root/trunk/leim/quail/sgml-input.el

Revision 4220, 48.7 kB (checked in by miyoshi, 9 months ago)

Sync up with Emacs22.2.

Line 
1 ;;; sgml-input.el --- Quail method for Unicode entered as SGML entities -*- coding: utf-8 -*-
2
3 ;; Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
4 ;;   Free Software Foundation, Inc.
5
6 ;; Author: Dave Love <fx@gnu.org>
7 ;; Keywords: i18n
8
9 ;; This file is part of GNU Emacs.
10
11 ;; This file is free software; you can redistribute it and/or modify
12 ;; it under the terms of the GNU General Public License as published by
13 ;; the Free Software Foundation; either version 3, or (at your option)
14 ;; any later version.
15
16 ;; This file is distributed in the hope that it will be useful,
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
19 ;; GNU General Public License for more details.
20
21 ;; You should have received a copy of the GNU General Public License
22 ;; along with GNU Emacs; see the file COPYING.  If not, write to
23 ;; the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
24 ;; Boston, MA 02110-1301, USA.
25
26 ;;; Commentary:
27
28 ;; The table was derived from the Unicode consortium file
29 ;; MAPPINGS/VENDORS/MISC/SGML.TXT.
30
31 ;;; Code:
32
33 (require 'quail)
34
35 (quail-define-package
36  "sgml" "UTF-8" "&" t
37  "Unicode characters input method using SGML entities.
38 Entities are covered from the public sets ISOamsa, ISOamsb, ISOamsc,
39 ISOamsn, ISOamso, ISOamsr, ISObox, ISOcyr1, ISOcyr2, ISOdia, ISOgrk1,
40 ISOgrk2, ISOgrk3, ISOgrk4, ISOlat1, ISOlat2, ISOnum, ISOpub, ISOtech,
41 HTMLspecial and HTMLsymbol.
42
43 E.g.: &aacute; -> á"
44  '(("\t" . quail-completion))
45  t nil nil nil nil nil nil nil nil t)
46
47 (quail-define-rules
48   ("&Aacgr;" ?\Ά) ;; GREEK CAPITAL LETTER ALPHA WITH TONOS
49   ("&aacgr;" ?\ά) ;; GREEK SMALL LETTER ALPHA WITH TONOS
50   ("&Aacute;" ?\Á) ;; LATIN CAPITAL LETTER A WITH ACUTE
51   ("&aacute;" ?\á) ;; LATIN SMALL LETTER A WITH ACUTE
52   ("&Abreve;" ?\Ă) ;; LATIN CAPITAL LETTER A WITH BREVE
53   ("&abreve;" ?\ă) ;; LATIN SMALL LETTER A WITH BREVE
54   ("&Acirc;" ?\Â) ;; LATIN CAPITAL LETTER A WITH CIRCUMFLEX
55   ("&acirc;" ?\â) ;; LATIN SMALL LETTER A WITH CIRCUMFLEX
56   ("&acute;" ?\ÂŽ) ;; ACUTE ACCENT
57   ("&Acy;" ?\А) ;; CYRILLIC CAPITAL LETTER A
58   ("&acy;" ?\а) ;; CYRILLIC SMALL LETTER A
59   ("&AElig;" ?\Æ) ;; LATIN CAPITAL LETTER AE
60   ("&aelig;" ?\Ê) ;; LATIN SMALL LETTER AE
61   ("&Agr;" ?\Α) ;; GREEK CAPITAL LETTER ALPHA
62   ("&agr;" ?\α) ;; GREEK SMALL LETTER ALPHA
63   ("&Agrave;" ?\À) ;; LATIN CAPITAL LETTER A WITH GRAVE
64   ("&agrave;" ?\à) ;; LATIN SMALL LETTER A WITH GRAVE
65   ("&alefsym;" ?\ℵ) ;; ALEF SYMBOL
66   ("&aleph;" ?\ℵ) ;; ALEF SYMBOL
67   ("&Alpha;" ?\Α) ;; GREEK CAPITAL LETTER ALPHA
68   ("&alpha;" ?\α) ;; GREEK SMALL LETTER ALPHA
69   ("&Amacr;" ?\Ā) ;; LATIN CAPITAL LETTER A WITH MACRON
70   ("&amacr;" ?\ā) ;; LATIN SMALL LETTER A WITH MACRON
71   ("&amalg;" ?\∐) ;; N-ARY COPRODUCT
72   ("&amp;" ?\&) ;; AMPERSAND
73   ("&and;" ?\∧) ;; LOGICAL AND
74   ("&ang;" ?\∠) ;; ANGLE
75   ("&ang90;" ?\∟) ;; RIGHT ANGLE
76   ("&angmsd;" ?\∡) ;; MEASURED ANGLE
77   ("&angsph;" ?\∢) ;; SPHERICAL ANGLE
78   ("&angst;" ?\Å) ;; ANGSTROM SIGN
79   ("&Aogon;" ?\Ą) ;; LATIN CAPITAL LETTER A WITH OGONEK
80   ("&aogon;" ?\Ä
81 ) ;; LATIN SMALL LETTER A WITH OGONEK
82   ("&ap;" ?\≈) ;; ALMOST EQUAL TO
83   ("&ape;" ?\≊) ;; ALMOST EQUAL OR EQUAL TO
84   ("&apos;" ?\ÊŒ) ;; MODIFIER LETTER APOSTROPHE
85   ("&Aring;" ?\Ã
86 ) ;; LATIN CAPITAL LETTER A WITH RING ABOVE
87   ("&aring;" ?\Ã¥) ;; LATIN SMALL LETTER A WITH RING ABOVE
88   ("&ast;" ?\*) ;; ASTERISK
89   ("&asymp;" ?\≈) ;; ALMOST EQUAL TO
90   ("&Atilde;" ?\Ã) ;; LATIN CAPITAL LETTER A WITH TILDE
91   ("&atilde;" ?\ã) ;; LATIN SMALL LETTER A WITH TILDE
92   ("&Auml;" ?\Ä) ;; LATIN CAPITAL LETTER A WITH DIAERESIS
93   ("&auml;" ?\À) ;; LATIN SMALL LETTER A WITH DIAERESIS
94   ("&b.alpha;" ?\α) ;; GREEK SMALL LETTER ALPHA
95   ("&barwed;" ?\⊌) ;; NAND
96   ("&Barwed;" ?\⌆) ;; PERSPECTIVE
97   ("&b.beta;" ?\β) ;; GREEK SMALL LETTER BETA
98   ("&bchi;" ?\χ) ;; GREEK SMALL LETTER CHI
99   ("&bcong;" ?\≌) ;; ALL EQUAL TO
100   ("&Bcy;" ?\Б) ;; CYRILLIC CAPITAL LETTER BE
101   ("&bcy;" ?\б) ;; CYRILLIC SMALL LETTER BE
102   ("&b.Delta;" ?\Δ) ;; GREEK CAPITAL LETTER DELTA
103   ("&b.delta;" ?\γ) ;; GREEK SMALL LETTER GAMMA
104   ("&bdquo;" ?\„) ;; DOUBLE LOW-9 QUOTATION MARK
105   ("&becaus;" ?\∵) ;; BECAUSE
106   ("&bepsi;" ?\∍) ;; SMALL CONTAINS AS MEMBER
107   ("&b.epsi;" ?\ε) ;; GREEK SMALL LETTER EPSILON
108   ("&b.epsis;" ?\ε) ;; GREEK SMALL LETTER EPSILON
109   ("&b.epsiv;" ?\ε) ;; GREEK SMALL LETTER EPSILON
110   ("&bernou;" ?\ℬ) ;; SCRIPT CAPITAL B
111   ("&Beta;" ?\Β) ;; GREEK CAPITAL LETTER BETA
112   ("&beta;" ?\β) ;; GREEK SMALL LETTER BETA
113   ("&b.eta;" ?\η) ;; GREEK SMALL LETTER ETA
114   ("&beth;" ?\ℶ) ;; BET SYMBOL
115   ("&b.Gamma;" ?\Γ) ;; GREEK CAPITAL LETTER GAMMA
116   ("&b.gamma;" ?\γ) ;; GREEK SMALL LETTER GAMMA
117   ("&b.gammagrk4;" ?\Ϝ) ;; GREEK LETTER DIGAMMA
118   ("&Bgr;" ?\Β) ;; GREEK CAPITAL LETTER BETA
119   ("&bgr;" ?\β) ;; GREEK SMALL LETTER BETA
120   ("&b.iota;" ?\ι) ;; GREEK SMALL LETTER IOTA
121   ("&b.kappa;" ?\κ) ;; GREEK SMALL LETTER KAPPA
122   ("&b.kappagrk4;" ?\ϰ) ;; GREEK KAPPA SYMBOL
123   ("&b.Lambdgrk4;" ?\Λ) ;; GREEK CAPITAL LETTER LAMDA
124   ("&b.lambdgrk4;" ?\λ) ;; GREEK SMALL LETTER LAMDA
125   ("&blank;" ?\␣) ;; OPEN BOX
126   ("&blk12;" ?\▒) ;; MEDIUM SHADE
127   ("&blk14;" ?\░) ;; LIGHT SHADE
128   ("&blk34;" ?\▓) ;; DARK SHADE
129   ("&block;" ?\█) ;; FULL BLOCK
130   ("&b.mu;" ?\ÎŒ) ;; GREEK SMALL LETTER MU
131   ("&b.nu;" ?\Μ) ;; GREEK SMALL LETTER NU
132   ("&b.Omega;" ?\Ω) ;; GREEK CAPITAL LETTER OMEGA
133   ("&b.omega;" ?\ώ) ;; GREEK SMALL LETTER OMEGA WITH TONOS
134   ("&bottom;" ?\⊥) ;; UP TACK
135   ("&bowtie;" ?\⋈) ;; BOWTIE
136   ("&boxdl;" ?\┐) ;; BOX DRAWINGS LIGHT DOWN AND LEFT
137   ("&boxdL;" ?\╕) ;; BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
138   ("&boxDl;" ?\╖) ;; BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
139   ("&boxDL;" ?\╗) ;; BOX DRAWINGS DOUBLE DOWN AND LEFT
140   ("&boxdr;" ?\┌) ;; BOX DRAWINGS LIGHT DOWN AND RIGHT
141   ("&boxdR;" ?\╒) ;; BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
142   ("&boxDr;" ?\╓) ;; BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
143   ("&boxDR;" ?\╔) ;; BOX DRAWINGS DOUBLE DOWN AND RIGHT
144   ("&boxh;" ?\─) ;; BOX DRAWINGS LIGHT HORIZONTAL
145   ("&boxH;" ?\═) ;; BOX DRAWINGS DOUBLE HORIZONTAL
146   ("&boxhd;" ?\┬) ;; BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
147   ("&boxHd;" ?\â•€) ;; BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
148   ("&boxhD;" ?\╥) ;; BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
149   ("&boxHD;" ?\╩) ;; BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
150   ("&boxhu;" ?\┮) ;; BOX DRAWINGS LIGHT UP AND HORIZONTAL
151   ("&boxHu;" ?\╧) ;; BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
152   ("&boxhU;" ?\╹) ;; BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
153   ("&boxHU;" ?\╩) ;; BOX DRAWINGS DOUBLE UP AND HORIZONTAL
154   ("&boxul;" ?\┘) ;; BOX DRAWINGS LIGHT UP AND LEFT
155   ("&boxuL;" ?\╛) ;; BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
156   ("&boxUl;" ?\╜) ;; BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
157   ("&boxUL;" ?\╝) ;; BOX DRAWINGS DOUBLE UP AND LEFT
158   ("&boxur;" ?\└) ;; BOX DRAWINGS LIGHT UP AND RIGHT
159   ("&boxuR;" ?\╘) ;; BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
160   ("&boxUr;" ?\╙) ;; BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
161   ("&boxUR;" ?\╚) ;; BOX DRAWINGS DOUBLE UP AND RIGHT
162   ("&boxv;" ?\│) ;; BOX DRAWINGS LIGHT VERTICAL
163   ("&boxV;" ?\║) ;; BOX DRAWINGS DOUBLE VERTICAL
164   ("&boxvh;" ?\┌) ;; BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
165   ("&boxvH;" ?\╪) ;; BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
166   ("&boxVh;" ?\╫) ;; BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
167   ("&boxVH;" ?\╬) ;; BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
168   ("&boxvl;" ?\─) ;; BOX DRAWINGS LIGHT VERTICAL AND LEFT
169   ("&boxvL;" ?\╡) ;; BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
170   ("&boxVl;" ?\╢) ;; BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
171   ("&boxVL;" ?\╣) ;; BOX DRAWINGS DOUBLE VERTICAL AND LEFT
172   ("&boxvr;" ?\├) ;; BOX DRAWINGS LIGHT VERTICAL AND RIGHT
173   ("&boxvR;" ?\╞) ;; BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
174   ("&boxVr;" ?\╟) ;; BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
175   ("&boxVR;" ?\╠) ;; BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
176   ("&b.Phi;" ?\Ί) ;; GREEK CAPITAL LETTER PHI
177   ("&b.phis;" ?\φ) ;; GREEK SMALL LETTER PHI
178   ("&b.phiv;" ?\ϕ) ;; GREEK PHI SYMBOL
179   ("&b.Pi;" ?\Π) ;; GREEK CAPITAL LETTER PI
180   ("&b.pi;" ?\π) ;; GREEK SMALL LETTER PI
181   ("&b.piv;" ?\ϖ) ;; GREEK PI SYMBOL
182   ("&bprime;" ?\‵) ;; REVERSED PRIME
183   ("&b.Psi;" ?\Κ) ;; GREEK CAPITAL LETTER PSI
184   ("&b.psi;" ?\ψ) ;; GREEK SMALL LETTER PSI
185   ("&breve;" ?\˘) ;; BREVE
186   ("&b.rho;" ?\ρ) ;; GREEK SMALL LETTER RHO
187   ("&b.rhov;" ?\ϱ) ;; GREEK RHO SYMBOL
188   ("&brvbar;" ?\Š) ;; BROKEN BAR
189   ("&b.Sigma;" ?\Σ) ;; GREEK CAPITAL LETTER SIGMA
190   ("&b.sigma;" ?\σ) ;; GREEK SMALL LETTER SIGMA
191   ("&b.sigmagrk4;" ?\ς) ;; GREEK SMALL LETTER FINAL SIGMA
192   ("&bsim;" ?\∜) ;; REVERSED TILDE
193   ("&bsime;" ?\⋍) ;; REVERSED TILDE EQUALS
194   ("&bsol;" ?\\) ;; REVERSE SOLIDUS
195   ("&b.tau;" ?\τ) ;; GREEK SMALL LETTER TAU
196   ("&b.Theta;" ?\Θ) ;; GREEK CAPITAL LETTER THETA
197   ("&b.thetagrk4;" ?\Ξ) ;; GREEK SMALL LETTER THETA
198   ("&b.thetagrk4;" ?\ϑ) ;; GREEK THETA SYMBOL
199   ("&bull;" ?\•) ;; BULLET
200   ("&bump;" ?\≎) ;; GEOMETRICALLY EQUIVALENT TO
201   ("&bumpe;" ?\≏) ;; DIFFERENCE BETWEEN
202   ("&b.Upsi;" ?\Î¥) ;; GREEK CAPITAL LETTER UPSILON
203   ("&b.upsi;" ?\Ï
204 ) ;; GREEK SMALL LETTER UPSILON
205   ("&b.Xi;" ?\Ξ) ;; GREEK CAPITAL LETTER XI
206   ("&b.xi;" ?\Ο) ;; GREEK SMALL LETTER XI
207   ("&b.zeta;" ?\ζ) ;; GREEK SMALL LETTER ZETA
208   ("&Cacute;" ?\Ć) ;; LATIN CAPITAL LETTER C WITH ACUTE
209   ("&cacute;" ?\ć) ;; LATIN SMALL LETTER C WITH ACUTE
210   ("&Cap;" ?\⋒) ;; DOUBLE INTERSECTION
211   ("&cap;" ?\∩) ;; INTERSECTION
212   ("&caret;" ?\⁁) ;; CARET INSERTION POINT
213   ("&caron;" ?\ˇ) ;; CARON
214   ("&Ccaron;" ?\Č) ;; LATIN CAPITAL LETTER C WITH CARON
215   ("&ccaron;" ?\č) ;; LATIN SMALL LETTER C WITH CARON
216   ("&Ccedil;" ?\Ç) ;; LATIN CAPITAL LETTER C WITH CEDILLA
217   ("&ccedil;" ?\ç) ;; LATIN SMALL LETTER C WITH CEDILLA
218   ("&Ccirc;" ?\Ĉ) ;; LATIN CAPITAL LETTER C WITH CIRCUMFLEX
219   ("&ccirc;" ?\ĉ) ;; LATIN SMALL LETTER C WITH CIRCUMFLEX
220   ("&Cdot;" ?\Ċ) ;; LATIN CAPITAL LETTER C WITH DOT ABOVE
221   ("&cdot;" ?\ċ) ;; LATIN SMALL LETTER C WITH DOT ABOVE
222   ("&cedil;" ?\ž) ;; CEDILLA
223   ("&cent;" ?\¢) ;; CENT SIGN
224   ("&CHcy;" ?\Ч) ;; CYRILLIC CAPITAL LETTER CHE
225   ("&chcy;" ?\ч)  ;; CYRILLIC SMALL LETTER CHE
226   ("&check;" ?\✓) ;; CHECK MARK
227   ("&Chi;" ?\Χ) ;; GREEK CAPITAL LETTER CHI
228   ("&chi;" ?\χ) ;; GREEK SMALL LETTER CHI
229   ("&cir;" ?\○) ;; WHITE CIRCLE
230   ("&circ;" ?\ˆ) ;; MODIFIER LETTER CIRCUMFLEX ACCENT
231   ("&cire;" ?\≗) ;; RING EQUAL TO
232   ("&clubs;" ?\♣) ;; BLACK CLUB SUIT
233   ("&colon;" ?\:) ;; COLON
234   ("&colone;" ?\≔) ;; COLON EQUALS
235   ("&comma;" ?\,) ;; COMMA
236   ("&commat;" ?\@) ;; COMMERCIAL AT
237   ("&comp;" ?\∁) ;; COMPLEMENT
238   ("&compfn;" ?\∘) ;; RING OPERATOR
239   ("&cong;" ?\â‰
240 ) ;; APPROXIMATELY EQUAL TO
241   ("&conint;" ?\∮) ;; CONTOUR INTEGRAL
242   ("&coprod;" ?\∐) ;; N-ARY COPRODUCT
243   ("&copy;" ?\©) ;; COPYRIGHT SIGN
244   ("&copysr;" ?\℗) ;; SOUND RECORDING COPYRIGHT
245   ("&crarr;" ?\↵) ;; DOWNWARDS ARROW WITH CORNER LEFTWARDS
246   ("&cross;" ?\✗) ;; BALLOT X
247   ("&cuepr;" ?\⋞) ;; EQUAL TO OR PRECEDES
248   ("&cuesc;" ?\⋟) ;; EQUAL TO OR SUCCEEDS
249   ("&cularr;" ?\↶) ;; ANTICLOCKWISE TOP SEMICIRCLE ARROW
250   ("&Cup;" ?\⋓) ;; DOUBLE UNION
251   ("&cup;" ?\∪) ;; UNION
252   ("&cupre;" ?\≌) ;; PRECEDES OR EQUAL TO
253   ("&curarr;" ?\↷) ;; CLOCKWISE TOP SEMICIRCLE ARROW
254   ("&curren;" ?\€) ;; CURRENCY SIGN
255   ("&cuvee;" ?\⋎) ;; CURLY LOGICAL OR
256   ("&cuwed;" ?\⋏) ;; CURLY LOGICAL AND
257   ("&dagger;" ?\†) ;; DAGGER
258   ("&Dagger;" ?\‡) ;; DOUBLE DAGGER
259   ("&daleth;" ?\ℾ) ;; DALET SYMBOL
260   ("&dArr;" ?\⇓) ;; DOWNWARDS DOUBLE ARROW
261   ("&darr;" ?\↓) ;; DOWNWARDS ARROW
262   ("&darr2;" ?\⇊) ;; DOWNWARDS PAIRED ARROWS
263   ("&dash;" ?\‐) ;; HYPHEN
264   ("&dashv;" ?\⊣) ;; LEFT TACK
265   ("&dblac;" ?\˝) ;; DOUBLE ACUTE ACCENT
266   ("&Dcaron;" ?\Ď) ;; LATIN CAPITAL LETTER D WITH CARON
267   ("&dcaron;" ?\ď) ;; LATIN SMALL LETTER D WITH CARON
268   ("&Dcy;" ?\Д) ;; CYRILLIC CAPITAL LETTER DE
269   ("&dcy;" ?\ÐŽ) ;; CYRILLIC SMALL LETTER DE
270   ("&deg;" ?\°) ;; DEGREE SIGN
271   ("&Delta;" ?\Δ) ;; GREEK CAPITAL LETTER DELTA
272   ("&delta;" ?\ÎŽ) ;; GREEK SMALL LETTER DELTA
273   ("&Dgr;" ?\Δ) ;; GREEK CAPITAL LETTER DELTA
274   ("&dgr;" ?\ÎŽ) ;; GREEK SMALL LETTER DELTA
275   ("&dharl;" ?\⇃) ;; DOWNWARDS HARPOON WITH BARB LEFTWARDS
276   ("&dharr;" ?\⇂) ;; DOWNWARDS HARPOON WITH BARB RIGHTWARDS
277   ("&diam;" ?\⋄) ;; DIAMOND OPERATOR
278   ("&diams;" ?\♩) ;; BLACK DIAMOND SUIT
279   ("&die;" ?\š) ;; DIAERESIS
280   ("&divide;" ?\÷) ;; DIVISION SIGN
281   ("&divonx;" ?\⋇) ;; DIVISION TIMES
282   ("&DJcy;" ?\Ђ) ;; CYRILLIC CAPITAL LETTER DJE
283   ("&djcy;" ?\ђ) ;; CYRILLIC SMALL LETTER DJE
284   ("&dlarr;" ?\↙) ;; SOUTH WEST ARROW
285   ("&dlcorn;" ?\⌞) ;; BOTTOM LEFT CORNER
286   ("&dlcrop;" ?\⌍) ;; BOTTOM LEFT CROP
287   ("&dollar;" ?\$) ;; DOLLAR SIGN
288   ("&dot;" ?\˙) ;; DOT ABOVE
289   ("&Dot;" ?\š) ;; DIAERESIS
290   ("&DotDot;" ?\⃜) ;; COMBINING FOUR DOTS ABOVE
291   ("&drarr;" ?\↘) ;; SOUTH EAST ARROW
292   ("&drcorn;" ?\⌟) ;; BOTTOM RIGHT CORNER
293   ("&drcrop;" ?\⌌) ;; BOTTOM RIGHT CROP
294   ("&DScy;" ?\Ð
295 ) ;; CYRILLIC CAPITAL LETTER DZE
296   ("&dscy;" ?\ѕ) ;; CYRILLIC SMALL LETTER DZE
297   ("&Dstrok;" ?\Đ) ;; LATIN CAPITAL LETTER D WITH STROKE
298   ("&dstrok;" ?\đ) ;; LATIN SMALL LETTER D WITH STROKE
299   ("&dtri;" ?\▿) ;; WHITE DOWN-POINTING SMALL TRIANGLE
300   ("&dtrif;" ?\â–Ÿ) ;; BLACK DOWN-POINTING SMALL TRIANGLE
301   ("&DZcy;" ?\Џ) ;; CYRILLIC CAPITAL LETTER DZHE
302   ("&dzcy;" ?\џ) ;; CYRILLIC SMALL LETTER DZHE
303   ("&Eacgr;" ?\Έ) ;; GREEK CAPITAL LETTER EPSILON WITH TONOS
304   ("&eacgr;" ?\έ) ;; GREEK SMALL LETTER EPSILON WITH TONOS
305   ("&Eacute;" ?\É) ;; LATIN CAPITAL LETTER E WITH ACUTE
306   ("&eacute;" ?\é) ;; LATIN SMALL LETTER E WITH ACUTE
307   ("&Ecaron;" ?\Ě) ;; LATIN CAPITAL LETTER E WITH CARON
308   ("&ecaron;" ?\ě) ;; LATIN SMALL LETTER E WITH CARON
309   ("&ecir;" ?\≖) ;; RING IN EQUAL TO
310   ("&Ecirc;" ?\Ê) ;; LATIN CAPITAL LETTER E WITH CIRCUMFLEX
311   ("&ecirc;" ?\ê) ;; LATIN SMALL LETTER E WITH CIRCUMFLEX
312   ("&ecolon;" ?\≕) ;; EQUALS COLON
313   ("&Ecy;" ?\Э) ;; CYRILLIC CAPITAL LETTER E
314   ("&ecy;" ?\э) ;; CYRILLIC SMALL LETTER E
315   ("&eDot;" ?\≑) ;; GEOMETRICALLY EQUAL TO
316   ("&Edot;" ?\Ė) ;; LATIN CAPITAL LETTER E WITH DOT ABOVE
317   ("&edot;" ?\ė) ;; LATIN SMALL LETTER E WITH DOT ABOVE
318   ("&EEacgr;" ?\Ή) ;; GREEK CAPITAL LETTER ETA WITH TONOS
319   ("&eeacgr;" ?\ή) ;; GREEK SMALL LETTER ETA WITH TONOS
320   ("&EEgr;" ?\Η) ;; GREEK CAPITAL LETTER ETA
321   ("&eegr;" ?\η) ;; GREEK SMALL LETTER ETA
322   ("&efDot;" ?\≒) ;; APPROXIMATELY EQUAL TO OR THE IMAGE OF
323   ("&Egr;" ?\Ε) ;; GREEK CAPITAL LETTER EPSILON
324   ("&egr;" ?\ε) ;; GREEK SMALL LETTER EPSILON
325   ("&Egrave;" ?\È) ;; LATIN CAPITAL LETTER E WITH GRAVE
326   ("&egrave;" ?\Ú) ;; LATIN SMALL LETTER E WITH GRAVE
327   ("&egs;" ?\⋝) ;; EQUAL TO OR GREATER-THAN
328   ("&ell;" ?\ℓ) ;; SCRIPT SMALL L
329   ("&els;" ?\⋜) ;; EQUAL TO OR LESS-THAN
330   ("&Emacr;" ?\Ē) ;; LATIN CAPITAL LETTER E WITH MACRON
331   ("&emacr;" ?\ē) ;; LATIN SMALL LETTER E WITH MACRON
332   ("&empty;" ?\âˆ
333 ) ;; EMPTY SET
334   ("&emsp;" ?\ ) ;; EM SPACE
335   ("&emsp13;" ?\ ) ;; THREE-PER-EM SPACE
336   ("&emsp14;" ?\â€
337 ) ;; FOUR-PER-EM SPACE
338   ("&ENG;" ?\Ŋ) ;; LATIN CAPITAL LETTER ENG
339   ("&eng;" ?\ŋ) ;; LATIN SMALL LETTER ENG
340   ("&ensp;" ?\ ) ;; EN SPACE
341   ("&Eogon;" ?\Ę) ;; LATIN CAPITAL LETTER E WITH OGONEK
342   ("&eogon;" ?\ę) ;; LATIN SMALL LETTER E WITH OGONEK
343   ("&epsi;" ?\ε) ;; GREEK SMALL LETTER EPSILON
344   ("&Epsilon;" ?\Ε) ;; GREEK CAPITAL LETTER EPSILON
345   ("&epsilon;" ?\ε) ;; GREEK SMALL LETTER EPSILON
346   ("&epsis;" ?\∊) ;; SMALL ELEMENT OF
347 ;;;  ("&epsiv;" ?\x????) ;; variant epsilon
348   ("&equals;" ?\=) ;; EQUALS SIGN
349   ("&equiv;" ?\≡) ;; IDENTICAL TO
350   ("&erDot;" ?\≓) ;; IMAGE OF OR APPROXIMATELY EQUAL TO
351   ("&esdot;" ?\≐) ;; APPROACHES THE LIMIT
352   ("&Eta;" ?\Η) ;; GREEK CAPITAL LETTER ETA
353   ("&eta;" ?\η) ;; GREEK SMALL LETTER ETA
354   ("&ETH;" ?\Ð) ;; LATIN CAPITAL LETTER ETH
355   ("&eth;" ?\ð) ;; LATIN SMALL LETTER ETH
356   ("&Euml;" ?\Ë) ;; LATIN CAPITAL LETTER E WITH DIAERESIS
357   ("&euml;" ?\ë) ;; LATIN SMALL LETTER E WITH DIAERESIS
358   ("&excl;" ?\!) ;; EXCLAMATION MARK
359   ("&exist;" ?\∃) ;; THERE EXISTS
360   ("&Fcy;" ?\Ѐ) ;; CYRILLIC CAPITAL LETTER EF
361   ("&fcy;" ?\ф) ;; CYRILLIC SMALL LETTER EF
362   ("&female;" ?\♀) ;; FEMALE SIGN
363   ("&ffilig;" ?\ffi) ;; LATIN SMALL LIGATURE FFI
364   ("&fflig;" ?\ff) ;; LATIN SMALL LIGATURE FF
365   ("&ffllig;" ?\ffl) ;; LATIN SMALL LIGATURE FFL
366   ("&filig;" ?\fi) ;; LATIN SMALL LIGATURE FI
367 ;;  ("&fjlig;" ?\x????) ;; fj ligature
368   ("&flat;" ?\♭) ;; MUSIC FLAT SIGN
369   ("&fllig;" ?\fl) ;; LATIN SMALL LIGATURE FL
370   ("&fnof;" ?\ƒ) ;; LATIN SMALL LETTER F WITH HOOK
371   ("&forall;" ?\∀) ;; FOR ALL
372   ("&fork;" ?\⋔) ;; PITCHFORK
373   ("&frac12;" ?\œ) ;; VULGAR FRACTION ONE HALF
374   ("&frac13;" ?\â
375 “) ;; VULGAR FRACTION ONE THIRD
376   ("&frac14;" ?\ÂŒ) ;; VULGAR FRACTION ONE QUARTER
377   ("&frac15;" ?\â
378 •) ;; VULGAR FRACTION ONE FIFTH
379   ("&frac16;" ?\â
380 ™) ;; VULGAR FRACTION ONE SIXTH
381   ("&frac18;" ?\â
382 ›) ;; VULGAR FRACTION ONE EIGHTH
383   ("&frac23;" ?\â
384 ”) ;; VULGAR FRACTION TWO THIRDS
385   ("&frac25;" ?\â
386 –) ;; VULGAR FRACTION TWO FIFTHS
387   ("&frac34;" ?\Ÿ) ;; VULGAR FRACTION THREE QUARTERS
388   ("&frac35;" ?\â
389 —) ;; VULGAR FRACTION THREE FIFTHS
390   ("&frac38;" ?\â
391 œ) ;; VULGAR FRACTION THREE EIGHTHS
392   ("&frac45;" ?\â
393 ˜) ;; VULGAR FRACTION FOUR FIFTHS
394   ("&frac56;" ?\â
395 š) ;; VULGAR FRACTION FIVE SIXTHS
396   ("&frac58;" ?\â
397 ) ;; VULGAR FRACTION FIVE EIGHTHS
398   ("&frac78;" ?\â
399 ž) ;; VULGAR FRACTION SEVEN EIGHTHS
400   ("&frasl;" ?\⁄) ;; FRACTION SLASH
401   ("&frown;" ?\⌢) ;; FROWN
402   ("&gacute;" ?\ǵ) ;; LATIN SMALL LETTER G WITH ACUTE
403   ("&Gamma;" ?\Γ) ;; GREEK CAPITAL LETTER GAMMA
404   ("&gamma;" ?\γ) ;; GREEK SMALL LETTER GAMMA
405   ("&gammad;" ?\Ϝ) ;; GREEK LETTER DIGAMMA
406 ;;;  ("&gap;" 0x????) ;; greater-than, approximately equal to
407   ("&Gbreve;" ?\Ğ) ;; LATIN CAPITAL LETTER G WITH BREVE
408   ("&gbreve;" ?\ğ) ;; LATIN SMALL LETTER G WITH BREVE
409   ("&Gcedil;" ?\Ä¢) ;; LATIN CAPITAL LETTER G WITH CEDILLA
410   ("&gcedil;" ?\Ä£) ;; LATIN SMALL LETTER G WITH CEDILLA
411   ("&Gcirc;" ?\Ĝ) ;; LATIN CAPITAL LETTER G WITH CIRCUMFLEX
412   ("&gcirc;" ?\ĝ) ;; LATIN SMALL LETTER G WITH CIRCUMFLEX
413   ("&Gcy;" ?\Г) ;; CYRILLIC CAPITAL LETTER GHE
414   ("&gcy;" ?\г) ;; CYRILLIC SMALL LETTER GHE
415   ("&Gdot;" ?\Ä ) ;; LATIN CAPITAL LETTER G WITH DOT ABOVE
416   ("&gdot;" ?\Ä¡) ;; LATIN SMALL LETTER G WITH DOT ABOVE
417   ("&gE;" ?\≧) ;; GREATER-THAN OVER EQUAL TO
418   ("&ge;" ?\≥) ;; GREATER-THAN OR EQUAL TO
419 ;;;  ("&gEl;" ?\x????) ;; greater-than, double equals, less-than
420   ("&gel;" ?\⋛) ;; GREATER-THAN EQUAL TO OR LESS-THAN
421   ("&ges;" ?\≥) ;; GREATER-THAN OR EQUAL TO
422   ("&Gg;" ?\⋙) ;; VERY MUCH GREATER-THAN
423   ("&Ggr;" ?\Γ) ;; GREEK CAPITAL LETTER GAMMA
424   ("&ggr;" ?\γ) ;; GREEK SMALL LETTER GAMMA
425   ("&gimel;" ?\ℷ) ;; GIMEL SYMBOL
426   ("&GJcy;" ?\Ѓ) ;; CYRILLIC CAPITAL LETTER GJE
427   ("&gjcy;" ?\ѓ) ;; CYRILLIC SMALL LETTER GJE
428   ("&gl;" ?\≷) ;; GREATER-THAN OR LESS-THAN
429 ;;;  ("&gnap;" ?\x????) ;; greater-than, not approximately equal to
430   ("&gne;" ?\≩) ;; GREATER-THAN BUT NOT EQUAL TO
431   ("&gnE;" ?\≩) ;; GREATER-THAN BUT NOT EQUAL TO
432   ("&gnsim;" ?\⋧) ;; GREATER-THAN BUT NOT EQUIVALENT TO
433   ("&grave;" ?\`) ;; GRAVE ACCENT
434   ("&gsdot;" ?\⋗) ;; GREATER-THAN WITH DOT
435   ("&gsim;" ?\≳) ;; GREATER-THAN OR EQUIVALENT TO
436   ("&Gt;" ?\≫) ;; MUCH GREATER-THAN
437   ("&gt;" ?\>) ;; GREATER-THAN SIGN
438   ("&gvnE;" ?\≩) ;; GREATER-THAN BUT NOT EQUAL TO
439   ("&hairsp;" ?\ ) ;; HAIR SPACE
440   ("&half;" ?\œ) ;; VULGAR FRACTION ONE HALF
441   ("&hamilt;" ?\ℋ) ;; SCRIPT CAPITAL H
442   ("&HARDcy;" ?\Ъ) ;; CYRILLIC CAPITAL LETTER HARD SIGN
443   ("&hardcy;" ?\ъ) ;; CYRILLIC SMALL LETTER HARD SIGN
444   ("&harr;" ?\↔) ;; LEFT RIGHT ARROW
445   ("&hArr;" ?\⇔) ;; LEFT RIGHT DOUBLE ARROW
446   ("&harrw;" ?\↭) ;; LEFT RIGHT WAVE ARROW
447   ("&Hcirc;" ?\Ä€) ;; LATIN CAPITAL LETTER H WITH CIRCUMFLEX
448   ("&hcirc;" ?\Ä¥) ;; LATIN SMALL LETTER H WITH CIRCUMFLEX
449   ("&hearts;" ?\♥) ;; BLACK HEART SUIT
450   ("&hellip;" ?\
) ;; HORIZONTAL ELLIPSIS
451   ("&horbar;" ?\―) ;; HORIZONTAL BAR
452   ("&Hstrok;" ?\ÄŠ) ;; LATIN CAPITAL LETTER H WITH STROKE
453   ("&hstrok;" ?\ħ) ;; LATIN SMALL LETTER H WITH STROKE
454   ("&hybull;" ?\⁃) ;; HYPHEN BULLET
455   ("&hyphen;" ?\-) ;; HYPHEN-MINUS
456   ("&Iacgr;" ?\Ί) ;; GREEK CAPITAL LETTER IOTA WITH TONOS
457   ("&iacgr;" ?\ί) ;; GREEK SMALL LETTER IOTA WITH TONOS
458   ("&Iacute;" ?\Í) ;; LATIN CAPITAL LETTER I WITH ACUTE
459   ("&iacute;" ?\í) ;; LATIN SMALL LETTER I WITH ACUTE
460   ("&Icirc;" ?\Î) ;; LATIN CAPITAL LETTER I WITH CIRCUMFLEX
461   ("&icirc;" ?\î) ;; LATIN SMALL LETTER I WITH CIRCUMFLEX
462   ("&Icy;" ?\И) ;; CYRILLIC CAPITAL LETTER I
463   ("&icy;" ?\О) ;; CYRILLIC SMALL LETTER I
464   ("&idiagr;" ?\ΐ) ;; GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
465   ("&Idigr;" ?\Ϊ) ;; GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
466   ("&idigr;" ?\ϊ) ;; GREEK SMALL LETTER IOTA WITH DIALYTIKA
467   ("&Idot;" ?\İ) ;; LATIN CAPITAL LETTER I WITH DOT ABOVE
468   ("&IEcy;" ?\Е) ;; CYRILLIC CAPITAL LETTER IE
469   ("&iecy;" ?\е) ;; CYRILLIC SMALL LETTER IE
470   ("&iexcl;" ?\¡) ;; INVERTED EXCLAMATION MARK
471   ("&iff;" ?\⇔) ;; LEFT RIGHT DOUBLE ARROW
472   ("&Igr;" ?\Ι) ;; GREEK CAPITAL LETTER IOTA
473   ("&igr;" ?\ι) ;; GREEK SMALL LETTER IOTA
474   ("&Igrave;" ?\Ì) ;; LATIN CAPITAL LETTER I WITH GRAVE
475   ("&igrave;" ?\ì) ;; LATIN SMALL LETTER I WITH GRAVE
476   ("&IJlig;" ?\IJ) ;; LATIN CAPITAL LIGATURE IJ
477   ("&ijlig;" ?\ij) ;; LATIN SMALL LIGATURE IJ
478   ("&Imacr;" ?\Ī) ;; LATIN CAPITAL LETTER I WITH MACRON
479   ("&imacr;" ?\Ä«) ;; LATIN SMALL LETTER I WITH MACRON
480   ("&image;" ?\ℑ) ;; BLACK-LETTER CAPITAL I
481   ("&incare;" ?\â„
482 ) ;; CARE OF
483   ("&infin;" ?\∞) ;; INFINITY
484   ("&inodot;" ?\ı) ;; LATIN SMALL LETTER DOTLESS I
485   ("&inodot;" ?\ı) ;; LATIN SMALL LETTER DOTLESS I
486   ("&int;" ?\∫) ;; INTEGRAL
487   ("&intcal;" ?\⊺) ;; INTERCALATE
488   ("&IOcy;" ?\Ё) ;; CYRILLIC CAPITAL LETTER IO
489   ("&iocy;" ?\ё) ;; CYRILLIC SMALL LETTER IO
490   ("&Iogon;" ?\Ä®) ;; LATIN CAPITAL LETTER I WITH OGONEK
491   ("&iogon;" ?\į) ;; LATIN SMALL LETTER I WITH OGONEK
492   ("&Iota;" ?\Ι) ;; GREEK CAPITAL LETTER IOTA
493   ("&iota;" ?\ι) ;; GREEK SMALL LETTER IOTA
494   ("&iquest;" ?\¿) ;; INVERTED QUESTION MARK
495   ("&isin;" ?\∈) ;; ELEMENT OF
496   ("&Itilde;" ?\Äš) ;; LATIN CAPITAL LETTER I WITH TILDE
497   ("&itilde;" ?\Ä©) ;; LATIN SMALL LETTER I WITH TILDE
498   ("&Iukcy;" ?\І) ;; CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
499   ("&iukcy;" ?\і) ;; CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
500   ("&Iuml;" ?\Ï) ;; LATIN CAPITAL LETTER I WITH DIAERESIS
501   ("&iuml;" ?\ï) ;; LATIN SMALL LETTER I WITH DIAERESIS
502   ("&Jcirc;" ?\ÄŽ) ;; LATIN CAPITAL LETTER J WITH CIRCUMFLEX
503   ("&jcirc;" ?\ĵ) ;; LATIN SMALL LETTER J WITH CIRCUMFLEX
504   ("&Jcy;" ?\Й) ;; CYRILLIC CAPITAL LETTER SHORT I
505   ("&jcy;" ?\й) ;; CYRILLIC SMALL LETTER SHORT I
506 ;;;  ("&jnodot;" ?\x????) ;; latin small letter dotless j
507   ("&Jsercy;" ?\Ј) ;; CYRILLIC CAPITAL LETTER JE
508   ("&jsercy;" ?\ј) ;; CYRILLIC SMALL LETTER JE
509   ("&Jukcy;" ?\Є) ;; CYRILLIC CAPITAL LETTER UKRAINIAN IE
510   ("&jukcy;" ?\є) ;; CYRILLIC SMALL LETTER UKRAINIAN IE
511   ("&Kappa;" ?\Κ) ;; GREEK CAPITAL LETTER KAPPA
512   ("&kappa;" ?\κ) ;; GREEK SMALL LETTER KAPPA
513   ("&kappav;" ?\ϰ) ;; GREEK KAPPA SYMBOL
514   ("&Kcedil;" ?\Ķ) ;; LATIN CAPITAL LETTER K WITH CEDILLA
515   ("&kcedil;" ?\Ä·) ;; LATIN SMALL LETTER K WITH CEDILLA
516   ("&Kcy;" ?\К) ;; CYRILLIC CAPITAL LETTER KA
517   ("&kcy;" ?\к) ;; CYRILLIC SMALL LETTER KA
518   ("&Kgr;" ?\Κ) ;; GREEK CAPITAL LETTER KAPPA
519   ("&kgr;" ?\κ) ;; GREEK SMALL LETTER KAPPA
520   ("&kgreen;" ?\Äž) ;; LATIN SMALL LETTER KRA
521   ("&KHcy;" ?\Ð¥) ;; CYRILLIC CAPITAL LETTER HA
522   ("&khcy;" ?\Ñ
523 ) ;; CYRILLIC SMALL LETTER HA
524   ("&KHgr;" ?\Χ) ;; GREEK CAPITAL LETTER CHI
525   ("&khgr;" ?\χ) ;; GREEK SMALL LETTER CHI
526   ("&KJcy;" ?\Ќ) ;; CYRILLIC CAPITAL LETTER KJE
527   ("&kjcy;" ?\ќ) ;; CYRILLIC SMALL LETTER KJE
528   ("&lAarr;" ?\⇚) ;; LEFTWARDS TRIPLE ARROW
529   ("&Lacute;" ?\Ĺ) ;; LATIN CAPITAL LETTER L WITH ACUTE
530   ("&lacute;" ?\ĺ) ;; LATIN SMALL LETTER L WITH ACUTE
531   ("&lagran;" ?\ℒ)