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 * https://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 */ 017 018/* Taken from: http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/java/org/apache/commons/lang/Entities.java?revision=636641 */ 019package org.openstreetmap.josm.data.validation.util; 020 021import java.util.HashMap; 022import java.util.Map; 023 024/** 025 * <p> 026 * Provides HTML and XML entity utilities. 027 * </p> 028 * @see <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO Latin-1</a> 029 * @see <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity references</a> 030 * @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a> 031 * @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a> 032 */ 033public final class Entities { 034 private static final String[][] ARRAY = { 035 /* BASIC */ 036 {"quot", "34"}, // " - double-quote 037 {"amp", "38"}, // & - ampersand 038 {"lt", "60"}, // < - less-than 039 {"gt", "62"}, // > - greater-than 040 /* XML */ 041 {"apos", "39"}, // XML apostrophe 042 /* ISO8859_1 */ 043 {"nbsp", "160"}, // non-breaking space 044 {"iexcl", "161"}, // inverted exclamation mark 045 {"cent", "162"}, // cent sign 046 {"pound", "163"}, // pound sign 047 {"curren", "164"}, // currency sign 048 {"yen", "165"}, // yen sign = yuan sign 049 {"brvbar", "166"}, // broken bar = broken vertical bar 050 {"sect", "167"}, // section sign 051 {"uml", "168"}, // diaeresis = spacing diaeresis 052 {"copy", "169"}, // © - copyright sign 053 {"ordf", "170"}, // feminine ordinal indicator 054 {"laquo", "171"}, // left-pointing double angle quotation mark = left pointing guillemet 055 {"not", "172"}, // not sign 056 {"shy", "173"}, // soft hyphen = discretionary hyphen 057 {"reg", "174"}, // ® - registered trademark sign 058 {"macr", "175"}, // macron = spacing macron = overline = APL overbar 059 {"deg", "176"}, // degree sign 060 {"plusmn", "177"}, // plus-minus sign = plus-or-minus sign 061 {"sup2", "178"}, // superscript two = superscript digit two = squared 062 {"sup3", "179"}, // superscript three = superscript digit three = cubed 063 {"acute", "180"}, // acute accent = spacing acute 064 {"micro", "181"}, // micro sign 065 {"para", "182"}, // pilcrow sign = paragraph sign 066 {"middot", "183"}, // middle dot = Georgian comma = Greek middle dot 067 {"cedil", "184"}, // cedilla = spacing cedilla 068 {"sup1", "185"}, // superscript one = superscript digit one 069 {"ordm", "186"}, // masculine ordinal indicator 070 {"raquo", "187"}, // right-pointing double angle quotation mark = right pointing guillemet 071 {"frac14", "188"}, // vulgar fraction one quarter = fraction one quarter 072 {"frac12", "189"}, // vulgar fraction one half = fraction one half 073 {"frac34", "190"}, // vulgar fraction three quarters = fraction three quarters 074 {"iquest", "191"}, // inverted question mark = turned question mark 075 {"Agrave", "192"}, // À - uppercase A, grave accent 076 {"Aacute", "193"}, // Á - uppercase A, acute accent 077 {"Acirc", "194"}, // Â - uppercase A, circumflex accent 078 {"Atilde", "195"}, // Ã - uppercase A, tilde 079 {"Auml", "196"}, // Ä - uppercase A, umlaut 080 {"Aring", "197"}, // Å - uppercase A, ring 081 {"AElig", "198"}, // Æ - uppercase AE 082 {"Ccedil", "199"}, // Ç - uppercase C, cedilla 083 {"Egrave", "200"}, // È - uppercase E, grave accent 084 {"Eacute", "201"}, // É - uppercase E, acute accent 085 {"Ecirc", "202"}, // Ê - uppercase E, circumflex accent 086 {"Euml", "203"}, // Ë - uppercase E, umlaut 087 {"Igrave", "204"}, // Ì - uppercase I, grave accent 088 {"Iacute", "205"}, // Í - uppercase I, acute accent 089 {"Icirc", "206"}, // Î - uppercase I, circumflex accent 090 {"Iuml", "207"}, // Ï - uppercase I, umlaut 091 {"ETH", "208"}, // Ð - uppercase Eth, Icelandic 092 {"Ntilde", "209"}, // Ñ - uppercase N, tilde 093 {"Ograve", "210"}, // Ò - uppercase O, grave accent 094 {"Oacute", "211"}, // Ó - uppercase O, acute accent 095 {"Ocirc", "212"}, // Ô - uppercase O, circumflex accent 096 {"Otilde", "213"}, // Õ - uppercase O, tilde 097 {"Ouml", "214"}, // Ö - uppercase O, umlaut 098 {"times", "215"}, // multiplication sign 099 {"Oslash", "216"}, // Ø - uppercase O, slash 100 {"Ugrave", "217"}, // Ù - uppercase U, grave accent 101 {"Uacute", "218"}, // Ú - uppercase U, acute accent 102 {"Ucirc", "219"}, // Û - uppercase U, circumflex accent 103 {"Uuml", "220"}, // Ü - uppercase U, umlaut 104 {"Yacute", "221"}, // Ý - uppercase Y, acute accent 105 {"THORN", "222"}, // Þ - uppercase THORN, Icelandic 106 {"szlig", "223"}, // ß - lowercase sharps, German 107 {"agrave", "224"}, // à - lowercase a, grave accent 108 {"aacute", "225"}, // á - lowercase a, acute accent 109 {"acirc", "226"}, // â - lowercase a, circumflex accent 110 {"atilde", "227"}, // ã - lowercase a, tilde 111 {"auml", "228"}, // ä - lowercase a, umlaut 112 {"aring", "229"}, // å - lowercase a, ring 113 {"aelig", "230"}, // æ - lowercase ae 114 {"ccedil", "231"}, // ç - lowercase c, cedilla 115 {"egrave", "232"}, // è - lowercase e, grave accent 116 {"eacute", "233"}, // é - lowercase e, acute accent 117 {"ecirc", "234"}, // ê - lowercase e, circumflex accent 118 {"euml", "235"}, // ë - lowercase e, umlaut 119 {"igrave", "236"}, // ì - lowercase i, grave accent 120 {"iacute", "237"}, // í - lowercase i, acute accent 121 {"icirc", "238"}, // î - lowercase i, circumflex accent 122 {"iuml", "239"}, // ï - lowercase i, umlaut 123 {"eth", "240"}, // ð - lowercase eth, Icelandic 124 {"ntilde", "241"}, // ñ - lowercase n, tilde 125 {"ograve", "242"}, // ò - lowercase o, grave accent 126 {"oacute", "243"}, // ó - lowercase o, acute accent 127 {"ocirc", "244"}, // ô - lowercase o, circumflex accent 128 {"otilde", "245"}, // õ - lowercase o, tilde 129 {"ouml", "246"}, // ö - lowercase o, umlaut 130 {"divide", "247"}, // division sign 131 {"oslash", "248"}, // ø - lowercase o, slash 132 {"ugrave", "249"}, // ù - lowercase u, grave accent 133 {"uacute", "250"}, // ú - lowercase u, acute accent 134 {"ucirc", "251"}, // û - lowercase u, circumflex accent 135 {"uuml", "252"}, // ü - lowercase u, umlaut 136 {"yacute", "253"}, // ý - lowercase y, acute accent 137 {"thorn", "254"}, // þ - lowercase thorn, Icelandic 138 {"yuml", "255"}, // ÿ - lowercase y, umlaut 139 /* HTML 40 */ 140 // <!-- Latin Extended-B --> 141 {"fnof", "402"}, // latin small f with hook = function= florin, U+0192 ISOtech --> 142 // <!-- Greek --> 143 {"Alpha", "913"}, // greek capital letter alpha, U+0391 --> 144 {"Beta", "914"}, // greek capital letter beta, U+0392 --> 145 {"Gamma", "915"}, // greek capital letter gamma,U+0393 ISOgrk3 --> 146 {"Delta", "916"}, // greek capital letter delta,U+0394 ISOgrk3 --> 147 {"Epsilon", "917"}, // greek capital letter epsilon, U+0395 --> 148 {"Zeta", "918"}, // greek capital letter zeta, U+0396 --> 149 {"Eta", "919"}, // greek capital letter eta, U+0397 --> 150 {"Theta", "920"}, // greek capital letter theta,U+0398 ISOgrk3 --> 151 {"Iota", "921"}, // greek capital letter iota, U+0399 --> 152 {"Kappa", "922"}, // greek capital letter kappa, U+039A --> 153 {"Lambda", "923"}, // greek capital letter lambda,U+039B ISOgrk3 --> 154 {"Mu", "924"}, // greek capital letter mu, U+039C --> 155 {"Nu", "925"}, // greek capital letter nu, U+039D --> 156 {"Xi", "926"}, // greek capital letter xi, U+039E ISOgrk3 --> 157 {"Omicron", "927"}, // greek capital letter omicron, U+039F --> 158 {"Pi", "928"}, // greek capital letter pi, U+03A0 ISOgrk3 --> 159 {"Rho", "929"}, // greek capital letter rho, U+03A1 --> 160 // <!-- there is no Sigmaf, and no U+03A2 character either --> 161 {"Sigma", "931"}, // greek capital letter sigma,U+03A3 ISOgrk3 --> 162 {"Tau", "932"}, // greek capital letter tau, U+03A4 --> 163 {"Upsilon", "933"}, // greek capital letter upsilon,U+03A5 ISOgrk3 --> 164 {"Phi", "934"}, // greek capital letter phi,U+03A6 ISOgrk3 --> 165 {"Chi", "935"}, // greek capital letter chi, U+03A7 --> 166 {"Psi", "936"}, // greek capital letter psi,U+03A8 ISOgrk3 --> 167 {"Omega", "937"}, // greek capital letter omega,U+03A9 ISOgrk3 --> 168 {"alpha", "945"}, // greek small letter alpha,U+03B1 ISOgrk3 --> 169 {"beta", "946"}, // greek small letter beta, U+03B2 ISOgrk3 --> 170 {"gamma", "947"}, // greek small letter gamma,U+03B3 ISOgrk3 --> 171 {"delta", "948"}, // greek small letter delta,U+03B4 ISOgrk3 --> 172 {"epsilon", "949"}, // greek small letter epsilon,U+03B5 ISOgrk3 --> 173 {"zeta", "950"}, // greek small letter zeta, U+03B6 ISOgrk3 --> 174 {"eta", "951"}, // greek small letter eta, U+03B7 ISOgrk3 --> 175 {"theta", "952"}, // greek small letter theta,U+03B8 ISOgrk3 --> 176 {"iota", "953"}, // greek small letter iota, U+03B9 ISOgrk3 --> 177 {"kappa", "954"}, // greek small letter kappa,U+03BA ISOgrk3 --> 178 {"lambda", "955"}, // greek small letter lambda,U+03BB ISOgrk3 --> 179 {"mu", "956"}, // greek small letter mu, U+03BC ISOgrk3 --> 180 {"nu", "957"}, // greek small letter nu, U+03BD ISOgrk3 --> 181 {"xi", "958"}, // greek small letter xi, U+03BE ISOgrk3 --> 182 {"omicron", "959"}, // greek small letter omicron, U+03BF NEW --> 183 {"pi", "960"}, // greek small letter pi, U+03C0 ISOgrk3 --> 184 {"rho", "961"}, // greek small letter rho, U+03C1 ISOgrk3 --> 185 {"sigmaf", "962"}, // greek small letter final sigma,U+03C2 ISOgrk3 --> 186 {"sigma", "963"}, // greek small letter sigma,U+03C3 ISOgrk3 --> 187 {"tau", "964"}, // greek small letter tau, U+03C4 ISOgrk3 --> 188 {"upsilon", "965"}, // greek small letter upsilon,U+03C5 ISOgrk3 --> 189 {"phi", "966"}, // greek small letter phi, U+03C6 ISOgrk3 --> 190 {"chi", "967"}, // greek small letter chi, U+03C7 ISOgrk3 --> 191 {"psi", "968"}, // greek small letter psi, U+03C8 ISOgrk3 --> 192 {"omega", "969"}, // greek small letter omega,U+03C9 ISOgrk3 --> 193 {"thetasym", "977"}, // greek small letter theta symbol,U+03D1 NEW --> 194 {"upsih", "978"}, // greek upsilon with hook symbol,U+03D2 NEW --> 195 {"piv", "982"}, // greek pi symbol, U+03D6 ISOgrk3 --> 196 // <!-- General Punctuation --> 197 {"bull", "8226"}, // bullet = black small circle,U+2022 ISOpub --> 198 // <!-- bullet is NOT the same as bullet operator, U+2219 --> 199 {"hellip", "8230"}, // horizontal ellipsis = three dot leader,U+2026 ISOpub --> 200 {"prime", "8242"}, // prime = minutes = feet, U+2032 ISOtech --> 201 {"Prime", "8243"}, // double prime = seconds = inches,U+2033 ISOtech --> 202 {"oline", "8254"}, // overline = spacing overscore,U+203E NEW --> 203 {"frasl", "8260"}, // fraction slash, U+2044 NEW --> 204 // <!-- Letterlike Symbols --> 205 {"weierp", "8472"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso --> 206 {"image", "8465"}, // blackletter capital I = imaginary part,U+2111 ISOamso --> 207 {"real", "8476"}, // blackletter capital R = real part symbol,U+211C ISOamso --> 208 {"trade", "8482"}, // trade mark sign, U+2122 ISOnum --> 209 {"alefsym", "8501"}, // alef symbol = first transfinite cardinal,U+2135 NEW --> 210 // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the 211 // same glyph could be used to depict both characters --> 212 // <!-- Arrows --> 213 {"larr", "8592"}, // leftwards arrow, U+2190 ISOnum --> 214 {"uarr", "8593"}, // upwards arrow, U+2191 ISOnum--> 215 {"rarr", "8594"}, // rightwards arrow, U+2192 ISOnum --> 216 {"darr", "8595"}, // downwards arrow, U+2193 ISOnum --> 217 {"harr", "8596"}, // left right arrow, U+2194 ISOamsa --> 218 {"crarr", "8629"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW --> 219 {"lArr", "8656"}, // leftwards double arrow, U+21D0 ISOtech --> 220 // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by' 221 // arrow but also does not have any other character for that function. 222 // So ? lArr canbe used for 'is implied by' as ISOtech suggests --> 223 {"uArr", "8657"}, // upwards double arrow, U+21D1 ISOamsa --> 224 {"rArr", "8658"}, // rightwards double arrow,U+21D2 ISOtech --> 225 // <!-- ISO 10646 does not say this is the 'implies' character but does not 226 // have another character with this function so ?rArr can be used for 227 // 'implies' as ISOtech suggests --> 228 {"dArr", "8659"}, // downwards double arrow, U+21D3 ISOamsa --> 229 {"hArr", "8660"}, // left right double arrow,U+21D4 ISOamsa --> 230 // <!-- Mathematical Operators --> 231 {"forall", "8704"}, // for all, U+2200 ISOtech --> 232 {"part", "8706"}, // partial differential, U+2202 ISOtech --> 233 {"exist", "8707"}, // there exists, U+2203 ISOtech --> 234 {"empty", "8709"}, // empty set = null set = diameter,U+2205 ISOamso --> 235 {"nabla", "8711"}, // nabla = backward difference,U+2207 ISOtech --> 236 {"isin", "8712"}, // element of, U+2208 ISOtech --> 237 {"notin", "8713"}, // not an element of, U+2209 ISOtech --> 238 {"ni", "8715"}, // contains as member, U+220B ISOtech --> 239 // <!-- should there be a more memorable name than 'ni'? --> 240 {"prod", "8719"}, // n-ary product = product sign,U+220F ISOamsb --> 241 // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi' 242 // though the same glyph might be used for both --> 243 {"sum", "8721"}, // n-ary summation, U+2211 ISOamsb --> 244 // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma' 245 // though the same glyph might be used for both --> 246 {"minus", "8722"}, // minus sign, U+2212 ISOtech --> 247 {"lowast", "8727"}, // asterisk operator, U+2217 ISOtech --> 248 {"radic", "8730"}, // square root = radical sign,U+221A ISOtech --> 249 {"prop", "8733"}, // proportional to, U+221D ISOtech --> 250 {"infin", "8734"}, // infinity, U+221E ISOtech --> 251 {"ang", "8736"}, // angle, U+2220 ISOamso --> 252 {"and", "8743"}, // logical and = wedge, U+2227 ISOtech --> 253 {"or", "8744"}, // logical or = vee, U+2228 ISOtech --> 254 {"cap", "8745"}, // intersection = cap, U+2229 ISOtech --> 255 {"cup", "8746"}, // union = cup, U+222A ISOtech --> 256 {"int", "8747"}, // integral, U+222B ISOtech --> 257 {"there4", "8756"}, // therefore, U+2234 ISOtech --> 258 {"sim", "8764"}, // tilde operator = varies with = similar to,U+223C ISOtech --> 259 // <!-- tilde operator is NOT the same character as the tilde, U+007E,although 260 // the same glyph might be used to represent both --> 261 {"cong", "8773"}, // approximately equal to, U+2245 ISOtech --> 262 {"asymp", "8776"}, // almost equal to = asymptotic to,U+2248 ISOamsr --> 263 {"ne", "8800"}, // not equal to, U+2260 ISOtech --> 264 {"equiv", "8801"}, // identical to, U+2261 ISOtech --> 265 {"le", "8804"}, // less-than or equal to, U+2264 ISOtech --> 266 {"ge", "8805"}, // greater-than or equal to,U+2265 ISOtech --> 267 {"sub", "8834"}, // subset of, U+2282 ISOtech --> 268 {"sup", "8835"}, // superset of, U+2283 ISOtech --> 269 // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the 270 // Symbol font encoding and is not included. Should it be, for symmetry? 271 // It is in ISOamsn --> <!ENTITY nsub", "8836"}, 272 // not a subset of, U+2284 ISOamsn --> 273 {"sube", "8838"}, // subset of or equal to, U+2286 ISOtech --> 274 {"supe", "8839"}, // superset of or equal to,U+2287 ISOtech --> 275 {"oplus", "8853"}, // circled plus = direct sum,U+2295 ISOamsb --> 276 {"otimes", "8855"}, // circled times = vector product,U+2297 ISOamsb --> 277 {"perp", "8869"}, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech --> 278 {"sdot", "8901"}, // dot operator, U+22C5 ISOamsb --> 279 // <!-- dot operator is NOT the same character as U+00B7 middle dot --> 280 // <!-- Miscellaneous Technical --> 281 {"lceil", "8968"}, // left ceiling = apl upstile,U+2308 ISOamsc --> 282 {"rceil", "8969"}, // right ceiling, U+2309 ISOamsc --> 283 {"lfloor", "8970"}, // left floor = apl downstile,U+230A ISOamsc --> 284 {"rfloor", "8971"}, // right floor, U+230B ISOamsc --> 285 {"lang", "9001"}, // left-pointing angle bracket = bra,U+2329 ISOtech --> 286 // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation 287 // mark' --> 288 {"rang", "9002"}, // right-pointing angle bracket = ket,U+232A ISOtech --> 289 // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A 290 // 'single right-pointing angle quotation mark' --> 291 // <!-- Geometric Shapes --> 292 {"loz", "9674"}, // lozenge, U+25CA ISOpub --> 293 // <!-- Miscellaneous Symbols --> 294 {"spades", "9824"}, // black spade suit, U+2660 ISOpub --> 295 // <!-- black here seems to mean filled as opposed to hollow --> 296 {"clubs", "9827"}, // black club suit = shamrock,U+2663 ISOpub --> 297 {"hearts", "9829"}, // black heart suit = valentine,U+2665 ISOpub --> 298 {"diams", "9830"}, // black diamond suit, U+2666 ISOpub --> 299 300 // <!-- Latin Extended-A --> 301 {"OElig", "338"}, // -- latin capital ligature OE,U+0152 ISOlat2 --> 302 {"oelig", "339"}, // -- latin small ligature oe, U+0153 ISOlat2 --> 303 // <!-- ligature is a misnomer, this is a separate character in some languages --> 304 {"Scaron", "352"}, // -- latin capital letter S with caron,U+0160 ISOlat2 --> 305 {"scaron", "353"}, // -- latin small letter s with caron,U+0161 ISOlat2 --> 306 {"Yuml", "376"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 --> 307 // <!-- Spacing Modifier Letters --> 308 {"circ", "710"}, // -- modifier letter circumflex accent,U+02C6 ISOpub --> 309 {"tilde", "732"}, // small tilde, U+02DC ISOdia --> 310 // <!-- General Punctuation --> 311 {"ensp", "8194"}, // en space, U+2002 ISOpub --> 312 {"emsp", "8195"}, // em space, U+2003 ISOpub --> 313 {"thinsp", "8201"}, // thin space, U+2009 ISOpub --> 314 {"zwnj", "8204"}, // zero width non-joiner,U+200C NEW RFC 2070 --> 315 {"zwj", "8205"}, // zero width joiner, U+200D NEW RFC 2070 --> 316 {"lrm", "8206"}, // left-to-right mark, U+200E NEW RFC 2070 --> 317 {"rlm", "8207"}, // right-to-left mark, U+200F NEW RFC 2070 --> 318 {"ndash", "8211"}, // en dash, U+2013 ISOpub --> 319 {"mdash", "8212"}, // em dash, U+2014 ISOpub --> 320 {"lsquo", "8216"}, // left single quotation mark,U+2018 ISOnum --> 321 {"rsquo", "8217"}, // right single quotation mark,U+2019 ISOnum --> 322 {"sbquo", "8218"}, // single low-9 quotation mark, U+201A NEW --> 323 {"ldquo", "8220"}, // left double quotation mark,U+201C ISOnum --> 324 {"rdquo", "8221"}, // right double quotation mark,U+201D ISOnum --> 325 {"bdquo", "8222"}, // double low-9 quotation mark, U+201E NEW --> 326 {"dagger", "8224"}, // dagger, U+2020 ISOpub --> 327 {"Dagger", "8225"}, // double dagger, U+2021 ISOpub --> 328 {"permil", "8240"}, // per mille sign, U+2030 ISOtech --> 329 {"lsaquo", "8249"}, // single left-pointing angle quotation mark,U+2039 ISO proposed --> 330 // <!-- lsaquo is proposed but not yet ISO standardized --> 331 {"rsaquo", "8250"}, // single right-pointing angle quotation mark,U+203A ISO proposed --> 332 // <!-- rsaquo is proposed but not yet ISO standardized --> 333 {"euro", "8364"}, // -- euro sign, U+20AC NEW --> 334 }; 335 336 private static volatile Map<String, String> mapNameToValue; 337 338 private Entities() { 339 // Private constructor for utilities classes 340 } 341 342 public static String unescape(String str) { 343 int firstAmp = str.indexOf('&'); 344 if (firstAmp < 0) 345 return str; 346 StringBuilder res = new StringBuilder(str.substring(0, firstAmp)); 347 int len = str.length(); 348 for (int i = firstAmp; i < len; i++) { 349 char c = str.charAt(i); 350 if (c == '&') { 351 int nextIdx = i + 1; 352 int semiColonIdx = str.indexOf(';', nextIdx); 353 if (semiColonIdx == -1) { 354 res.append(c); 355 continue; 356 } 357 int amphersandIdx = str.indexOf('&', i + 1); 358 if (amphersandIdx != -1 && amphersandIdx < semiColonIdx) { 359 // Then the text looks like &...&...; 360 res.append(c); 361 continue; 362 } 363 String entityContent = str.substring(nextIdx, semiColonIdx); 364 int entityValue = -1; 365 int entityContentLen = entityContent.length(); 366 if (entityContentLen > 0) { 367 if (entityContent.charAt(0) == '#') { // escaped value content is an integer (decimal or 368 // hexidecimal) 369 if (entityContentLen > 1) { 370 char isHexChar = entityContent.charAt(1); 371 try { 372 switch (isHexChar) { 373 case 'X' : 374 case 'x' : 375 entityValue = Integer.parseInt(entityContent.substring(2), 16); 376 break; 377 default : 378 entityValue = Integer.parseInt(entityContent.substring(1), 10); 379 } 380 if (entityValue > 0xFFFF) { 381 entityValue = -1; 382 } 383 } catch (NumberFormatException e) { 384 entityValue = -1; 385 } 386 } 387 } else { // escaped value content is an entity name 388 if (mapNameToValue == null) { 389 mapNameToValue = new HashMap<>(); 390 for (String[] pair : ARRAY) { 391 mapNameToValue.put(pair[0], pair[1]); 392 } 393 } 394 String value = mapNameToValue.get(entityContent); 395 entityValue = value == null ? -1 : Integer.parseInt(value); 396 } 397 } 398 399 if (entityValue == -1) { 400 res.append('&').append(entityContent).append(';'); 401 } else { 402 res.append((char) entityValue); 403 } 404 i = semiColonIdx; // move index up to the semi-colon 405 } else { 406 res.append(c); 407 } 408 } 409 return res.toString(); 410 } 411}