View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *      http://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  package org.apache.commons.lang3.text.translate;
18  
19  /**
20   * Class holding various entity data for HTML and XML - generally for use with
21   * the LookupTranslator.
22   * All arrays are of length [*][2].
23   *
24   * @since 3.0
25   * @deprecated As of 3.6, use Apache Commons Text
26   * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/CodePointTranslator.html">
27   * EntityArrays</a> instead
28   */
29  @Deprecated
30  public class EntityArrays {
31  
32      private static final String[][] ISO8859_1_ESCAPE = {
33          {"\u00A0", "&nbsp;"}, // non-breaking space
34          {"\u00A1", "&iexcl;"}, // inverted exclamation mark
35          {"\u00A2", "&cent;"}, // cent sign
36          {"\u00A3", "&pound;"}, // pound sign
37          {"\u00A4", "&curren;"}, // currency sign
38          {"\u00A5", "&yen;"}, // yen sign = yuan sign
39          {"\u00A6", "&brvbar;"}, // broken bar = broken vertical bar
40          {"\u00A7", "&sect;"}, // section sign
41          {"\u00A8", "&uml;"}, // dieresis = spacing dieresis
42          {"\u00A9", "&copy;"}, // © - copyright sign
43          {"\u00AA", "&ordf;"}, // feminine ordinal indicator
44          {"\u00AB", "&laquo;"}, // left-pointing double angle quotation mark = left pointing guillemet
45          {"\u00AC", "&not;"}, // not sign
46          {"\u00AD", "&shy;"}, // soft hyphen = discretionary hyphen
47          {"\u00AE", "&reg;"}, // ® - registered trademark sign
48          {"\u00AF", "&macr;"}, // macron = spacing macron = overline = APL overbar
49          {"\u00B0", "&deg;"}, // degree sign
50          {"\u00B1", "&plusmn;"}, // plus-minus sign = plus-or-minus sign
51          {"\u00B2", "&sup2;"}, // superscript two = superscript digit two = squared
52          {"\u00B3", "&sup3;"}, // superscript three = superscript digit three = cubed
53          {"\u00B4", "&acute;"}, // acute accent = spacing acute
54          {"\u00B5", "&micro;"}, // micro sign
55          {"\u00B6", "&para;"}, // pilcrow sign = paragraph sign
56          {"\u00B7", "&middot;"}, // middle dot = Georgian comma = Greek middle dot
57          {"\u00B8", "&cedil;"}, // cedilla = spacing cedilla
58          {"\u00B9", "&sup1;"}, // superscript one = superscript digit one
59          {"\u00BA", "&ordm;"}, // masculine ordinal indicator
60          {"\u00BB", "&raquo;"}, // right-pointing double angle quotation mark = right pointing guillemet
61          {"\u00BC", "&frac14;"}, // vulgar fraction one quarter = fraction one quarter
62          {"\u00BD", "&frac12;"}, // vulgar fraction one half = fraction one half
63          {"\u00BE", "&frac34;"}, // vulgar fraction three quarters = fraction three quarters
64          {"\u00BF", "&iquest;"}, // inverted question mark = turned question mark
65          {"\u00C0", "&Agrave;"}, // À - uppercase A, grave accent
66          {"\u00C1", "&Aacute;"}, // Á - uppercase A, acute accent
67          {"\u00C2", "&Acirc;"}, // Â - uppercase A, circumflex accent
68          {"\u00C3", "&Atilde;"}, // Ã - uppercase A, tilde
69          {"\u00C4", "&Auml;"}, // Ä - uppercase A, umlaut
70          {"\u00C5", "&Aring;"}, // Å - uppercase A, ring
71          {"\u00C6", "&AElig;"}, // Æ - uppercase AE
72          {"\u00C7", "&Ccedil;"}, // Ç - uppercase C, cedilla
73          {"\u00C8", "&Egrave;"}, // È - uppercase E, grave accent
74          {"\u00C9", "&Eacute;"}, // É - uppercase E, acute accent
75          {"\u00CA", "&Ecirc;"}, // Ê - uppercase E, circumflex accent
76          {"\u00CB", "&Euml;"}, // Ë - uppercase E, umlaut
77          {"\u00CC", "&Igrave;"}, // Ì - uppercase I, grave accent
78          {"\u00CD", "&Iacute;"}, // Í - uppercase I, acute accent
79          {"\u00CE", "&Icirc;"}, // Î - uppercase I, circumflex accent
80          {"\u00CF", "&Iuml;"}, // Ï - uppercase I, umlaut
81          {"\u00D0", "&ETH;"}, // Ð - uppercase Eth, Icelandic
82          {"\u00D1", "&Ntilde;"}, // Ñ - uppercase N, tilde
83          {"\u00D2", "&Ograve;"}, // Ò - uppercase O, grave accent
84          {"\u00D3", "&Oacute;"}, // Ó - uppercase O, acute accent
85          {"\u00D4", "&Ocirc;"}, // Ô - uppercase O, circumflex accent
86          {"\u00D5", "&Otilde;"}, // Õ - uppercase O, tilde
87          {"\u00D6", "&Ouml;"}, // Ö - uppercase O, umlaut
88          {"\u00D7", "&times;"}, // multiplication sign
89          {"\u00D8", "&Oslash;"}, // Ø - uppercase O, slash
90          {"\u00D9", "&Ugrave;"}, // Ù - uppercase U, grave accent
91          {"\u00DA", "&Uacute;"}, // Ú - uppercase U, acute accent
92          {"\u00DB", "&Ucirc;"}, // Û - uppercase U, circumflex accent
93          {"\u00DC", "&Uuml;"}, // Ü - uppercase U, umlaut
94          {"\u00DD", "&Yacute;"}, // Ý - uppercase Y, acute accent
95          {"\u00DE", "&THORN;"}, // Þ - uppercase THORN, Icelandic
96          {"\u00DF", "&szlig;"}, // ß - lowercase sharps, German
97          {"\u00E0", "&agrave;"}, // à - lowercase a, grave accent
98          {"\u00E1", "&aacute;"}, // á - lowercase a, acute accent
99          {"\u00E2", "&acirc;"}, // â - lowercase a, circumflex accent
100         {"\u00E3", "&atilde;"}, // ã - lowercase a, tilde
101         {"\u00E4", "&auml;"}, // ä - lowercase a, umlaut
102         {"\u00E5", "&aring;"}, // å - lowercase a, ring
103         {"\u00E6", "&aelig;"}, // æ - lowercase ae
104         {"\u00E7", "&ccedil;"}, // ç - lowercase c, cedilla
105         {"\u00E8", "&egrave;"}, // è - lowercase e, grave accent
106         {"\u00E9", "&eacute;"}, // é - lowercase e, acute accent
107         {"\u00EA", "&ecirc;"}, // ê - lowercase e, circumflex accent
108         {"\u00EB", "&euml;"}, // ë - lowercase e, umlaut
109         {"\u00EC", "&igrave;"}, // ì - lowercase i, grave accent
110         {"\u00ED", "&iacute;"}, // í - lowercase i, acute accent
111         {"\u00EE", "&icirc;"}, // î - lowercase i, circumflex accent
112         {"\u00EF", "&iuml;"}, // ï - lowercase i, umlaut
113         {"\u00F0", "&eth;"}, // ð - lowercase eth, Icelandic
114         {"\u00F1", "&ntilde;"}, // ñ - lowercase n, tilde
115         {"\u00F2", "&ograve;"}, // ò - lowercase o, grave accent
116         {"\u00F3", "&oacute;"}, // ó - lowercase o, acute accent
117         {"\u00F4", "&ocirc;"}, // ô - lowercase o, circumflex accent
118         {"\u00F5", "&otilde;"}, // õ - lowercase o, tilde
119         {"\u00F6", "&ouml;"}, // ö - lowercase o, umlaut
120         {"\u00F7", "&divide;"}, // division sign
121         {"\u00F8", "&oslash;"}, // ø - lowercase o, slash
122         {"\u00F9", "&ugrave;"}, // ù - lowercase u, grave accent
123         {"\u00FA", "&uacute;"}, // ú - lowercase u, acute accent
124         {"\u00FB", "&ucirc;"}, // û - lowercase u, circumflex accent
125         {"\u00FC", "&uuml;"}, // ü - lowercase u, umlaut
126         {"\u00FD", "&yacute;"}, // ý - lowercase y, acute accent
127         {"\u00FE", "&thorn;"}, // þ - lowercase thorn, Icelandic
128         {"\u00FF", "&yuml;"}, // ÿ - lowercase y, umlaut
129     };
130 
131     private static final String[][] ISO8859_1_UNESCAPE = invert(ISO8859_1_ESCAPE);
132 
133     private static final String[][] HTML40_EXTENDED_ESCAPE = {
134         // <!-- Latin Extended-B -->
135         {"\u0192", "&fnof;"}, // latin small f with hook = function= florin, U+0192 ISOtech -->
136         // <!-- Greek -->
137         {"\u0391", "&Alpha;"}, // greek capital letter alpha, U+0391 -->
138         {"\u0392", "&Beta;"}, // greek capital letter beta, U+0392 -->
139         {"\u0393", "&Gamma;"}, // greek capital letter gamma, U+0393 ISOgrk3 -->
140         {"\u0394", "&Delta;"}, // greek capital letter delta, U+0394 ISOgrk3 -->
141         {"\u0395", "&Epsilon;"}, // greek capital letter epsilon, U+0395 -->
142         {"\u0396", "&Zeta;"}, // greek capital letter zeta, U+0396 -->
143         {"\u0397", "&Eta;"}, // greek capital letter eta, U+0397 -->
144         {"\u0398", "&Theta;"}, // greek capital letter theta, U+0398 ISOgrk3 -->
145         {"\u0399", "&Iota;"}, // greek capital letter iota, U+0399 -->
146         {"\u039A", "&Kappa;"}, // greek capital letter kappa, U+039A -->
147         {"\u039B", "&Lambda;"}, // greek capital letter lambda, U+039B ISOgrk3 -->
148         {"\u039C", "&Mu;"}, // greek capital letter mu, U+039C -->
149         {"\u039D", "&Nu;"}, // greek capital letter nu, U+039D -->
150         {"\u039E", "&Xi;"}, // greek capital letter xi, U+039E ISOgrk3 -->
151         {"\u039F", "&Omicron;"}, // greek capital letter omicron, U+039F -->
152         {"\u03A0", "&Pi;"}, // greek capital letter pi, U+03A0 ISOgrk3 -->
153         {"\u03A1", "&Rho;"}, // greek capital letter rho, U+03A1 -->
154         // <!-- there is no Sigmaf, and no U+03A2 character either -->
155         {"\u03A3", "&Sigma;"}, // greek capital letter sigma, U+03A3 ISOgrk3 -->
156         {"\u03A4", "&Tau;"}, // greek capital letter tau, U+03A4 -->
157         {"\u03A5", "&Upsilon;"}, // greek capital letter upsilon, U+03A5 ISOgrk3 -->
158         {"\u03A6", "&Phi;"}, // greek capital letter phi, U+03A6 ISOgrk3 -->
159         {"\u03A7", "&Chi;"}, // greek capital letter chi, U+03A7 -->
160         {"\u03A8", "&Psi;"}, // greek capital letter psi, U+03A8 ISOgrk3 -->
161         {"\u03A9", "&Omega;"}, // greek capital letter omega, U+03A9 ISOgrk3 -->
162         {"\u03B1", "&alpha;"}, // greek small letter alpha, U+03B1 ISOgrk3 -->
163         {"\u03B2", "&beta;"}, // greek small letter beta, U+03B2 ISOgrk3 -->
164         {"\u03B3", "&gamma;"}, // greek small letter gamma, U+03B3 ISOgrk3 -->
165         {"\u03B4", "&delta;"}, // greek small letter delta, U+03B4 ISOgrk3 -->
166         {"\u03B5", "&epsilon;"}, // greek small letter epsilon, U+03B5 ISOgrk3 -->
167         {"\u03B6", "&zeta;"}, // greek small letter zeta, U+03B6 ISOgrk3 -->
168         {"\u03B7", "&eta;"}, // greek small letter eta, U+03B7 ISOgrk3 -->
169         {"\u03B8", "&theta;"}, // greek small letter theta, U+03B8 ISOgrk3 -->
170         {"\u03B9", "&iota;"}, // greek small letter iota, U+03B9 ISOgrk3 -->
171         {"\u03BA", "&kappa;"}, // greek small letter kappa, U+03BA ISOgrk3 -->
172         {"\u03BB", "&lambda;"}, // greek small letter lambda, U+03BB ISOgrk3 -->
173         {"\u03BC", "&mu;"}, // greek small letter mu, U+03BC ISOgrk3 -->
174         {"\u03BD", "&nu;"}, // greek small letter nu, U+03BD ISOgrk3 -->
175         {"\u03BE", "&xi;"}, // greek small letter xi, U+03BE ISOgrk3 -->
176         {"\u03BF", "&omicron;"}, // greek small letter omicron, U+03BF NEW -->
177         {"\u03C0", "&pi;"}, // greek small letter pi, U+03C0 ISOgrk3 -->
178         {"\u03C1", "&rho;"}, // greek small letter rho, U+03C1 ISOgrk3 -->
179         {"\u03C2", "&sigmaf;"}, // greek small letter final sigma, U+03C2 ISOgrk3 -->
180         {"\u03C3", "&sigma;"}, // greek small letter sigma, U+03C3 ISOgrk3 -->
181         {"\u03C4", "&tau;"}, // greek small letter tau, U+03C4 ISOgrk3 -->
182         {"\u03C5", "&upsilon;"}, // greek small letter upsilon, U+03C5 ISOgrk3 -->
183         {"\u03C6", "&phi;"}, // greek small letter phi, U+03C6 ISOgrk3 -->
184         {"\u03C7", "&chi;"}, // greek small letter chi, U+03C7 ISOgrk3 -->
185         {"\u03C8", "&psi;"}, // greek small letter psi, U+03C8 ISOgrk3 -->
186         {"\u03C9", "&omega;"}, // greek small letter omega, U+03C9 ISOgrk3 -->
187         {"\u03D1", "&thetasym;"}, // greek small letter theta symbol, U+03D1 NEW -->
188         {"\u03D2", "&upsih;"}, // greek upsilon with hook symbol, U+03D2 NEW -->
189         {"\u03D6", "&piv;"}, // greek pi symbol, U+03D6 ISOgrk3 -->
190         // <!-- General Punctuation -->
191         {"\u2022", "&bull;"}, // bullet = black small circle, U+2022 ISOpub -->
192         // <!-- bullet is NOT the same as bullet operator, U+2219 -->
193         {"\u2026", "&hellip;"}, // horizontal ellipsis = three dot leader, U+2026 ISOpub -->
194         {"\u2032", "&prime;"}, // prime = minutes = feet, U+2032 ISOtech -->
195         {"\u2033", "&Prime;"}, // double prime = seconds = inches, U+2033 ISOtech -->
196         {"\u203E", "&oline;"}, // overline = spacing overscore, U+203E NEW -->
197         {"\u2044", "&frasl;"}, // fraction slash, U+2044 NEW -->
198         // <!-- Letterlike Symbols -->
199         {"\u2118", "&weierp;"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso -->
200         {"\u2111", "&image;"}, // blackletter capital I = imaginary part, U+2111 ISOamso -->
201         {"\u211C", "&real;"}, // blackletter capital R = real part symbol, U+211C ISOamso -->
202         {"\u2122", "&trade;"}, // trade mark sign, U+2122 ISOnum -->
203         {"\u2135", "&alefsym;"}, // alef symbol = first transfinite cardinal, U+2135 NEW -->
204         // <!-- alef symbol is NOT the same as hebrew letter alef, U+05D0 although the
205         // same glyph could be used to depict both characters -->
206         // <!-- Arrows -->
207         {"\u2190", "&larr;"}, // leftwards arrow, U+2190 ISOnum -->
208         {"\u2191", "&uarr;"}, // upwards arrow, U+2191 ISOnum-->
209         {"\u2192", "&rarr;"}, // rightwards arrow, U+2192 ISOnum -->
210         {"\u2193", "&darr;"}, // downwards arrow, U+2193 ISOnum -->
211         {"\u2194", "&harr;"}, // left right arrow, U+2194 ISOamsa -->
212         {"\u21B5", "&crarr;"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
213         {"\u21D0", "&lArr;"}, // leftwards double arrow, U+21D0 ISOtech -->
214         // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'
215         // arrow but also does not have any other character for that function.
216         // So ? lArr canbe used for 'is implied by' as ISOtech suggests -->
217         {"\u21D1", "&uArr;"}, // upwards double arrow, U+21D1 ISOamsa -->
218         {"\u21D2", "&rArr;"}, // rightwards double arrow, U+21D2 ISOtech -->
219         // <!-- ISO 10646 does not say this is the 'implies' character but does not
220         // have another character with this function so ?rArr can be used for
221         // 'implies' as ISOtech suggests -->
222         {"\u21D3", "&dArr;"}, // downwards double arrow, U+21D3 ISOamsa -->
223         {"\u21D4", "&hArr;"}, // left right double arrow, U+21D4 ISOamsa -->
224         // <!-- Mathematical Operators -->
225         {"\u2200", "&forall;"}, // for all, U+2200 ISOtech -->
226         {"\u2202", "&part;"}, // partial differential, U+2202 ISOtech -->
227         {"\u2203", "&exist;"}, // there exists, U+2203 ISOtech -->
228         {"\u2205", "&empty;"}, // empty set = null set = diameter, U+2205 ISOamso -->
229         {"\u2207", "&nabla;"}, // nabla = backward difference, U+2207 ISOtech -->
230         {"\u2208", "&isin;"}, // element of, U+2208 ISOtech -->
231         {"\u2209", "&notin;"}, // not an element of, U+2209 ISOtech -->
232         {"\u220B", "&ni;"}, // contains as member, U+220B ISOtech -->
233         // <!-- should there be a more memorable name than 'ni'? -->
234         {"\u220F", "&prod;"}, // n-ary product = product sign, U+220F ISOamsb -->
235         // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'
236         // though the same glyph might be used for both -->
237         {"\u2211", "&sum;"}, // n-ary summation, U+2211 ISOamsb -->
238         // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
239         // though the same glyph might be used for both -->
240         {"\u2212", "&minus;"}, // minus sign, U+2212 ISOtech -->
241         {"\u2217", "&lowast;"}, // asterisk operator, U+2217 ISOtech -->
242         {"\u221A", "&radic;"}, // square root = radical sign, U+221A ISOtech -->
243         {"\u221D", "&prop;"}, // proportional to, U+221D ISOtech -->
244         {"\u221E", "&infin;"}, // infinity, U+221E ISOtech -->
245         {"\u2220", "&ang;"}, // angle, U+2220 ISOamso -->
246         {"\u2227", "&and;"}, // logical and = wedge, U+2227 ISOtech -->
247         {"\u2228", "&or;"}, // logical or = vee, U+2228 ISOtech -->
248         {"\u2229", "&cap;"}, // intersection = cap, U+2229 ISOtech -->
249         {"\u222A", "&cup;"}, // union = cup, U+222A ISOtech -->
250         {"\u222B", "&int;"}, // integral, U+222B ISOtech -->
251         {"\u2234", "&there4;"}, // therefore, U+2234 ISOtech -->
252         {"\u223C", "&sim;"}, // tilde operator = varies with = similar to, U+223C ISOtech -->
253         // <!-- tilde operator is NOT the same character as the tilde, U+007E, although
254         // the same glyph might be used to represent both -->
255         {"\u2245", "&cong;"}, // approximately equal to, U+2245 ISOtech -->
256         {"\u2248", "&asymp;"}, // almost equal to = asymptotic to, U+2248 ISOamsr -->
257         {"\u2260", "&ne;"}, // not equal to, U+2260 ISOtech -->
258         {"\u2261", "&equiv;"}, // identical to, U+2261 ISOtech -->
259         {"\u2264", "&le;"}, // less-than or equal to, U+2264 ISOtech -->
260         {"\u2265", "&ge;"}, // greater-than or equal to, U+2265 ISOtech -->
261         {"\u2282", "&sub;"}, // subset of, U+2282 ISOtech -->
262         {"\u2283", "&sup;"}, // superset of, U+2283 ISOtech -->
263         // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the
264         // Symbol font encoding and is not included. Should it be, for symmetry?
265         // It is in ISOamsn -->,
266         {"\u2284", "&nsub;"}, // not a subset of, U+2284 ISOamsn -->
267         {"\u2286", "&sube;"}, // subset of or equal to, U+2286 ISOtech -->
268         {"\u2287", "&supe;"}, // superset of or equal to, U+2287 ISOtech -->
269         {"\u2295", "&oplus;"}, // circled plus = direct sum, U+2295 ISOamsb -->
270         {"\u2297", "&otimes;"}, // circled times = vector product, U+2297 ISOamsb -->
271         {"\u22A5", "&perp;"}, // up tack = orthogonal to = perpendicular, U+22A5 ISOtech -->
272         {"\u22C5", "&sdot;"}, // dot operator, U+22C5 ISOamsb -->
273         // <!-- dot operator is NOT the same character as U+00B7 middle dot -->
274         // <!-- Miscellaneous Technical -->
275         {"\u2308", "&lceil;"}, // left ceiling = apl upstile, U+2308 ISOamsc -->
276         {"\u2309", "&rceil;"}, // right ceiling, U+2309 ISOamsc -->
277         {"\u230A", "&lfloor;"}, // left floor = apl downstile, U+230A ISOamsc -->
278         {"\u230B", "&rfloor;"}, // right floor, U+230B ISOamsc -->
279         {"\u2329", "&lang;"}, // left-pointing angle bracket = bra, U+2329 ISOtech -->
280         // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation
281         // mark' -->
282         {"\u232A", "&rang;"}, // right-pointing angle bracket = ket, U+232A ISOtech -->
283         // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A
284         // 'single right-pointing angle quotation mark' -->
285         // <!-- Geometric Shapes -->
286         {"\u25CA", "&loz;"}, // lozenge, U+25CA ISOpub -->
287         // <!-- Miscellaneous Symbols -->
288         {"\u2660", "&spades;"}, // black spade suit, U+2660 ISOpub -->
289         // <!-- black here seems to mean filled as opposed to hollow -->
290         {"\u2663", "&clubs;"}, // black club suit = shamrock, U+2663 ISOpub -->
291         {"\u2665", "&hearts;"}, // black heart suit = valentine, U+2665 ISOpub -->
292         {"\u2666", "&diams;"}, // black diamond suit, U+2666 ISOpub -->
293 
294         // <!-- Latin Extended-A -->
295         {"\u0152", "&OElig;"}, // -- latin capital ligature OE, U+0152 ISOlat2 -->
296         {"\u0153", "&oelig;"}, // -- latin small ligature oe, U+0153 ISOlat2 -->
297         // <!-- ligature is a misnomer, this is a separate character in some languages -->
298         {"\u0160", "&Scaron;"}, // -- latin capital letter S with caron, U+0160 ISOlat2 -->
299         {"\u0161", "&scaron;"}, // -- latin small letter s with caron, U+0161 ISOlat2 -->
300         {"\u0178", "&Yuml;"}, // -- latin capital letter Y with dieresis, U+0178 ISOlat2 -->
301         // <!-- Spacing Modifier Letters -->
302         {"\u02C6", "&circ;"}, // -- modifier letter circumflex accent, U+02C6 ISOpub -->
303         {"\u02DC", "&tilde;"}, // small tilde, U+02DC ISOdia -->
304         // <!-- General Punctuation -->
305         {"\u2002", "&ensp;"}, // en space, U+2002 ISOpub -->
306         {"\u2003", "&emsp;"}, // em space, U+2003 ISOpub -->
307         {"\u2009", "&thinsp;"}, // thin space, U+2009 ISOpub -->
308         {"\u200C", "&zwnj;"}, // zero width non-joiner, U+200C NEW RFC 2070 -->
309         {"\u200D", "&zwj;"}, // zero width joiner, U+200D NEW RFC 2070 -->
310         {"\u200E", "&lrm;"}, // left-to-right mark, U+200E NEW RFC 2070 -->
311         {"\u200F", "&rlm;"}, // right-to-left mark, U+200F NEW RFC 2070 -->
312         {"\u2013", "&ndash;"}, // en dash, U+2013 ISOpub -->
313         {"\u2014", "&mdash;"}, // em dash, U+2014 ISOpub -->
314         {"\u2018", "&lsquo;"}, // left single quotation mark, U+2018 ISOnum -->
315         {"\u2019", "&rsquo;"}, // right single quotation mark, U+2019 ISOnum -->
316         {"\u201A", "&sbquo;"}, // single low-9 quotation mark, U+201A NEW -->
317         {"\u201C", "&ldquo;"}, // left double quotation mark, U+201C ISOnum -->
318         {"\u201D", "&rdquo;"}, // right double quotation mark, U+201D ISOnum -->
319         {"\u201E", "&bdquo;"}, // double low-9 quotation mark, U+201E NEW -->
320         {"\u2020", "&dagger;"}, // dagger, U+2020 ISOpub -->
321         {"\u2021", "&Dagger;"}, // double dagger, U+2021 ISOpub -->
322         {"\u2030", "&permil;"}, // per mille sign, U+2030 ISOtech -->
323         {"\u2039", "&lsaquo;"}, // single left-pointing angle quotation mark, U+2039 ISO proposed -->
324         // <!-- lsaquo is proposed but not yet ISO standardized -->
325         {"\u203A", "&rsaquo;"}, // single right-pointing angle quotation mark, U+203A ISO proposed -->
326         // <!-- rsaquo is proposed but not yet ISO standardized -->
327         {"\u20AC", "&euro;"}, // -- euro sign, U+20AC NEW -->
328     };
329 
330     private static final String[][] HTML40_EXTENDED_UNESCAPE = invert(HTML40_EXTENDED_ESCAPE);
331 
332     private static final String[][] BASIC_ESCAPE = {
333         {"\"", "&quot;"}, // " - double-quote
334         {"&", "&amp;"},   // & - ampersand
335         {"<", "&lt;"},    // < - less-than
336         {">", "&gt;"},    // > - greater-than
337     };
338 
339     private static final String[][] BASIC_UNESCAPE = invert(BASIC_ESCAPE);
340 
341     private static final String[][] APOS_ESCAPE = {
342         {"'", "&apos;"}, // XML apostrophe
343     };
344 
345     private static final String[][] APOS_UNESCAPE = invert(APOS_ESCAPE);
346 
347     private static final String[][] JAVA_CTRL_CHARS_ESCAPE = {
348         {"\b", "\\b"},
349         {"\n", "\\n"},
350         {"\t", "\\t"},
351         {"\f", "\\f"},
352         {"\r", "\\r"}
353     };
354 
355     private static final String[][] JAVA_CTRL_CHARS_UNESCAPE = invert(JAVA_CTRL_CHARS_ESCAPE);
356 
357     /**
358      * Mapping to escape the apostrophe character to its XML character entity.
359      * @return the mapping table
360      */
361     public static String[][] APOS_ESCAPE() {
362         return APOS_ESCAPE.clone();
363     }
364 
365     /**
366      * Reverse of {@link #APOS_ESCAPE()} for unescaping purposes.
367      * @return the mapping table
368      */
369     public static String[][] APOS_UNESCAPE() {
370         return APOS_UNESCAPE.clone();
371     }
372 
373     /**
374      * Mapping to escape the basic XML and HTML character entities.
375      *
376      * Namely: {@code " & < >}
377      * @return the mapping table
378      */
379     public static String[][] BASIC_ESCAPE() {
380         return BASIC_ESCAPE.clone();
381     }
382 
383     /**
384      * Reverse of {@link #BASIC_ESCAPE()} for unescaping purposes.
385      * @return the mapping table
386      */
387     public static String[][] BASIC_UNESCAPE() {
388         return BASIC_UNESCAPE.clone();
389     }
390 
391     /**
392      * Mapping to escape additional <a href="https://www.w3.org/TR/REC-html40/sgml/entities.html">character entity
393      * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE()} to get the full list of
394      * HTML 4.0 character entities.
395      * @return the mapping table
396      */
397     public static String[][] HTML40_EXTENDED_ESCAPE() {
398         return HTML40_EXTENDED_ESCAPE.clone();
399     }
400 
401     /**
402      * Reverse of {@link #HTML40_EXTENDED_ESCAPE()} for unescaping purposes.
403      * @return the mapping table
404      */
405     public static String[][] HTML40_EXTENDED_UNESCAPE() {
406         return HTML40_EXTENDED_UNESCAPE.clone();
407     }
408 
409     /**
410      * Used to invert an escape array into an unescape array
411      * @param array String[][] to be inverted
412      * @return String[][] inverted array
413      */
414     public static String[][] invert(final String[][] array) {
415         final String[][] newarray = new String[array.length][2];
416         for (int i = 0; i<array.length; i++) {
417             newarray[i][0] = array[i][1];
418             newarray[i][1] = array[i][0];
419         }
420         return newarray;
421     }
422 
423     /**
424      * Mapping to escape <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1">ISO-8859-1</a>
425      * characters to their named HTML 3.x equivalents.
426      * @return the mapping table
427      */
428     public static String[][] ISO8859_1_ESCAPE() {
429         return ISO8859_1_ESCAPE.clone();
430     }
431 
432     /**
433      * Reverse of {@link #ISO8859_1_ESCAPE()} for unescaping purposes.
434      * @return the mapping table
435      */
436     public static String[][] ISO8859_1_UNESCAPE() {
437         return ISO8859_1_UNESCAPE.clone();
438     }
439 
440     /**
441      * Mapping to escape the Java control characters.
442      *
443      * Namely: {@code \b \n \t \f \r}
444      * @return the mapping table
445      */
446     public static String[][] JAVA_CTRL_CHARS_ESCAPE() {
447         return JAVA_CTRL_CHARS_ESCAPE.clone();
448     }
449 
450     /**
451      * Reverse of {@link #JAVA_CTRL_CHARS_ESCAPE()} for unescaping purposes.
452      * @return the mapping table
453      */
454     public static String[][] JAVA_CTRL_CHARS_UNESCAPE() {
455         return JAVA_CTRL_CHARS_UNESCAPE.clone();
456     }
457 
458 }