',
673: 965 => '\ensuremath{\upsilon}',
674: 'upsilon'=> '\ensuremath{\upsilon}',
675: 966 => '\ensuremath{\phi}',
676: 'phi' => '\ensuremath{\phi}',
677: 967 => '\ensuremath{\chi}',
678: 'chi' => '\ensuremath{\chi}',
679: 968 => '\ensuremath{\psi}',
680: 'psi' => '\ensuremath{\psi}',
681: 969 => '\ensuremath{\omega}',
682: 'omega' => '\ensuremath{\omega}',
683: 977 => '\ensuremath{\vartheta}',
684: 'thetasym'=>'\ensuremath{\vartheta}',
685: 978 => '\ensuremath{\mathit{\Upsilon}}',
686: 'upsih' => '\ensuremath{\mathit{\Upsilon}}',
687: 982 => '\ensuremath{\varpi}',
688: 'piv' => '\ensuremath{\varpi}',
689:
690: =pod
691:
692: =item (8194-8364)
693:
694: The general punctuation set:
695:
696: =cut
697:
698: 8194, => '\hspace{.5em}',
699: 'enspc' => '\hspace{.5em}',
700: 8195 => '\hspace{1.0em}',
701: 'emspc' => '\hspace{1.0em}',
702: 8201 => '\hspace{0.167em}',
703: 'thinsp' => '\hspace{0.167em}',
704: 8204 => '{}',
705: 'zwnj' => '{}',
706: 8205 => '',
707: 'zwj' => '',
708: 8206 => '',
709: 'lrm' => '',
710: 8207 => '',
711: 'rlm' => '',
712: 8211 => '--',
713: 'ndash' => '--',
714: 8212 => '---',
715: 'mdash' => '---',
716: 8216 => '`',
717: 'lsquo' => '`',
718: 8217 => "'",
719: 'rsquo' => "'",
720: 8218 => '\quotesinglbase',
721: 'sbquo' => '\quotesinglbase',
722: 8220 => '``',
723: 'ldquo' => '``',
724: 8221 => "''",
725: 'rdquo' => "''",
726: 8222 => '\quotedblbase',
727: 'bdquo' => '\quotedblbase',
728: 8224 => '\ensuremath{\dagger}',
729: 'dagger' => '\ensuremath{\dagger}',
730: '8225' => '\ensuremath{\ddag}',
731: 'Dagger' => '\ensuremath{\ddag}',
732: 8226 => '\textbullet',
733: 'bull' => '\textbullet',
734: 8230 => '\textellipsis',
735: 'hellep' => '\textellipsis',
736: 8240 => '\textperthousand',
737: permil => '\textperthousand',
738: 8242 => '\textquotesingle',
739: 'prime' => '\textquotesingle',
740: 8243 => '\textquotedbl',
741: 'Prime' => '\textquotedbl',
742: 8249 => '\guilsinglleft',
743: 'lsaquo' => '\guilsinglleft',
744: 8250 => '\guilsinglright',
745: 'rsaquo' => '\guilsinglright',
746: 8254 => '\textasciimacron',
747: oline => '\textasciimacron',
748: 8260 => '\textfractionsolidus',
749: 'frasl' => '\textfractionsolidus',
750: 8364 => '\texteuro',
751: 'euro' => '\texteuro',
752:
753: =pod
754:
755: =item (8472-8501)
756:
757: Letter like symbols
758:
759: =cut
760:
761:
762: 8472 => '\ensuremath{\wp}',
763: 'weierp' => '\ensuremath{\wp}',
764: 8465 => '\ensuremath{\Im}',
765: 'image' => '\ensuremath{\Im}',
766: 8476 => '\ensuremath{\Re}',
767: 'real' => '\ensuremath{\Re}',
768: 8482 => '\texttrademark',
769: 'trade' => '\texttrademark',
770: 8501 => '\ensuremath{\aleph}',
771: 'alefsym'=> '\ensuremath{\aleph}',
772:
773: =pod
774:
775: =item (8592-8669)
776:
777: Arrows and then some (harpoons from Hon Kie).
778:
779: =cut
780:
781: 8592 => '\textleftarrow',
782: 'larr' => '\textleftarrow',
783: 8593 => '\textuparrow',
784: 'uarr' => '\textuparrow',
785: 8594 => '\textrightarrow',
786: 'rarr' => '\textrightarrow',
787: 8595 => '\textdownarrow',
788: 'darr' => '\textdownarrow',
789: 8596 => '\ensuremath{\leftrightarrow}',
790: 'harr' => '\ensuremath{\leftrightarrow}',
791: 8598 => '\ensuremath{\nwarrow}',
792: 8599 => '\ensuremath{\nearrow}',
793: 8600 => '\ensuremath{\searrow}',
794: 8601 => '\ensuremath{\swarrow}',
795: 8605 => '\ensuremath{\leadsto}',
796: 8614 => '\ensuremath{\mapsto}',
797: 8617 => '\ensuremath{\hookleftarrow}',
798: 8618 => '\ensuremath{\hookrightarrow}',
799: 8629 => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
800: 'crarr' => '\ensuremath{\hookleftarrow}', # not an exact match but best I know.
801: 8636 => '\ensuremath{\leftharpoonup}',
802: 8637 => '\ensuremath{\leftharpoondown}',
803: 8640 => '\ensuremath{\rightharpoonup}',
804: 8641 => '\ensuremath{\rightharpoondown}',
805: 8652 => '\ensuremath{\rightleftharpoons}',
806: 8656 => '\ensuremath{\Leftarrow}',
807: 'lArr' => '\ensuremath{\Leftarrow}',
808: 8657 => '\ensuremath{\Uparrow}',
809: 'uArr' => '\ensuremath{\Uparrow}',
810: 8658 => '\ensuremath{\Rightarrow}',
811: 'rArr' => '\ensuremath{\Rightarrow}',
812: 8659 => '\ensuremath{\Downarrow}',
813: 'dArr' => '\ensuremath{\Downarrow}',
814: 8660 => '\ensuremath{\Leftrightarrow}',
815: 'hArr' => '\ensuremath{\Leftrightarrow}',
816: 8661 => '\ensuremath{\Updownarrow}',
817: 'vArr' => '\ensuremath{\Updownarrow}',
818: 8666 => '\ensuremath{\Lleftarrow}',
819: 'lAarr' => '\ensuremath{\Lleftarrow}',
820: 8667 => '\ensuremath{\Rrightarrow}',
821: 'rAarr' => '\ensuremath{\Rrightarrow}',
822: 8669 => '\ensuremath{\rightsquigarrow}',
823: 'rarrw' => '\ensuremath{\rightsquigarrow}',
824:
825: =pod
826:
827: =item (8704-8734)
828:
829: Mathematical operators.
830:
831: =cut
832:
833:
834: 'forall' => '\ensuremath{\forall}',
835: 8704 => '\ensuremath{\forall}',
836: 'comp' => '\ensuremath{\complement}',
837: 8705 => '\ensuremath{\complement}',
838: 'part' => '\ensuremath{\partial}',
839: 8706 => '\ensuremath{\partial}',
840: 'exist' => '\ensuremath{\exists}',
841: 8707 => '\ensuremath{\exists}',
842: 'nexist' => '\ensuremath{\nexists}',
843: 8708 => '\ensuremath{\nexists}',
844: 'empty' => '\ensuremath{\emptyset}',
845: 8709 => '\ensuremath{\emptyset}',
846: 8710 => '\ensuremath{\Delta}',
847: 'nabla' => '\ensuremath{\nabla}',
848: 8711 => '\ensuremath{\nabla}',
849: 'isin' => '\ensuremath{\in}',
850: 8712 => '\ensuremath{\in}',
851: 'notin' => '\ensuremath{\notin}',
852: 8713 => '\ensuremath{\notin}',
853: ni => '\ensuremath{\ni}',
854: 8715 => '\ensuremath{\ni}',
855: 8716 => '\ensuremath{\not\ni}',
856: 'prod' => '\ensuremath{\prod}',
857: 8719 => '\ensuremath{\prod}',
858: 8720 => '\ensuremath{\coprod}',
859: 'sum' => '\ensuremath{\sum}',
860: 8721 => '\ensuremath{\sum}',
861: 'minus' => '\ensuremath{-}',
862: 8722 => '\ensuremath{-}',
863: 8723 => '\ensuremath{\mp}',
864: 8724 => '\ensuremath{\dotplus}',
865: 8725 => '\ensuremath{\diagup}',
866: 8726 => '\ensuremath{\smallsetminus}',
867: 'lowast' => '\ensuremath{*}',
868: 8727 => '\ensuremath{*}',
869: 8728 => '\ensuremath{\circ}',
870: 8729 => '\ensuremath{\bullet}',
871: 'radic' => '\ensuremath{\surd}',
872: 8730 => '\ensuremath{\surd}',
873: 8731 => '\ensuremath{\sqrt[3]{}}',
874: 8732 => '\ensuremath{\sqrt[4]{}}',
875: 'prop' => '\ensuremath{\propto}',
876: 8733 => '\ensuremath{\propto}',
877: 'infin' => '\ensuremath{\infty}',
878: 8734 => '\ensuremath{\infty}',
879:
880:
881: =pod
882:
883: =item (8735-9830)
884:
885:
886: The items below require the isoent latex package which I can't find at least for FC5.
887: Temporarily commented out.
888:
889: 'ang90' => '\ensuremath{\sqangle}',
890: 8735 => '\ensuremath{\sqangle}',
891:
892: =cut
893:
894: 'ang' => '\ensuremath{\angle}',
895: 8736 => '\ensuremath{\angle}',
896: 'angmsd' => '\ensuremath{\measuredangle}',
897: 8737 => '\ensuremath{\measuredangle}',
898: 'angsph' => '\ensuremath{\sphericalangle}',
899: 8738 => '\ensuremath{\sphericalangle}',
900: 8739 => '\ensuremath{\vert}',
901: 8740 => '\ensuremath{\Vert}',
902: 'and' => '\ensuremath{\land}',
903: 8743 => '\ensuremath{\land}',
904: 'or' => '\ensuremath{\lor}',
905: 8744 => '\ensuremath{\lor}',
906: 'cap' => '\ensuremath{\cap}',
907: 8745 => '\ensuremath{\cap}',
908: 'cup' => '\ensuremath{\cup}',
909: 8746 => '\ensuremath{\cup}',
910: 'int' => '\ensuremath{\int}',
911: 8747 => '\ensuremath{\int}',
912: 'conint' => '\ensuremath{\oint}',
913: 8750 => '\ensuremath{\oint}',
914: 'there4' => '\ensuremath{\therefore}',
915: 8756 => '\ensuremath{\therefore}',
916: 'becaus' => '\ensuremath{\because}',
917: 8757 => '\ensuremath{\because}',
918: 8758 => '\ensuremath{:}',
919: 8759 => '\ensuremath{::}',
920: 'sim' => '\ensuremath{\sim}',
921: 8764 => '\ensuremath{\sim}',
922: 8765 => '\ensuremath{\backsim}',
923: 'wreath' => '\ensuremath{\wr}',
924: 8768 => '\ensuremath{\wr}',
925: 'nsim' => '\ensuremath{\not\sim}',
926: 8769 => '\ensuremath{\not\sim}',
927: # 'asymp' => '\ensuremath{\asymp}', ≈ is actually a different glyph.
928: 8771 => '\ensuremath{\asymp}',
929: 8772 => '\ensuremath{\not\asymp}',
930: 'cong' => '\ensuremath{\cong}',
931: 8773 => '\ensuremath{\cong}',
932: 8775 => '\ensuremath{\ncong}',
933: 8778 => '\ensuremath{\approxeq}',
934: 8784 => '\ensuremath{\doteq}',
935: 8785 => '\ensuremath{\doteqdot}',
936: 8786 => '\ensuremath{\fallingdotseq}',
937: 8787 => '\ensuremath{\risingdotseq}',
938: 8788 => '\ensuremath{:=}',
939: 8789 => '\ensuremath{=:}',
940: 8790 => '\ensuremath{\eqcirc}',
941: 8791 => '\ensuremath{\circeq}',
942: 'wedgeq' => '\ensuremath{\stackrel{\wedge}{=}}',
943: 8792 => '\ensuremath{\stackrel{\wedge}{=}}',
944: 8794 => '\ensuremath{\stackrel{\vee}{=}}',
945: 8795 => '\ensuremath{\stackrel{\star}{=}}',
946: 8796 => '\ensuremath{\triangleq}',
947: 8797 => '\ensuremath{\stackrel{def}{=}}',
948: 8798 => '\ensuremath{\stackrel{m}{=}}',
949: 8799 => '\ensuremath{\stackrel{?}{=}}',
950: 'ne' => '\ensuremath{\neq}',
951: 8800 => '\ensuremath{\neq}',
952: 'equiv' => '\ensuremath{\equiv}',
953: 8801 => '\ensuremath{\equiv}',
954: 8802 => '\ensuremath{\not\equiv}',
955: 'le' => '\ensuremath{\leq}',
956: 8804 => '\ensuremath{\leq}',
957: 'ge' => '\ensuremath{\geq}',
958: 8805 => '\ensuremath{\geq}',
959: 8806 => '\ensuremath{\leqq}',
960: 8807 => '\ensuremath{\geqq}',
961: 8810 => '\ensuremath{\ll}',
962: 8811 => '\ensuremath{\gg}',
963: 'twixt' => '\ensuremath{\between}',
964: 8812 => '\ensuremath{\between}',
965: 8813 => '\ensuremath{\not\asymp}',
966: 8814 => '\ensuremath{\not<}',
967: 8815 => '\ensuremath{\not>}',
968: 8816 => '\ensuremath{\not\leqslant}',
969: 8817 => '\ensuremath{\not\geqslant}',
970: 8818 => '\ensuremath{\lesssim}',
971: 8819 => '\ensuremath{\gtrsim}',
972: 8820 => '\ensuremath{\stackrel{<}{>}}',
973: 8821 => '\ensuremath{\stackrel{>}{<}}',
974: 8826 => '\ensuremath{\prec}',
975: 8827 => '\ensuremath{\succ}',
976: 8828 => '\ensuremath{\preceq}',
977: 8829 => '\ensuremath{\succeq}',
978: 8830 => '\ensuremath{\not\prec}',
979: 8831 => '\ensuremath{\not\succ}',
980: 'sub' => '\ensuremath{\subset}',
981: 8834 => '\ensuremath{\subset}',
982: 'sup' => '\ensuremath{\supset}',
983: 8835 => '\ensuremath{\supset}',
984: 'nsub' => '\ensuremath{\not\subset}',
985: 8836 => '\ensuremath{\not\subset}',
986: 8837 => '\ensuremath{\not\supset}',
987: 'sube' => '\ensuremath{\subseteq}',
988: 8838 => '\ensuremath{\subseteq}',
989: 'supe' => '\ensuremath{\supseteq}',
990: 8839 => '\ensuremath{\supseteq}',
991: 8840 => '\ensuremath{\nsubseteq}',
992: 8841 => '\ensuremath{\nsupseteq}',
993: 8842 => '\ensuremath{\subsetneq}',
994: 8843 => '\ensuremath{\supsetneq}',
995: 8847 => '\ensuremath{\sqsubset}',
996: 8848 => '\ensuremath{\sqsupset}',
997: 8849 => '\ensuremath{\sqsubseteq}',
998: 8850 => '\ensuremath{\sqsupseteq}',
999: 8851 => '\ensuremath{\sqcap}',
1000: 8852 => '\ensuremath{\sqcup}',
1001: 'oplus' => '\ensuremath{\oplus}',
1002: 8853 => '\ensuremath{\oplus}',
1003: 8854 => '\ensuremath{\ominus}',
1004: 'otimes' => '\ensuremath{\otimes}',
1005: 8855 => '\ensuremath{\otimes}',
1006: 8856 => '\ensuremath{\oslash}',
1007: 8857 => '\ensuremath{\odot}',
1008: 8858 => '\ensuremath{\circledcirc}',
1009: 8859 => '\ensuremath{\circledast}',
1010: 8861 => '\ensuremath{\ominus}', # Close enough for government work.
1011: 8862 => '\ensuremath{\boxplus}',
1012: 8863 => '\ensuremath{\boxminus}',
1013: 8864 => '\ensuremath{\boxtimes}',
1014: 8865 => '\ensuremath{\boxdot}',
1015: 'vdash' => '\ensuremath{\vdash}',
1016: 8866 => '\ensuremath{\vdash}',
1017: 'dashv' => '\ensuremath{\dashv}',
1018: 8867 => '\ensuremath{\dashv}',
1019: 'perp' => '\ensuremath{\perp}',
1020: 8869 => '\ensuremath{\perp}',
1021: 8871 => '\ensuremath{\models}',
1022: 8872 => '\ensuremath{\vDash}',
1023: 8873 => '\ensuremath{\Vdash}',
1024: 8874 => '\ensuremath{\Vvdash}',
1025: 8876 => '\ensuremath{\nvdash}',
1026: 8877 => '\ensuremath{\nvDash}',
1027: 8878 => '\ensuremath{\nVdash}',
1028: 8880 => '\ensuremath{\prec}',
1029: 8881 => '\ensuremath{\succ}',
1030: 8882 => '\ensuremath{\vartriangleleft}',
1031: 8883 => '\ensuremath{\vartriangleright}',
1032: 8884 => '\ensuremath{\trianglelefteq}',
1033: 8885 => '\ensuremath{\trianglerighteq}',
1034: 8891 => '\ensuremath{\veebar}',
1035: 8896 => '\ensuremath{\land}',
1036: 8897 => '\ensuremath{\lor}',
1037: 8898 => '\ensuremath{\cap}',
1038: 8899 => '\ensuremath{\cup}',
1039: 8900 => '\ensuremath{\diamond}',
1040: 'sdot' => '\ensuremath{\cdot}',
1041: 8901 => '\ensuremath{\cdot}',
1042: 8902 => '\ensuremath{\star}',
1043: 8903 => '\ensuremath{\divideontimes}',
1044: 8904 => '\ensuremath{\bowtie}',
1045: 8905 => '\ensuremath{\ltimes}',
1046: 8906 => '\ensuremath{\rtimes}',
1047: 8907 => '\ensuremath{\leftthreetimes}',
1048: 8908 => '\ensuremath{\rightthreetimes}',
1049: 8909 => '\ensuremath{\simeq}',
1050: 8910 => '\ensuremath{\curlyvee}',
1051: 8911 => '\ensuremath{\curlywedge}',
1052: 8912 => '\ensuremath{\Subset}',
1053: 8913 => '\ensuremath{\Supset}',
1054: 8914 => '\ensuremath{\Cap}',
1055: 8915 => '\ensuremath{\Cup}',
1056: 8916 => '\ensuremath{\pitchfork}',
1057: 8918 => '\ensuremath{\lessdot}',
1058: 8919 => '\ensuremath{\gtrdot}',
1059: 8920 => '\ensuremath{\lll}',
1060: 8921 => '\ensuremath{\ggg}',
1061: 8922 => '\ensuremath{\gtreqless}',
1062: 8923 => '\ensuremath{\lesseqgtr}',
1063: 8924 => '\ensuremath{\eqslantless}',
1064: 8925 => '\ensuremath{\eqslantgtr}',
1065: 8926 => '\ensuremath{\curlyeqprec}',
1066: 8927 => '\ensuremath{\curlyeqsucc}',
1067: 8928 => '\ensuremath{\not\preccurlyeq}',
1068: 8929 => '\ensuremath{\not\succcurlyeq}',
1069: 8930 => '\ensuremath{\not\sqsupseteq}',
1070: 8931 => '\ensuremath{\not\sqsubseteq}',
1071: 8938 => '\ensuremath{\not\vartriangleleft}',
1072: 8939 => '\ensuremath{\not\vartriangleright}',
1073: 8940 => '\ensuremath{\not\trianglelefteq}',
1074: 8941 => '\ensuremath{\not\trianglerighteq}',
1075: 8942 => '\ensuremath{\vdots}',
1076: 8960 => '\ensuremath{\varnothing}',
1077: 'lceil' => '\ensuremath{\lceil}',
1078: 8968 => '\ensuremath{\lceil}',
1079: 'rceil' => '\ensuremath{\rceil}',
1080: 8969 => '\ensuremath{\rceil}',
1081: 'lfloor' => '\ensuremath{\lfloor}',
1082: 8970 => '\ensuremath{\lfloor}',
1083: 'rfloor' => '\ensuremath{\rfloor}',
1084: 8971 => '\ensuremath{\rfloor}',
1085: 'lang' => '\ensuremath{\langle}',
1086: 9001 => '\ensuremath{\langle}',
1087: 'rang' => '\ensuremath{\rangle}',
1088: 9002 => '\ensuremath{\rangle}',
1089: 'loz' => '\ensuremath{\lozenge}',
1090: 9674 => '\ensuremath{\lozenge}',
1091: 'spades' => '\ensuremath{\spadesuit}',
1092: 9824 => '\ensuremath{\spadesuit}',
1093: 9825 => '\ensuremath{\heartsuit}',
1094: 9826 => '\ensuremath{\diamondsuit}',
1095: 'clubs' => '\ensuremath{\clubsuit}',
1096: 9827 => '\ensuremath{\clubsuit}',
1097: 'diams' => '\ensuremath{\blacklozenge}',
1098: 9830 => '\ensuremath{\blacklozenge}'
1099:
1100: );
1101:
1102: =pod
1103:
1104: =item *
1105:
1106: There are some named entities that don't have a good
1107: latex equivalent, these are converted to utf-8 via this table
1108: of entity name -> unicode number.
1109:
1110: =cut
1111:
1112: my %utf_table = (
1113: 'THORN' => 222,
1114: 'thorn' => 254,
1115: 'eth' => 240,
1116: 'hearts' => 9829
1117: );
1118:
1119: sub entity_to_utf8 {
1120: my ($unicode) = @_;
1121: my $result = pack("U", $unicode);
1122: return $result;
1123: }
1124:
1125:
1126:
1127: sub entity_to_latex {
1128: my ($entity) = @_;
1129:
1130: # Try to look up the entity (text or numeric) in the hash:
1131:
1132:
1133:
1134: my $latex = $entities{"$entity"};
1135: if (defined $latex) {
1136: return $latex;
1137: }
1138: # If the text is purely numeric we can do the UTF-8 conversion:
1139: # Otherwise there are a few textual entities that don't have good latex
1140: # which can be converted to unicode:
1141: #
1142: if ($entity =~ /^\d+$/) {
1143: return &entity_to_utf8($entity);
1144: } else {
1145: my $result = $utf_table{"$entity"};
1146: if (defined $result) {
1147: return &entity_to_utf8($result);
1148: }
1149: }
1150: # Can't do the conversion`< ...
1151:
1152: return " ";
1153: }
1154:
1155:
1156: sub replace_entities {
1157: my ($input) = @_;
1158: my $start;
1159: my $end;
1160: my $entity;
1161: my $latex;
1162:
1163: # First the &#nnn; entities:
1164:
1165: while ($input =~ /(&\#\d+;)/) {
1166: ($start) = @-;
1167: ($end) = @+;
1168: $entity = substr($input, $start+2, $end-$start-3);
1169: $latex = &entity_to_latex($entity);
1170: substr($input, $start, $end-$start) = $latex;
1171: }
1172:
1173: # Hexadecimal entities:
1174:
1175: while ($input =~ /&\#x(\d|[a-f,A-f])+;/) {
1176: ($start) = @-;
1177: ($end) = @+;
1178: $entity = "0" . substr($input, $start+2, $end-$start-3); # 0xhexnumber
1179: $latex = &entity_to_latex(hex($entity));
1180: substr($input, $start, $end-$start) = $latex;
1181: }
1182:
1183:
1184: # Now the &text; entites;
1185:
1186: while ($input =~/(&\w+;)/) {
1187: ($start) = @-;
1188: ($end) = @+;
1189: $entity = substr($input, $start+1, $end-$start-2);
1190: $latex = &entity_to_latex($entity);
1191: substr($input, $start, $end-$start) = $latex;
1192:
1193: }
1194: return $input;
1195: }
1196:
1197: 1;
1198:
1199: __END__
1200:
1201: =pod
1202:
1203: =back
1204:
1205: =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