Source code

001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3.text.translate;
018
019/**
020 * Class holding various entity data for HTML and XML - generally for use with
021 * the LookupTranslator.
022 * All arrays are of length [*][2].
023 *
024 * @since 3.0
025 * @version $Id: EntityArrays.java 1436770 2013-01-22 07:09:45Z ggregory $
026 */
027public class EntityArrays {
028
029    /**
030     * Mapping to escape <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1">ISO-8859-1</a>
031     * characters to their named HTML 3.x equivalents.
032     * @return the mapping table
033     */
034    public static String[][] ISO8859_1_ESCAPE() { return ISO8859_1_ESCAPE.clone(); }
035    private static final String[][] ISO8859_1_ESCAPE = {
036        {"\u00A0", "&nbsp;"}, // non-breaking space
037        {"\u00A1", "&iexcl;"}, // inverted exclamation mark
038        {"\u00A2", "&cent;"}, // cent sign
039        {"\u00A3", "&pound;"}, // pound sign
040        {"\u00A4", "&curren;"}, // currency sign
041        {"\u00A5", "&yen;"}, // yen sign = yuan sign
042        {"\u00A6", "&brvbar;"}, // broken bar = broken vertical bar
043        {"\u00A7", "&sect;"}, // section sign
044        {"\u00A8", "&uml;"}, // diaeresis = spacing diaeresis
045        {"\u00A9", "&copy;"}, // © - copyright sign
046        {"\u00AA", "&ordf;"}, // feminine ordinal indicator
047        {"\u00AB", "&laquo;"}, // left-pointing double angle quotation mark = left pointing guillemet
048        {"\u00AC", "&not;"}, // not sign
049        {"\u00AD", "&shy;"}, // soft hyphen = discretionary hyphen
050        {"\u00AE", "&reg;"}, // ® - registered trademark sign
051        {"\u00AF", "&macr;"}, // macron = spacing macron = overline = APL overbar
052        {"\u00B0", "&deg;"}, // degree sign
053        {"\u00B1", "&plusmn;"}, // plus-minus sign = plus-or-minus sign
054        {"\u00B2", "&sup2;"}, // superscript two = superscript digit two = squared
055        {"\u00B3", "&sup3;"}, // superscript three = superscript digit three = cubed
056        {"\u00B4", "&acute;"}, // acute accent = spacing acute
057        {"\u00B5", "&micro;"}, // micro sign
058        {"\u00B6", "&para;"}, // pilcrow sign = paragraph sign
059        {"\u00B7", "&middot;"}, // middle dot = Georgian comma = Greek middle dot
060        {"\u00B8", "&cedil;"}, // cedilla = spacing cedilla
061        {"\u00B9", "&sup1;"}, // superscript one = superscript digit one
062        {"\u00BA", "&ordm;"}, // masculine ordinal indicator
063        {"\u00BB", "&raquo;"}, // right-pointing double angle quotation mark = right pointing guillemet
064        {"\u00BC", "&frac14;"}, // vulgar fraction one quarter = fraction one quarter
065        {"\u00BD", "&frac12;"}, // vulgar fraction one half = fraction one half
066        {"\u00BE", "&frac34;"}, // vulgar fraction three quarters = fraction three quarters
067        {"\u00BF", "&iquest;"}, // inverted question mark = turned question mark
068        {"\u00C0", "&Agrave;"}, // À - uppercase A, grave accent
069        {"\u00C1", "&Aacute;"}, // Á - uppercase A, acute accent
070        {"\u00C2", "&Acirc;"}, // Â - uppercase A, circumflex accent
071        {"\u00C3", "&Atilde;"}, // Ã - uppercase A, tilde
072        {"\u00C4", "&Auml;"}, // Ä - uppercase A, umlaut
073        {"\u00C5", "&Aring;"}, // Å - uppercase A, ring
074        {"\u00C6", "&AElig;"}, // Æ - uppercase AE
075        {"\u00C7", "&Ccedil;"}, // Ç - uppercase C, cedilla
076        {"\u00C8", "&Egrave;"}, // È - uppercase E, grave accent
077        {"\u00C9", "&Eacute;"}, // É - uppercase E, acute accent
078        {"\u00CA", "&Ecirc;"}, // Ê - uppercase E, circumflex accent
079        {"\u00CB", "&Euml;"}, // Ë - uppercase E, umlaut
080        {"\u00CC", "&Igrave;"}, // Ì - uppercase I, grave accent
081        {"\u00CD", "&Iacute;"}, // Í - uppercase I, acute accent
082        {"\u00CE", "&Icirc;"}, // Î - uppercase I, circumflex accent
083        {"\u00CF", "&Iuml;"}, // Ï - uppercase I, umlaut
084        {"\u00D0", "&ETH;"}, // Ð - uppercase Eth, Icelandic
085        {"\u00D1", "&Ntilde;"}, // Ñ - uppercase N, tilde
086        {"\u00D2", "&Ograve;"}, // Ò - uppercase O, grave accent
087        {"\u00D3", "&Oacute;"}, // Ó - uppercase O, acute accent
088        {"\u00D4", "&Ocirc;"}, // Ô - uppercase O, circumflex accent
089        {"\u00D5", "&Otilde;"}, // Õ - uppercase O, tilde
090        {"\u00D6", "&Ouml;"}, // Ö - uppercase O, umlaut
091        {"\u00D7", "&times;"}, // multiplication sign
092        {"\u00D8", "&Oslash;"}, // Ø - uppercase O, slash
093        {"\u00D9", "&Ugrave;"}, // Ù - uppercase U, grave accent
094        {"\u00DA", "&Uacute;"}, // Ú - uppercase U, acute accent
095        {"\u00DB", "&Ucirc;"}, // Û - uppercase U, circumflex accent
096        {"\u00DC", "&Uuml;"}, // Ü - uppercase U, umlaut
097        {"\u00DD", "&Yacute;"}, // Ý - uppercase Y, acute accent
098        {"\u00DE", "&THORN;"}, // Þ - uppercase THORN, Icelandic
099        {"\u00DF", "&szlig;"}, // ß - lowercase sharps, German
100        {"\u00E0", "&agrave;"}, // à - lowercase a, grave accent
101        {"\u00E1", "&aacute;"}, // á - lowercase a, acute accent
102        {"\u00E2", "&acirc;"}, // â - lowercase a, circumflex accent
103        {"\u00E3", "&atilde;"}, // ã - lowercase a, tilde
104        {"\u00E4", "&auml;"}, // ä - lowercase a, umlaut
105        {"\u00E5", "&aring;"}, // å - lowercase a, ring
106        {"\u00E6", "&aelig;"}, // æ - lowercase ae
107        {"\u00E7", "&ccedil;"}, // ç - lowercase c, cedilla
108        {"\u00E8", "&egrave;"}, // è - lowercase e, grave accent
109        {"\u00E9", "&eacute;"}, // é - lowercase e, acute accent
110        {"\u00EA", "&ecirc;"}, // ê - lowercase e, circumflex accent
111        {"\u00EB", "&euml;"}, // ë - lowercase e, umlaut
112        {"\u00EC", "&igrave;"}, // ì - lowercase i, grave accent
113        {"\u00ED", "&iacute;"}, // í - lowercase i, acute accent
114        {"\u00EE", "&icirc;"}, // î - lowercase i, circumflex accent
115        {"\u00EF", "&iuml;"}, // ï - lowercase i, umlaut
116        {"\u00F0", "&eth;"}, // ð - lowercase eth, Icelandic
117        {"\u00F1", "&ntilde;"}, // ñ - lowercase n, tilde
118        {"\u00F2", "&ograve;"}, // ò - lowercase o, grave accent
119        {"\u00F3", "&oacute;"}, // ó - lowercase o, acute accent
120        {"\u00F4", "&ocirc;"}, // ô - lowercase o, circumflex accent
121        {"\u00F5", "&otilde;"}, // õ - lowercase o, tilde
122        {"\u00F6", "&ouml;"}, // ö - lowercase o, umlaut
123        {"\u00F7", "&divide;"}, // division sign
124        {"\u00F8", "&oslash;"}, // ø - lowercase o, slash
125        {"\u00F9", "&ugrave;"}, // ù - lowercase u, grave accent
126        {"\u00FA", "&uacute;"}, // ú - lowercase u, acute accent
127        {"\u00FB", "&ucirc;"}, // û - lowercase u, circumflex accent
128        {"\u00FC", "&uuml;"}, // ü - lowercase u, umlaut
129        {"\u00FD", "&yacute;"}, // ý - lowercase y, acute accent
130        {"\u00FE", "&thorn;"}, // þ - lowercase thorn, Icelandic
131        {"\u00FF", "&yuml;"}, // ÿ - lowercase y, umlaut
132    };
133
134    /**
135     * Reverse of {@link #ISO8859_1_ESCAPE()} for unescaping purposes.
136     * @return the mapping table
137     */
138    public static String[][] ISO8859_1_UNESCAPE() { return ISO8859_1_UNESCAPE.clone(); }
139    private static final String[][] ISO8859_1_UNESCAPE = invert(ISO8859_1_ESCAPE);
140
141    /**
142     * Mapping to escape additional <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">character entity
143     * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE()} to get the full list of
144     * HTML 4.0 character entities.
145     * @return the mapping table
146     */
147    public static String[][] HTML40_EXTENDED_ESCAPE() { return HTML40_EXTENDED_ESCAPE.clone(); }
148    private static final String[][] HTML40_EXTENDED_ESCAPE = {
149        // <!-- Latin Extended-B -->
150        {"\u0192", "&fnof;"}, // latin small f with hook = function= florin, U+0192 ISOtech -->
151        // <!-- Greek -->
152        {"\u0391", "&Alpha;"}, // greek capital letter alpha, U+0391 -->
153        {"\u0392", "&Beta;"}, // greek capital letter beta, U+0392 -->
154        {"\u0393", "&Gamma;"}, // greek capital letter gamma,U+0393 ISOgrk3 -->
155        {"\u0394", "&Delta;"}, // greek capital letter delta,U+0394 ISOgrk3 -->
156        {"\u0395", "&Epsilon;"}, // greek capital letter epsilon, U+0395 -->
157        {"\u0396", "&Zeta;"}, // greek capital letter zeta, U+0396 -->
158        {"\u0397", "&Eta;"}, // greek capital letter eta, U+0397 -->
159        {"\u0398", "&Theta;"}, // greek capital letter theta,U+0398 ISOgrk3 -->
160        {"\u0399", "&Iota;"}, // greek capital letter iota, U+0399 -->
161        {"\u039A", "&Kappa;"}, // greek capital letter kappa, U+039A -->
162        {"\u039B", "&Lambda;"}, // greek capital letter lambda,U+039B ISOgrk3 -->
163        {"\u039C", "&Mu;"}, // greek capital letter mu, U+039C -->
164        {"\u039D", "&Nu;"}, // greek capital letter nu, U+039D -->
165        {"\u039E", "&Xi;"}, // greek capital letter xi, U+039E ISOgrk3 -->
166        {"\u039F", "&Omicron;"}, // greek capital letter omicron, U+039F -->
167        {"\u03A0", "&Pi;"}, // greek capital letter pi, U+03A0 ISOgrk3 -->
168        {"\u03A1", "&Rho;"}, // greek capital letter rho, U+03A1 -->
169        // <!-- there is no Sigmaf, and no U+03A2 character either -->
170        {"\u03A3", "&Sigma;"}, // greek capital letter sigma,U+03A3 ISOgrk3 -->
171        {"\u03A4", "&Tau;"}, // greek capital letter tau, U+03A4 -->
172        {"\u03A5", "&Upsilon;"}, // greek capital letter upsilon,U+03A5 ISOgrk3 -->
173        {"\u03A6", "&Phi;"}, // greek capital letter phi,U+03A6 ISOgrk3 -->
174        {"\u03A7", "&Chi;"}, // greek capital letter chi, U+03A7 -->
175        {"\u03A8", "&Psi;"}, // greek capital letter psi,U+03A8 ISOgrk3 -->
176        {"\u03A9", "&Omega;"}, // greek capital letter omega,U+03A9 ISOgrk3 -->
177        {"\u03B1", "&alpha;"}, // greek small letter alpha,U+03B1 ISOgrk3 -->
178        {"\u03B2", "&beta;"}, // greek small letter beta, U+03B2 ISOgrk3 -->
179        {"\u03B3", "&gamma;"}, // greek small letter gamma,U+03B3 ISOgrk3 -->
180        {"\u03B4", "&delta;"}, // greek small letter delta,U+03B4 ISOgrk3 -->
181        {"\u03B5", "&epsilon;"}, // greek small letter epsilon,U+03B5 ISOgrk3 -->
182        {"\u03B6", "&zeta;"}, // greek small letter zeta, U+03B6 ISOgrk3 -->
183        {"\u03B7", "&eta;"}, // greek small letter eta, U+03B7 ISOgrk3 -->
184        {"\u03B8", "&theta;"}, // greek small letter theta,U+03B8 ISOgrk3 -->
185        {"\u03B9", "&iota;"}, // greek small letter iota, U+03B9 ISOgrk3 -->
186        {"\u03BA", "&kappa;"}, // greek small letter kappa,U+03BA ISOgrk3 -->
187        {"\u03BB", "&lambda;"}, // greek small letter lambda,U+03BB ISOgrk3 -->
188        {"\u03BC", "&mu;"}, // greek small letter mu, U+03BC ISOgrk3 -->
189        {"\u03BD", "&nu;"}, // greek small letter nu, U+03BD ISOgrk3 -->
190        {"\u03BE", "&xi;"}, // greek small letter xi, U+03BE ISOgrk3 -->
191        {"\u03BF", "&omicron;"}, // greek small letter omicron, U+03BF NEW -->
192        {"\u03C0", "&pi;"}, // greek small letter pi, U+03C0 ISOgrk3 -->
193        {"\u03C1", "&rho;"}, // greek small letter rho, U+03C1 ISOgrk3 -->
194        {"\u03C2", "&sigmaf;"}, // greek small letter final sigma,U+03C2 ISOgrk3 -->
195        {"\u03C3", "&sigma;"}, // greek small letter sigma,U+03C3 ISOgrk3 -->
196        {"\u03C4", "&tau;"}, // greek small letter tau, U+03C4 ISOgrk3 -->
197        {"\u03C5", "&upsilon;"}, // greek small letter upsilon,U+03C5 ISOgrk3 -->
198        {"\u03C6", "&phi;"}, // greek small letter phi, U+03C6 ISOgrk3 -->
199        {"\u03C7", "&chi;"}, // greek small letter chi, U+03C7 ISOgrk3 -->
200        {"\u03C8", "&psi;"}, // greek small letter psi, U+03C8 ISOgrk3 -->
201        {"\u03C9", "&omega;"}, // greek small letter omega,U+03C9 ISOgrk3 -->
202        {"\u03D1", "&thetasym;"}, // greek small letter theta symbol,U+03D1 NEW -->
203        {"\u03D2", "&upsih;"}, // greek upsilon with hook symbol,U+03D2 NEW -->
204        {"\u03D6", "&piv;"}, // greek pi symbol, U+03D6 ISOgrk3 -->
205        // <!-- General Punctuation -->
206        {"\u2022", "&bull;"}, // bullet = black small circle,U+2022 ISOpub -->
207        // <!-- bullet is NOT the same as bullet operator, U+2219 -->
208        {"\u2026", "&hellip;"}, // horizontal ellipsis = three dot leader,U+2026 ISOpub -->
209        {"\u2032", "&prime;"}, // prime = minutes = feet, U+2032 ISOtech -->
210        {"\u2033", "&Prime;"}, // double prime = seconds = inches,U+2033 ISOtech -->
211        {"\u203E", "&oline;"}, // overline = spacing overscore,U+203E NEW -->
212        {"\u2044", "&frasl;"}, // fraction slash, U+2044 NEW -->
213        // <!-- Letterlike Symbols -->
214        {"\u2118", "&weierp;"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso -->
215        {"\u2111", "&image;"}, // blackletter capital I = imaginary part,U+2111 ISOamso -->
216        {"\u211C", "&real;"}, // blackletter capital R = real part symbol,U+211C ISOamso -->
217        {"\u2122", "&trade;"}, // trade mark sign, U+2122 ISOnum -->
218        {"\u2135", "&alefsym;"}, // alef symbol = first transfinite cardinal,U+2135 NEW -->
219        // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the
220        // same glyph could be used to depict both characters -->
221        // <!-- Arrows -->
222        {"\u2190", "&larr;"}, // leftwards arrow, U+2190 ISOnum -->
223        {"\u2191", "&uarr;"}, // upwards arrow, U+2191 ISOnum-->
224        {"\u2192", "&rarr;"}, // rightwards arrow, U+2192 ISOnum -->
225        {"\u2193", "&darr;"}, // downwards arrow, U+2193 ISOnum -->
226        {"\u2194", "&harr;"}, // left right arrow, U+2194 ISOamsa -->
227        {"\u21B5", "&crarr;"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
228        {"\u21D0", "&lArr;"}, // leftwards double arrow, U+21D0 ISOtech -->
229        // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'
230        // arrow but also does not have any other character for that function.
231        // So ? lArr canbe used for 'is implied by' as ISOtech suggests -->
232        {"\u21D1", "&uArr;"}, // upwards double arrow, U+21D1 ISOamsa -->
233        {"\u21D2", "&rArr;"}, // rightwards double arrow,U+21D2 ISOtech -->
234        // <!-- ISO 10646 does not say this is the 'implies' character but does not
235        // have another character with this function so ?rArr can be used for
236        // 'implies' as ISOtech suggests -->
237        {"\u21D3", "&dArr;"}, // downwards double arrow, U+21D3 ISOamsa -->
238        {"\u21D4", "&hArr;"}, // left right double arrow,U+21D4 ISOamsa -->
239        // <!-- Mathematical Operators -->
240        {"\u2200", "&forall;"}, // for all, U+2200 ISOtech -->
241        {"\u2202", "&part;"}, // partial differential, U+2202 ISOtech -->
242        {"\u2203", "&exist;"}, // there exists, U+2203 ISOtech -->
243        {"\u2205", "&empty;"}, // empty set = null set = diameter,U+2205 ISOamso -->
244        {"\u2207", "&nabla;"}, // nabla = backward difference,U+2207 ISOtech -->
245        {"\u2208", "&isin;"}, // element of, U+2208 ISOtech -->
246        {"\u2209", "&notin;"}, // not an element of, U+2209 ISOtech -->
247        {"\u220B", "&ni;"}, // contains as member, U+220B ISOtech -->
248        // <!-- should there be a more memorable name than 'ni'? -->
249        {"\u220F", "&prod;"}, // n-ary product = product sign,U+220F ISOamsb -->
250        // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'
251        // though the same glyph might be used for both -->
252        {"\u2211", "&sum;"}, // n-ary summation, U+2211 ISOamsb -->
253        // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
254        // though the same glyph might be used for both -->
255        {"\u2212", "&minus;"}, // minus sign, U+2212 ISOtech -->
256        {"\u2217", "&lowast;"}, // asterisk operator, U+2217 ISOtech -->
257        {"\u221A", "&radic;"}, // square root = radical sign,U+221A ISOtech -->
258        {"\u221D", "&prop;"}, // proportional to, U+221D ISOtech -->
259        {"\u221E", "&infin;"}, // infinity, U+221E ISOtech -->
260        {"\u2220", "&ang;"}, // angle, U+2220 ISOamso -->
261        {"\u2227", "&and;"}, // logical and = wedge, U+2227 ISOtech -->
262        {"\u2228", "&or;"}, // logical or = vee, U+2228 ISOtech -->
263        {"\u2229", "&cap;"}, // intersection = cap, U+2229 ISOtech -->
264        {"\u222A", "&cup;"}, // union = cup, U+222A ISOtech -->
265        {"\u222B", "&int;"}, // integral, U+222B ISOtech -->
266        {"\u2234", "&there4;"}, // therefore, U+2234 ISOtech -->
267        {"\u223C", "&sim;"}, // tilde operator = varies with = similar to,U+223C ISOtech -->
268        // <!-- tilde operator is NOT the same character as the tilde, U+007E,although
269        // the same glyph might be used to represent both -->
270        {"\u2245", "&cong;"}, // approximately equal to, U+2245 ISOtech -->
271        {"\u2248", "&asymp;"}, // almost equal to = asymptotic to,U+2248 ISOamsr -->
272        {"\u2260", "&ne;"}, // not equal to, U+2260 ISOtech -->
273        {"\u2261", "&equiv;"}, // identical to, U+2261 ISOtech -->
274        {"\u2264", "&le;"}, // less-than or equal to, U+2264 ISOtech -->
275        {"\u2265", "&ge;"}, // greater-than or equal to,U+2265 ISOtech -->
276        {"\u2282", "&sub;"}, // subset of, U+2282 ISOtech -->
277        {"\u2283", "&sup;"}, // superset of, U+2283 ISOtech -->
278        // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the
279        // Symbol font encoding and is not included. Should it be, for symmetry?
280        // It is in ISOamsn --> <!ENTITY nsub", "8836"},
281        // not a subset of, U+2284 ISOamsn -->
282        {"\u2286", "&sube;"}, // subset of or equal to, U+2286 ISOtech -->
283        {"\u2287", "&supe;"}, // superset of or equal to,U+2287 ISOtech -->
284        {"\u2295", "&oplus;"}, // circled plus = direct sum,U+2295 ISOamsb -->
285        {"\u2297", "&otimes;"}, // circled times = vector product,U+2297 ISOamsb -->
286        {"\u22A5", "&perp;"}, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech -->
287        {"\u22C5", "&sdot;"}, // dot operator, U+22C5 ISOamsb -->
288        // <!-- dot operator is NOT the same character as U+00B7 middle dot -->
289        // <!-- Miscellaneous Technical -->
290        {"\u2308", "&lceil;"}, // left ceiling = apl upstile,U+2308 ISOamsc -->
291        {"\u2309", "&rceil;"}, // right ceiling, U+2309 ISOamsc -->
292        {"\u230A", "&lfloor;"}, // left floor = apl downstile,U+230A ISOamsc -->
293        {"\u230B", "&rfloor;"}, // right floor, U+230B ISOamsc -->
294        {"\u2329", "&lang;"}, // left-pointing angle bracket = bra,U+2329 ISOtech -->
295        // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation
296        // mark' -->
297        {"\u232A", "&rang;"}, // right-pointing angle bracket = ket,U+232A ISOtech -->
298        // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A
299        // 'single right-pointing angle quotation mark' -->
300        // <!-- Geometric Shapes -->
301        {"\u25CA", "&loz;"}, // lozenge, U+25CA ISOpub -->
302        // <!-- Miscellaneous Symbols -->
303        {"\u2660", "&spades;"}, // black spade suit, U+2660 ISOpub -->
304        // <!-- black here seems to mean filled as opposed to hollow -->
305        {"\u2663", "&clubs;"}, // black club suit = shamrock,U+2663 ISOpub -->
306        {"\u2665", "&hearts;"}, // black heart suit = valentine,U+2665 ISOpub -->
307        {"\u2666", "&diams;"}, // black diamond suit, U+2666 ISOpub -->
308
309        // <!-- Latin Extended-A -->
310        {"\u0152", "&OElig;"}, // -- latin capital ligature OE,U+0152 ISOlat2 -->
311        {"\u0153", "&oelig;"}, // -- latin small ligature oe, U+0153 ISOlat2 -->
312        // <!-- ligature is a misnomer, this is a separate character in some languages -->
313        {"\u0160", "&Scaron;"}, // -- latin capital letter S with caron,U+0160 ISOlat2 -->
314        {"\u0161", "&scaron;"}, // -- latin small letter s with caron,U+0161 ISOlat2 -->
315        {"\u0178", "&Yuml;"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 -->
316        // <!-- Spacing Modifier Letters -->
317        {"\u02C6", "&circ;"}, // -- modifier letter circumflex accent,U+02C6 ISOpub -->
318        {"\u02DC", "&tilde;"}, // small tilde, U+02DC ISOdia -->
319        // <!-- General Punctuation -->
320        {"\u2002", "&ensp;"}, // en space, U+2002 ISOpub -->
321        {"\u2003", "&emsp;"}, // em space, U+2003 ISOpub -->
322        {"\u2009", "&thinsp;"}, // thin space, U+2009 ISOpub -->
323        {"\u200C", "&zwnj;"}, // zero width non-joiner,U+200C NEW RFC 2070 -->
324        {"\u200D", "&zwj;"}, // zero width joiner, U+200D NEW RFC 2070 -->
325        {"\u200E", "&lrm;"}, // left-to-right mark, U+200E NEW RFC 2070 -->
326        {"\u200F", "&rlm;"}, // right-to-left mark, U+200F NEW RFC 2070 -->
327        {"\u2013", "&ndash;"}, // en dash, U+2013 ISOpub -->
328        {"\u2014", "&mdash;"}, // em dash, U+2014 ISOpub -->
329        {"\u2018", "&lsquo;"}, // left single quotation mark,U+2018 ISOnum -->
330        {"\u2019", "&rsquo;"}, // right single quotation mark,U+2019 ISOnum -->
331        {"\u201A", "&sbquo;"}, // single low-9 quotation mark, U+201A NEW -->
332        {"\u201C", "&ldquo;"}, // left double quotation mark,U+201C ISOnum -->
333        {"\u201D", "&rdquo;"}, // right double quotation mark,U+201D ISOnum -->
334        {"\u201E", "&bdquo;"}, // double low-9 quotation mark, U+201E NEW -->
335        {"\u2020", "&dagger;"}, // dagger, U+2020 ISOpub -->
336        {"\u2021", "&Dagger;"}, // double dagger, U+2021 ISOpub -->
337        {"\u2030", "&permil;"}, // per mille sign, U+2030 ISOtech -->
338        {"\u2039", "&lsaquo;"}, // single left-pointing angle quotation mark,U+2039 ISO proposed -->
339        // <!-- lsaquo is proposed but not yet ISO standardized -->
340        {"\u203A", "&rsaquo;"}, // single right-pointing angle quotation mark,U+203A ISO proposed -->
341        // <!-- rsaquo is proposed but not yet ISO standardized -->
342        {"\u20AC", "&euro;"}, // -- euro sign, U+20AC NEW -->
343    };
344
345    /**
346     * Reverse of {@link #HTML40_EXTENDED_ESCAPE()} for unescaping purposes.
347     * @return the mapping table
348     */
349    public static String[][] HTML40_EXTENDED_UNESCAPE() { return HTML40_EXTENDED_UNESCAPE.clone(); }
350    private static final String[][] HTML40_EXTENDED_UNESCAPE = invert(HTML40_EXTENDED_ESCAPE);
351
352    /**
353     * Mapping to escape the basic XML and HTML character entities.
354     *
355     * Namely: {@code " & < >}
356     * @return the mapping table
357     */
358    public static String[][] BASIC_ESCAPE() { return BASIC_ESCAPE.clone(); }
359    private static final String[][] BASIC_ESCAPE = {
360        {"\"", "&quot;"}, // " - double-quote
361        {"&", "&amp;"},   // & - ampersand
362        {"<", "&lt;"},    // < - less-than
363        {">", "&gt;"},    // > - greater-than
364    };
365
366    /**
367     * Reverse of {@link #BASIC_ESCAPE()} for unescaping purposes.
368     * @return the mapping table
369     */
370    public static String[][] BASIC_UNESCAPE() { return BASIC_UNESCAPE.clone(); }
371    private static final String[][] BASIC_UNESCAPE = invert(BASIC_ESCAPE);
372
373    /**
374     * Mapping to escape the apostrophe character to its XML character entity.
375     * @return the mapping table
376     */
377    public static String[][] APOS_ESCAPE() { return APOS_ESCAPE.clone(); }
378    private static final String[][] APOS_ESCAPE = {
379        {"'", "&apos;"}, // XML apostrophe
380    };
381
382    /**
383     * Reverse of {@link #APOS_ESCAPE()} for unescaping purposes.
384     * @return the mapping table
385     */
386    public static String[][] APOS_UNESCAPE() { return APOS_UNESCAPE.clone(); }
387    private static final String[][] APOS_UNESCAPE = invert(APOS_ESCAPE);
388
389    /**
390     * Mapping to escape the Java control characters.
391     *
392     * Namely: {@code \b \n \t \f \r}
393     * @return the mapping table
394     */
395    public static String[][] JAVA_CTRL_CHARS_ESCAPE() { return JAVA_CTRL_CHARS_ESCAPE.clone(); }
396    private static final String[][] JAVA_CTRL_CHARS_ESCAPE = {
397        {"\b", "\\b"},
398        {"\n", "\\n"},
399        {"\t", "\\t"},
400        {"\f", "\\f"},
401        {"\r", "\\r"}
402    };
403
404    /**
405     * Reverse of {@link #JAVA_CTRL_CHARS_ESCAPE()} for unescaping purposes.
406     * @return the mapping table
407     */
408    public static String[][] JAVA_CTRL_CHARS_UNESCAPE() { return JAVA_CTRL_CHARS_UNESCAPE.clone(); }
409    private static final String[][] JAVA_CTRL_CHARS_UNESCAPE = invert(JAVA_CTRL_CHARS_ESCAPE);
410
411    /**
412     * Used to invert an escape array into an unescape array
413     * @param array String[][] to be inverted
414     * @return String[][] inverted array
415     */
416    public static String[][] invert(final String[][] array) {
417        final String[][] newarray = new String[array.length][2];
418        for(int i = 0; i<array.length; i++) {
419            newarray[i][0] = array[i][1];
420            newarray[i][1] = array[i][0];
421        }
422        return newarray;
423    }
424
425}