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 |
|
---|
18 | /* Taken from: http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/java/org/apache/commons/lang/Entities.java?revision=636641 */
|
---|
19 | package org.openstreetmap.josm.data.validation.util;
|
---|
20 |
|
---|
21 | import java.util.HashMap;
|
---|
22 | import java.util.Map;
|
---|
23 |
|
---|
24 | /**
|
---|
25 | * <p>
|
---|
26 | * Provides HTML and XML entity utilities.
|
---|
27 | * </p>
|
---|
28 | * @see <a href="http://hotwired.lycos.com/webmonkey/reference/special_characters/">ISO Entities</a>
|
---|
29 | * @see <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO Latin-1</a>
|
---|
30 | * @see <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity references</a>
|
---|
31 | * @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a>
|
---|
32 | * @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a>
|
---|
33 | */
|
---|
34 | public class Entities {
|
---|
35 | private static final String[][] ARRAY = {
|
---|
36 | /* BASIC */
|
---|
37 | {"quot", "34"}, // " - double-quote
|
---|
38 | {"amp", "38"}, // & - ampersand
|
---|
39 | {"lt", "60"}, // < - less-than
|
---|
40 | {"gt", "62"}, // > - greater-than
|
---|
41 | /* XML */
|
---|
42 | {"apos", "39"}, // XML apostrophe
|
---|
43 | /* ISO8859_1 */
|
---|
44 | {"nbsp", "160"}, // non-breaking space
|
---|
45 | {"iexcl", "161"}, // inverted exclamation mark
|
---|
46 | {"cent", "162"}, // cent sign
|
---|
47 | {"pound", "163"}, // pound sign
|
---|
48 | {"curren", "164"}, // currency sign
|
---|
49 | {"yen", "165"}, // yen sign = yuan sign
|
---|
50 | {"brvbar", "166"}, // broken bar = broken vertical bar
|
---|
51 | {"sect", "167"}, // section sign
|
---|
52 | {"uml", "168"}, // diaeresis = spacing diaeresis
|
---|
53 | {"copy", "169"}, // © - copyright sign
|
---|
54 | {"ordf", "170"}, // feminine ordinal indicator
|
---|
55 | {"laquo", "171"}, // left-pointing double angle quotation mark = left pointing guillemet
|
---|
56 | {"not", "172"}, // not sign
|
---|
57 | {"shy", "173"}, // soft hyphen = discretionary hyphen
|
---|
58 | {"reg", "174"}, // ® - registered trademark sign
|
---|
59 | {"macr", "175"}, // macron = spacing macron = overline = APL overbar
|
---|
60 | {"deg", "176"}, // degree sign
|
---|
61 | {"plusmn", "177"}, // plus-minus sign = plus-or-minus sign
|
---|
62 | {"sup2", "178"}, // superscript two = superscript digit two = squared
|
---|
63 | {"sup3", "179"}, // superscript three = superscript digit three = cubed
|
---|
64 | {"acute", "180"}, // acute accent = spacing acute
|
---|
65 | {"micro", "181"}, // micro sign
|
---|
66 | {"para", "182"}, // pilcrow sign = paragraph sign
|
---|
67 | {"middot", "183"}, // middle dot = Georgian comma = Greek middle dot
|
---|
68 | {"cedil", "184"}, // cedilla = spacing cedilla
|
---|
69 | {"sup1", "185"}, // superscript one = superscript digit one
|
---|
70 | {"ordm", "186"}, // masculine ordinal indicator
|
---|
71 | {"raquo", "187"}, // right-pointing double angle quotation mark = right pointing guillemet
|
---|
72 | {"frac14", "188"}, // vulgar fraction one quarter = fraction one quarter
|
---|
73 | {"frac12", "189"}, // vulgar fraction one half = fraction one half
|
---|
74 | {"frac34", "190"}, // vulgar fraction three quarters = fraction three quarters
|
---|
75 | {"iquest", "191"}, // inverted question mark = turned question mark
|
---|
76 | {"Agrave", "192"}, // À - uppercase A, grave accent
|
---|
77 | {"Aacute", "193"}, // Á - uppercase A, acute accent
|
---|
78 | {"Acirc", "194"}, // Â - uppercase A, circumflex accent
|
---|
79 | {"Atilde", "195"}, // Ã - uppercase A, tilde
|
---|
80 | {"Auml", "196"}, // Ä - uppercase A, umlaut
|
---|
81 | {"Aring", "197"}, // Å - uppercase A, ring
|
---|
82 | {"AElig", "198"}, // Æ - uppercase AE
|
---|
83 | {"Ccedil", "199"}, // Ç - uppercase C, cedilla
|
---|
84 | {"Egrave", "200"}, // È - uppercase E, grave accent
|
---|
85 | {"Eacute", "201"}, // É - uppercase E, acute accent
|
---|
86 | {"Ecirc", "202"}, // Ê - uppercase E, circumflex accent
|
---|
87 | {"Euml", "203"}, // Ë - uppercase E, umlaut
|
---|
88 | {"Igrave", "204"}, // Ì - uppercase I, grave accent
|
---|
89 | {"Iacute", "205"}, // Í - uppercase I, acute accent
|
---|
90 | {"Icirc", "206"}, // Î - uppercase I, circumflex accent
|
---|
91 | {"Iuml", "207"}, // Ï - uppercase I, umlaut
|
---|
92 | {"ETH", "208"}, // Ð - uppercase Eth, Icelandic
|
---|
93 | {"Ntilde", "209"}, // Ñ - uppercase N, tilde
|
---|
94 | {"Ograve", "210"}, // Ò - uppercase O, grave accent
|
---|
95 | {"Oacute", "211"}, // Ó - uppercase O, acute accent
|
---|
96 | {"Ocirc", "212"}, // Ô - uppercase O, circumflex accent
|
---|
97 | {"Otilde", "213"}, // Õ - uppercase O, tilde
|
---|
98 | {"Ouml", "214"}, // Ö - uppercase O, umlaut
|
---|
99 | {"times", "215"}, // multiplication sign
|
---|
100 | {"Oslash", "216"}, // Ø - uppercase O, slash
|
---|
101 | {"Ugrave", "217"}, // Ù - uppercase U, grave accent
|
---|
102 | {"Uacute", "218"}, // Ú - uppercase U, acute accent
|
---|
103 | {"Ucirc", "219"}, // Û - uppercase U, circumflex accent
|
---|
104 | {"Uuml", "220"}, // Ü - uppercase U, umlaut
|
---|
105 | {"Yacute", "221"}, // Ý - uppercase Y, acute accent
|
---|
106 | {"THORN", "222"}, // Þ - uppercase THORN, Icelandic
|
---|
107 | {"szlig", "223"}, // ß - lowercase sharps, German
|
---|
108 | {"agrave", "224"}, // à - lowercase a, grave accent
|
---|
109 | {"aacute", "225"}, // á - lowercase a, acute accent
|
---|
110 | {"acirc", "226"}, // â - lowercase a, circumflex accent
|
---|
111 | {"atilde", "227"}, // ã - lowercase a, tilde
|
---|
112 | {"auml", "228"}, // ä - lowercase a, umlaut
|
---|
113 | {"aring", "229"}, // å - lowercase a, ring
|
---|
114 | {"aelig", "230"}, // æ - lowercase ae
|
---|
115 | {"ccedil", "231"}, // ç - lowercase c, cedilla
|
---|
116 | {"egrave", "232"}, // è - lowercase e, grave accent
|
---|
117 | {"eacute", "233"}, // é - lowercase e, acute accent
|
---|
118 | {"ecirc", "234"}, // ê - lowercase e, circumflex accent
|
---|
119 | {"euml", "235"}, // ë - lowercase e, umlaut
|
---|
120 | {"igrave", "236"}, // ì - lowercase i, grave accent
|
---|
121 | {"iacute", "237"}, // í - lowercase i, acute accent
|
---|
122 | {"icirc", "238"}, // î - lowercase i, circumflex accent
|
---|
123 | {"iuml", "239"}, // ï - lowercase i, umlaut
|
---|
124 | {"eth", "240"}, // ð - lowercase eth, Icelandic
|
---|
125 | {"ntilde", "241"}, // ñ - lowercase n, tilde
|
---|
126 | {"ograve", "242"}, // ò - lowercase o, grave accent
|
---|
127 | {"oacute", "243"}, // ó - lowercase o, acute accent
|
---|
128 | {"ocirc", "244"}, // ô - lowercase o, circumflex accent
|
---|
129 | {"otilde", "245"}, // õ - lowercase o, tilde
|
---|
130 | {"ouml", "246"}, // ö - lowercase o, umlaut
|
---|
131 | {"divide", "247"}, // division sign
|
---|
132 | {"oslash", "248"}, // ø - lowercase o, slash
|
---|
133 | {"ugrave", "249"}, // ù - lowercase u, grave accent
|
---|
134 | {"uacute", "250"}, // ú - lowercase u, acute accent
|
---|
135 | {"ucirc", "251"}, // û - lowercase u, circumflex accent
|
---|
136 | {"uuml", "252"}, // ü - lowercase u, umlaut
|
---|
137 | {"yacute", "253"}, // ý - lowercase y, acute accent
|
---|
138 | {"thorn", "254"}, // þ - lowercase thorn, Icelandic
|
---|
139 | {"yuml", "255"}, // ÿ - lowercase y, umlaut
|
---|
140 | /* HTML 40 */
|
---|
141 | // <!-- Latin Extended-B -->
|
---|
142 | {"fnof", "402"}, // latin small f with hook = function= florin, U+0192 ISOtech -->
|
---|
143 | // <!-- Greek -->
|
---|
144 | {"Alpha", "913"}, // greek capital letter alpha, U+0391 -->
|
---|
145 | {"Beta", "914"}, // greek capital letter beta, U+0392 -->
|
---|
146 | {"Gamma", "915"}, // greek capital letter gamma,U+0393 ISOgrk3 -->
|
---|
147 | {"Delta", "916"}, // greek capital letter delta,U+0394 ISOgrk3 -->
|
---|
148 | {"Epsilon", "917"}, // greek capital letter epsilon, U+0395 -->
|
---|
149 | {"Zeta", "918"}, // greek capital letter zeta, U+0396 -->
|
---|
150 | {"Eta", "919"}, // greek capital letter eta, U+0397 -->
|
---|
151 | {"Theta", "920"}, // greek capital letter theta,U+0398 ISOgrk3 -->
|
---|
152 | {"Iota", "921"}, // greek capital letter iota, U+0399 -->
|
---|
153 | {"Kappa", "922"}, // greek capital letter kappa, U+039A -->
|
---|
154 | {"Lambda", "923"}, // greek capital letter lambda,U+039B ISOgrk3 -->
|
---|
155 | {"Mu", "924"}, // greek capital letter mu, U+039C -->
|
---|
156 | {"Nu", "925"}, // greek capital letter nu, U+039D -->
|
---|
157 | {"Xi", "926"}, // greek capital letter xi, U+039E ISOgrk3 -->
|
---|
158 | {"Omicron", "927"}, // greek capital letter omicron, U+039F -->
|
---|
159 | {"Pi", "928"}, // greek capital letter pi, U+03A0 ISOgrk3 -->
|
---|
160 | {"Rho", "929"}, // greek capital letter rho, U+03A1 -->
|
---|
161 | // <!-- there is no Sigmaf, and no U+03A2 character either -->
|
---|
162 | {"Sigma", "931"}, // greek capital letter sigma,U+03A3 ISOgrk3 -->
|
---|
163 | {"Tau", "932"}, // greek capital letter tau, U+03A4 -->
|
---|
164 | {"Upsilon", "933"}, // greek capital letter upsilon,U+03A5 ISOgrk3 -->
|
---|
165 | {"Phi", "934"}, // greek capital letter phi,U+03A6 ISOgrk3 -->
|
---|
166 | {"Chi", "935"}, // greek capital letter chi, U+03A7 -->
|
---|
167 | {"Psi", "936"}, // greek capital letter psi,U+03A8 ISOgrk3 -->
|
---|
168 | {"Omega", "937"}, // greek capital letter omega,U+03A9 ISOgrk3 -->
|
---|
169 | {"alpha", "945"}, // greek small letter alpha,U+03B1 ISOgrk3 -->
|
---|
170 | {"beta", "946"}, // greek small letter beta, U+03B2 ISOgrk3 -->
|
---|
171 | {"gamma", "947"}, // greek small letter gamma,U+03B3 ISOgrk3 -->
|
---|
172 | {"delta", "948"}, // greek small letter delta,U+03B4 ISOgrk3 -->
|
---|
173 | {"epsilon", "949"}, // greek small letter epsilon,U+03B5 ISOgrk3 -->
|
---|
174 | {"zeta", "950"}, // greek small letter zeta, U+03B6 ISOgrk3 -->
|
---|
175 | {"eta", "951"}, // greek small letter eta, U+03B7 ISOgrk3 -->
|
---|
176 | {"theta", "952"}, // greek small letter theta,U+03B8 ISOgrk3 -->
|
---|
177 | {"iota", "953"}, // greek small letter iota, U+03B9 ISOgrk3 -->
|
---|
178 | {"kappa", "954"}, // greek small letter kappa,U+03BA ISOgrk3 -->
|
---|
179 | {"lambda", "955"}, // greek small letter lambda,U+03BB ISOgrk3 -->
|
---|
180 | {"mu", "956"}, // greek small letter mu, U+03BC ISOgrk3 -->
|
---|
181 | {"nu", "957"}, // greek small letter nu, U+03BD ISOgrk3 -->
|
---|
182 | {"xi", "958"}, // greek small letter xi, U+03BE ISOgrk3 -->
|
---|
183 | {"omicron", "959"}, // greek small letter omicron, U+03BF NEW -->
|
---|
184 | {"pi", "960"}, // greek small letter pi, U+03C0 ISOgrk3 -->
|
---|
185 | {"rho", "961"}, // greek small letter rho, U+03C1 ISOgrk3 -->
|
---|
186 | {"sigmaf", "962"}, // greek small letter final sigma,U+03C2 ISOgrk3 -->
|
---|
187 | {"sigma", "963"}, // greek small letter sigma,U+03C3 ISOgrk3 -->
|
---|
188 | {"tau", "964"}, // greek small letter tau, U+03C4 ISOgrk3 -->
|
---|
189 | {"upsilon", "965"}, // greek small letter upsilon,U+03C5 ISOgrk3 -->
|
---|
190 | {"phi", "966"}, // greek small letter phi, U+03C6 ISOgrk3 -->
|
---|
191 | {"chi", "967"}, // greek small letter chi, U+03C7 ISOgrk3 -->
|
---|
192 | {"psi", "968"}, // greek small letter psi, U+03C8 ISOgrk3 -->
|
---|
193 | {"omega", "969"}, // greek small letter omega,U+03C9 ISOgrk3 -->
|
---|
194 | {"thetasym", "977"}, // greek small letter theta symbol,U+03D1 NEW -->
|
---|
195 | {"upsih", "978"}, // greek upsilon with hook symbol,U+03D2 NEW -->
|
---|
196 | {"piv", "982"}, // greek pi symbol, U+03D6 ISOgrk3 -->
|
---|
197 | // <!-- General Punctuation -->
|
---|
198 | {"bull", "8226"}, // bullet = black small circle,U+2022 ISOpub -->
|
---|
199 | // <!-- bullet is NOT the same as bullet operator, U+2219 -->
|
---|
200 | {"hellip", "8230"}, // horizontal ellipsis = three dot leader,U+2026 ISOpub -->
|
---|
201 | {"prime", "8242"}, // prime = minutes = feet, U+2032 ISOtech -->
|
---|
202 | {"Prime", "8243"}, // double prime = seconds = inches,U+2033 ISOtech -->
|
---|
203 | {"oline", "8254"}, // overline = spacing overscore,U+203E NEW -->
|
---|
204 | {"frasl", "8260"}, // fraction slash, U+2044 NEW -->
|
---|
205 | // <!-- Letterlike Symbols -->
|
---|
206 | {"weierp", "8472"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso -->
|
---|
207 | {"image", "8465"}, // blackletter capital I = imaginary part,U+2111 ISOamso -->
|
---|
208 | {"real", "8476"}, // blackletter capital R = real part symbol,U+211C ISOamso -->
|
---|
209 | {"trade", "8482"}, // trade mark sign, U+2122 ISOnum -->
|
---|
210 | {"alefsym", "8501"}, // alef symbol = first transfinite cardinal,U+2135 NEW -->
|
---|
211 | // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the
|
---|
212 | // same glyph could be used to depict both characters -->
|
---|
213 | // <!-- Arrows -->
|
---|
214 | {"larr", "8592"}, // leftwards arrow, U+2190 ISOnum -->
|
---|
215 | {"uarr", "8593"}, // upwards arrow, U+2191 ISOnum-->
|
---|
216 | {"rarr", "8594"}, // rightwards arrow, U+2192 ISOnum -->
|
---|
217 | {"darr", "8595"}, // downwards arrow, U+2193 ISOnum -->
|
---|
218 | {"harr", "8596"}, // left right arrow, U+2194 ISOamsa -->
|
---|
219 | {"crarr", "8629"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
|
---|
220 | {"lArr", "8656"}, // leftwards double arrow, U+21D0 ISOtech -->
|
---|
221 | // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'
|
---|
222 | // arrow but also does not have any other character for that function.
|
---|
223 | // So ? lArr canbe used for 'is implied by' as ISOtech suggests -->
|
---|
224 | {"uArr", "8657"}, // upwards double arrow, U+21D1 ISOamsa -->
|
---|
225 | {"rArr", "8658"}, // rightwards double arrow,U+21D2 ISOtech -->
|
---|
226 | // <!-- ISO 10646 does not say this is the 'implies' character but does not
|
---|
227 | // have another character with this function so ?rArr can be used for
|
---|
228 | // 'implies' as ISOtech suggests -->
|
---|
229 | {"dArr", "8659"}, // downwards double arrow, U+21D3 ISOamsa -->
|
---|
230 | {"hArr", "8660"}, // left right double arrow,U+21D4 ISOamsa -->
|
---|
231 | // <!-- Mathematical Operators -->
|
---|
232 | {"forall", "8704"}, // for all, U+2200 ISOtech -->
|
---|
233 | {"part", "8706"}, // partial differential, U+2202 ISOtech -->
|
---|
234 | {"exist", "8707"}, // there exists, U+2203 ISOtech -->
|
---|
235 | {"empty", "8709"}, // empty set = null set = diameter,U+2205 ISOamso -->
|
---|
236 | {"nabla", "8711"}, // nabla = backward difference,U+2207 ISOtech -->
|
---|
237 | {"isin", "8712"}, // element of, U+2208 ISOtech -->
|
---|
238 | {"notin", "8713"}, // not an element of, U+2209 ISOtech -->
|
---|
239 | {"ni", "8715"}, // contains as member, U+220B ISOtech -->
|
---|
240 | // <!-- should there be a more memorable name than 'ni'? -->
|
---|
241 | {"prod", "8719"}, // n-ary product = product sign,U+220F ISOamsb -->
|
---|
242 | // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'
|
---|
243 | // though the same glyph might be used for both -->
|
---|
244 | {"sum", "8721"}, // n-ary summation, U+2211 ISOamsb -->
|
---|
245 | // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
|
---|
246 | // though the same glyph might be used for both -->
|
---|
247 | {"minus", "8722"}, // minus sign, U+2212 ISOtech -->
|
---|
248 | {"lowast", "8727"}, // asterisk operator, U+2217 ISOtech -->
|
---|
249 | {"radic", "8730"}, // square root = radical sign,U+221A ISOtech -->
|
---|
250 | {"prop", "8733"}, // proportional to, U+221D ISOtech -->
|
---|
251 | {"infin", "8734"}, // infinity, U+221E ISOtech -->
|
---|
252 | {"ang", "8736"}, // angle, U+2220 ISOamso -->
|
---|
253 | {"and", "8743"}, // logical and = wedge, U+2227 ISOtech -->
|
---|
254 | {"or", "8744"}, // logical or = vee, U+2228 ISOtech -->
|
---|
255 | {"cap", "8745"}, // intersection = cap, U+2229 ISOtech -->
|
---|
256 | {"cup", "8746"}, // union = cup, U+222A ISOtech -->
|
---|
257 | {"int", "8747"}, // integral, U+222B ISOtech -->
|
---|
258 | {"there4", "8756"}, // therefore, U+2234 ISOtech -->
|
---|
259 | {"sim", "8764"}, // tilde operator = varies with = similar to,U+223C ISOtech -->
|
---|
260 | // <!-- tilde operator is NOT the same character as the tilde, U+007E,although
|
---|
261 | // the same glyph might be used to represent both -->
|
---|
262 | {"cong", "8773"}, // approximately equal to, U+2245 ISOtech -->
|
---|
263 | {"asymp", "8776"}, // almost equal to = asymptotic to,U+2248 ISOamsr -->
|
---|
264 | {"ne", "8800"}, // not equal to, U+2260 ISOtech -->
|
---|
265 | {"equiv", "8801"}, // identical to, U+2261 ISOtech -->
|
---|
266 | {"le", "8804"}, // less-than or equal to, U+2264 ISOtech -->
|
---|
267 | {"ge", "8805"}, // greater-than or equal to,U+2265 ISOtech -->
|
---|
268 | {"sub", "8834"}, // subset of, U+2282 ISOtech -->
|
---|
269 | {"sup", "8835"}, // superset of, U+2283 ISOtech -->
|
---|
270 | // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the
|
---|
271 | // Symbol font encoding and is not included. Should it be, for symmetry?
|
---|
272 | // It is in ISOamsn --> <!ENTITY nsub", "8836"},
|
---|
273 | // not a subset of, U+2284 ISOamsn -->
|
---|
274 | {"sube", "8838"}, // subset of or equal to, U+2286 ISOtech -->
|
---|
275 | {"supe", "8839"}, // superset of or equal to,U+2287 ISOtech -->
|
---|
276 | {"oplus", "8853"}, // circled plus = direct sum,U+2295 ISOamsb -->
|
---|
277 | {"otimes", "8855"}, // circled times = vector product,U+2297 ISOamsb -->
|
---|
278 | {"perp", "8869"}, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech -->
|
---|
279 | {"sdot", "8901"}, // dot operator, U+22C5 ISOamsb -->
|
---|
280 | // <!-- dot operator is NOT the same character as U+00B7 middle dot -->
|
---|
281 | // <!-- Miscellaneous Technical -->
|
---|
282 | {"lceil", "8968"}, // left ceiling = apl upstile,U+2308 ISOamsc -->
|
---|
283 | {"rceil", "8969"}, // right ceiling, U+2309 ISOamsc -->
|
---|
284 | {"lfloor", "8970"}, // left floor = apl downstile,U+230A ISOamsc -->
|
---|
285 | {"rfloor", "8971"}, // right floor, U+230B ISOamsc -->
|
---|
286 | {"lang", "9001"}, // left-pointing angle bracket = bra,U+2329 ISOtech -->
|
---|
287 | // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation
|
---|
288 | // mark' -->
|
---|
289 | {"rang", "9002"}, // right-pointing angle bracket = ket,U+232A ISOtech -->
|
---|
290 | // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A
|
---|
291 | // 'single right-pointing angle quotation mark' -->
|
---|
292 | // <!-- Geometric Shapes -->
|
---|
293 | {"loz", "9674"}, // lozenge, U+25CA ISOpub -->
|
---|
294 | // <!-- Miscellaneous Symbols -->
|
---|
295 | {"spades", "9824"}, // black spade suit, U+2660 ISOpub -->
|
---|
296 | // <!-- black here seems to mean filled as opposed to hollow -->
|
---|
297 | {"clubs", "9827"}, // black club suit = shamrock,U+2663 ISOpub -->
|
---|
298 | {"hearts", "9829"}, // black heart suit = valentine,U+2665 ISOpub -->
|
---|
299 | {"diams", "9830"}, // black diamond suit, U+2666 ISOpub -->
|
---|
300 |
|
---|
301 | // <!-- Latin Extended-A -->
|
---|
302 | {"OElig", "338"}, // -- latin capital ligature OE,U+0152 ISOlat2 -->
|
---|
303 | {"oelig", "339"}, // -- latin small ligature oe, U+0153 ISOlat2 -->
|
---|
304 | // <!-- ligature is a misnomer, this is a separate character in some languages -->
|
---|
305 | {"Scaron", "352"}, // -- latin capital letter S with caron,U+0160 ISOlat2 -->
|
---|
306 | {"scaron", "353"}, // -- latin small letter s with caron,U+0161 ISOlat2 -->
|
---|
307 | {"Yuml", "376"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 -->
|
---|
308 | // <!-- Spacing Modifier Letters -->
|
---|
309 | {"circ", "710"}, // -- modifier letter circumflex accent,U+02C6 ISOpub -->
|
---|
310 | {"tilde", "732"}, // small tilde, U+02DC ISOdia -->
|
---|
311 | // <!-- General Punctuation -->
|
---|
312 | {"ensp", "8194"}, // en space, U+2002 ISOpub -->
|
---|
313 | {"emsp", "8195"}, // em space, U+2003 ISOpub -->
|
---|
314 | {"thinsp", "8201"}, // thin space, U+2009 ISOpub -->
|
---|
315 | {"zwnj", "8204"}, // zero width non-joiner,U+200C NEW RFC 2070 -->
|
---|
316 | {"zwj", "8205"}, // zero width joiner, U+200D NEW RFC 2070 -->
|
---|
317 | {"lrm", "8206"}, // left-to-right mark, U+200E NEW RFC 2070 -->
|
---|
318 | {"rlm", "8207"}, // right-to-left mark, U+200F NEW RFC 2070 -->
|
---|
319 | {"ndash", "8211"}, // en dash, U+2013 ISOpub -->
|
---|
320 | {"mdash", "8212"}, // em dash, U+2014 ISOpub -->
|
---|
321 | {"lsquo", "8216"}, // left single quotation mark,U+2018 ISOnum -->
|
---|
322 | {"rsquo", "8217"}, // right single quotation mark,U+2019 ISOnum -->
|
---|
323 | {"sbquo", "8218"}, // single low-9 quotation mark, U+201A NEW -->
|
---|
324 | {"ldquo", "8220"}, // left double quotation mark,U+201C ISOnum -->
|
---|
325 | {"rdquo", "8221"}, // right double quotation mark,U+201D ISOnum -->
|
---|
326 | {"bdquo", "8222"}, // double low-9 quotation mark, U+201E NEW -->
|
---|
327 | {"dagger", "8224"}, // dagger, U+2020 ISOpub -->
|
---|
328 | {"Dagger", "8225"}, // double dagger, U+2021 ISOpub -->
|
---|
329 | {"permil", "8240"}, // per mille sign, U+2030 ISOtech -->
|
---|
330 | {"lsaquo", "8249"}, // single left-pointing angle quotation mark,U+2039 ISO proposed -->
|
---|
331 | // <!-- lsaquo is proposed but not yet ISO standardized -->
|
---|
332 | {"rsaquo", "8250"}, // single right-pointing angle quotation mark,U+203A ISO proposed -->
|
---|
333 | // <!-- rsaquo is proposed but not yet ISO standardized -->
|
---|
334 | {"euro", "8364"}, // -- euro sign, U+20AC NEW -->
|
---|
335 | };
|
---|
336 |
|
---|
337 | private static Map<String, String> mapNameToValue = null;
|
---|
338 |
|
---|
339 | public String unescape(String str) {
|
---|
340 | int firstAmp = str.indexOf('&');
|
---|
341 | if (firstAmp < 0)
|
---|
342 | return str;
|
---|
343 | String res = str.substring(0, firstAmp);
|
---|
344 | int len = str.length();
|
---|
345 | for (int i = firstAmp; i < len; i++) {
|
---|
346 | char c = str.charAt(i);
|
---|
347 | if (c == '&') {
|
---|
348 | int nextIdx = i + 1;
|
---|
349 | int semiColonIdx = str.indexOf(';', nextIdx);
|
---|
350 | if (semiColonIdx == -1) {
|
---|
351 | res += c;
|
---|
352 | continue;
|
---|
353 | }
|
---|
354 | int amphersandIdx = str.indexOf('&', i + 1);
|
---|
355 | if (amphersandIdx != -1 && amphersandIdx < semiColonIdx) {
|
---|
356 | // Then the text looks like &...&...;
|
---|
357 | res += c;
|
---|
358 | continue;
|
---|
359 | }
|
---|
360 | String entityContent = str.substring(nextIdx, semiColonIdx);
|
---|
361 | int entityValue = -1;
|
---|
362 | int entityContentLen = entityContent.length();
|
---|
363 | if (entityContentLen > 0) {
|
---|
364 | if (entityContent.charAt(0) == '#') { // escaped value content is an integer (decimal or
|
---|
365 | // hexidecimal)
|
---|
366 | if (entityContentLen > 1) {
|
---|
367 | char isHexChar = entityContent.charAt(1);
|
---|
368 | try {
|
---|
369 | switch (isHexChar) {
|
---|
370 | case 'X' :
|
---|
371 | case 'x' : {
|
---|
372 | entityValue = Integer.parseInt(entityContent.substring(2), 16);
|
---|
373 | break;
|
---|
374 | }
|
---|
375 | default : {
|
---|
376 | entityValue = Integer.parseInt(entityContent.substring(1), 10);
|
---|
377 | }
|
---|
378 | }
|
---|
379 | if (entityValue > 0xFFFF) {
|
---|
380 | entityValue = -1;
|
---|
381 | }
|
---|
382 | } catch (NumberFormatException e) {
|
---|
383 | entityValue = -1;
|
---|
384 | }
|
---|
385 | }
|
---|
386 | } else { // escaped value content is an entity name
|
---|
387 | if(mapNameToValue == null)
|
---|
388 | {
|
---|
389 | mapNameToValue = new HashMap<String, String>();
|
---|
390 | for (String[] pair : ARRAY)
|
---|
391 | mapNameToValue.put(pair[0], pair[1]);
|
---|
392 | }
|
---|
393 | String value = mapNameToValue.get(entityContent);
|
---|
394 | entityValue = (value == null ? -1 : Integer.parseInt(value));
|
---|
395 | }
|
---|
396 | }
|
---|
397 |
|
---|
398 | if (entityValue == -1) {
|
---|
399 | res += '&' + entityContent + ';';
|
---|
400 | } else {
|
---|
401 | res += (char) entityValue;
|
---|
402 | }
|
---|
403 | i = semiColonIdx; // move index up to the semi-colon
|
---|
404 | } else {
|
---|
405 | res += c;
|
---|
406 | }
|
---|
407 | }
|
---|
408 | return res;
|
---|
409 | }
|
---|
410 | }
|
---|