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.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 1.0 25 */ 26 public class EntityArrays { 27 28 /** 29 * Mapping to escape <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1">ISO-8859-1</a> 30 * characters to their named HTML 3.x equivalents. 31 * @return the mapping table 32 */ 33 public static String[][] ISO8859_1_ESCAPE() { return ISO8859_1_ESCAPE.clone(); } 34 private static final String[][] ISO8859_1_ESCAPE = { 35 {"\u00A0", " "}, // non-breaking space 36 {"\u00A1", "¡"}, // inverted exclamation mark 37 {"\u00A2", "¢"}, // cent sign 38 {"\u00A3", "£"}, // pound sign 39 {"\u00A4", "¤"}, // currency sign 40 {"\u00A5", "¥"}, // yen sign = yuan sign 41 {"\u00A6", "¦"}, // broken bar = broken vertical bar 42 {"\u00A7", "§"}, // section sign 43 {"\u00A8", "¨"}, // diaeresis = spacing diaeresis 44 {"\u00A9", "©"}, // © - copyright sign 45 {"\u00AA", "ª"}, // feminine ordinal indicator 46 {"\u00AB", "«"}, // left-pointing double angle quotation mark = left pointing guillemet 47 {"\u00AC", "¬"}, // not sign 48 {"\u00AD", "­"}, // soft hyphen = discretionary hyphen 49 {"\u00AE", "®"}, // ® - registered trademark sign 50 {"\u00AF", "¯"}, // macron = spacing macron = overline = APL overbar 51 {"\u00B0", "°"}, // degree sign 52 {"\u00B1", "±"}, // plus-minus sign = plus-or-minus sign 53 {"\u00B2", "²"}, // superscript two = superscript digit two = squared 54 {"\u00B3", "³"}, // superscript three = superscript digit three = cubed 55 {"\u00B4", "´"}, // acute accent = spacing acute 56 {"\u00B5", "µ"}, // micro sign 57 {"\u00B6", "¶"}, // pilcrow sign = paragraph sign 58 {"\u00B7", "·"}, // middle dot = Georgian comma = Greek middle dot 59 {"\u00B8", "¸"}, // cedilla = spacing cedilla 60 {"\u00B9", "¹"}, // superscript one = superscript digit one 61 {"\u00BA", "º"}, // masculine ordinal indicator 62 {"\u00BB", "»"}, // right-pointing double angle quotation mark = right pointing guillemet 63 {"\u00BC", "¼"}, // vulgar fraction one quarter = fraction one quarter 64 {"\u00BD", "½"}, // vulgar fraction one half = fraction one half 65 {"\u00BE", "¾"}, // vulgar fraction three quarters = fraction three quarters 66 {"\u00BF", "¿"}, // inverted question mark = turned question mark 67 {"\u00C0", "À"}, // à - uppercase A, grave accent 68 {"\u00C1", "Á"}, // à - uppercase A, acute accent 69 {"\u00C2", "Â"}, // à - uppercase A, circumflex accent 70 {"\u00C3", "Ã"}, // à - uppercase A, tilde 71 {"\u00C4", "Ä"}, // à - uppercase A, umlaut 72 {"\u00C5", "Å"}, // à - uppercase A, ring 73 {"\u00C6", "Æ"}, // à - uppercase AE 74 {"\u00C7", "Ç"}, // à - uppercase C, cedilla 75 {"\u00C8", "È"}, // à - uppercase E, grave accent 76 {"\u00C9", "É"}, // à - uppercase E, acute accent 77 {"\u00CA", "Ê"}, // à - uppercase E, circumflex accent 78 {"\u00CB", "Ë"}, // à - uppercase E, umlaut 79 {"\u00CC", "Ì"}, // à - uppercase I, grave accent 80 {"\u00CD", "Í"}, // à - uppercase I, acute accent 81 {"\u00CE", "Î"}, // à - uppercase I, circumflex accent 82 {"\u00CF", "Ï"}, // à - uppercase I, umlaut 83 {"\u00D0", "Ð"}, // à - uppercase Eth, Icelandic 84 {"\u00D1", "Ñ"}, // à - uppercase N, tilde 85 {"\u00D2", "Ò"}, // à - uppercase O, grave accent 86 {"\u00D3", "Ó"}, // à - uppercase O, acute accent 87 {"\u00D4", "Ô"}, // à - uppercase O, circumflex accent 88 {"\u00D5", "Õ"}, // à - uppercase O, tilde 89 {"\u00D6", "Ö"}, // à - uppercase O, umlaut 90 {"\u00D7", "×"}, // multiplication sign 91 {"\u00D8", "Ø"}, // à - uppercase O, slash 92 {"\u00D9", "Ù"}, // à - uppercase U, grave accent 93 {"\u00DA", "Ú"}, // à - uppercase U, acute accent 94 {"\u00DB", "Û"}, // à - uppercase U, circumflex accent 95 {"\u00DC", "Ü"}, // à - uppercase U, umlaut 96 {"\u00DD", "Ý"}, // à - uppercase Y, acute accent 97 {"\u00DE", "Þ"}, // à - uppercase THORN, Icelandic 98 {"\u00DF", "ß"}, // à - lowercase sharps, German 99 {"\u00E0", "à"}, // à - lowercase a, grave accent 100 {"\u00E1", "á"}, // á - lowercase a, acute accent 101 {"\u00E2", "â"}, // â - lowercase a, circumflex accent 102 {"\u00E3", "ã"}, // ã - lowercase a, tilde 103 {"\u00E4", "ä"}, // ä - lowercase a, umlaut 104 {"\u00E5", "å"}, // Ã¥ - lowercase a, ring 105 {"\u00E6", "æ"}, // æ - lowercase ae 106 {"\u00E7", "ç"}, // ç - lowercase c, cedilla 107 {"\u00E8", "è"}, // è - lowercase e, grave accent 108 {"\u00E9", "é"}, // é - lowercase e, acute accent 109 {"\u00EA", "ê"}, // ê - lowercase e, circumflex accent 110 {"\u00EB", "ë"}, // ë - lowercase e, umlaut 111 {"\u00EC", "ì"}, // ì - lowercase i, grave accent 112 {"\u00ED", "í"}, // à - lowercase i, acute accent 113 {"\u00EE", "î"}, // î - lowercase i, circumflex accent 114 {"\u00EF", "ï"}, // ï - lowercase i, umlaut 115 {"\u00F0", "ð"}, // ð - lowercase eth, Icelandic 116 {"\u00F1", "ñ"}, // ñ - lowercase n, tilde 117 {"\u00F2", "ò"}, // ò - lowercase o, grave accent 118 {"\u00F3", "ó"}, // ó - lowercase o, acute accent 119 {"\u00F4", "ô"}, // ô - lowercase o, circumflex accent 120 {"\u00F5", "õ"}, // õ - lowercase o, tilde 121 {"\u00F6", "ö"}, // ö - lowercase o, umlaut 122 {"\u00F7", "÷"}, // division sign 123 {"\u00F8", "ø"}, // ø - lowercase o, slash 124 {"\u00F9", "ù"}, // ù - lowercase u, grave accent 125 {"\u00FA", "ú"}, // ú - lowercase u, acute accent 126 {"\u00FB", "û"}, // û - lowercase u, circumflex accent 127 {"\u00FC", "ü"}, // ü - lowercase u, umlaut 128 {"\u00FD", "ý"}, // ý - lowercase y, acute accent 129 {"\u00FE", "þ"}, // þ - lowercase thorn, Icelandic 130 {"\u00FF", "ÿ"}, // ÿ - lowercase y, umlaut 131 }; 132 133 /** 134 * Reverse of {@link #ISO8859_1_ESCAPE()} for unescaping purposes. 135 * @return the mapping table 136 */ 137 public static String[][] ISO8859_1_UNESCAPE() { return ISO8859_1_UNESCAPE.clone(); } 138 private static final String[][] ISO8859_1_UNESCAPE = invert(ISO8859_1_ESCAPE); 139 140 /** 141 * Mapping to escape additional <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">character entity 142 * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE()} to get the full list of 143 * HTML 4.0 character entities. 144 * @return the mapping table 145 */ 146 public static String[][] HTML40_EXTENDED_ESCAPE() { return HTML40_EXTENDED_ESCAPE.clone(); } 147 private static final String[][] HTML40_EXTENDED_ESCAPE = { 148 // <!-- Latin Extended-B --> 149 {"\u0192", "ƒ"}, // latin small f with hook = function= florin, U+0192 ISOtech --> 150 // <!-- Greek --> 151 {"\u0391", "Α"}, // greek capital letter alpha, U+0391 --> 152 {"\u0392", "Β"}, // greek capital letter beta, U+0392 --> 153 {"\u0393", "Γ"}, // greek capital letter gamma,U+0393 ISOgrk3 --> 154 {"\u0394", "Δ"}, // greek capital letter delta,U+0394 ISOgrk3 --> 155 {"\u0395", "Ε"}, // greek capital letter epsilon, U+0395 --> 156 {"\u0396", "Ζ"}, // greek capital letter zeta, U+0396 --> 157 {"\u0397", "Η"}, // greek capital letter eta, U+0397 --> 158 {"\u0398", "Θ"}, // greek capital letter theta,U+0398 ISOgrk3 --> 159 {"\u0399", "Ι"}, // greek capital letter iota, U+0399 --> 160 {"\u039A", "Κ"}, // greek capital letter kappa, U+039A --> 161 {"\u039B", "Λ"}, // greek capital letter lambda,U+039B ISOgrk3 --> 162 {"\u039C", "Μ"}, // greek capital letter mu, U+039C --> 163 {"\u039D", "Ν"}, // greek capital letter nu, U+039D --> 164 {"\u039E", "Ξ"}, // greek capital letter xi, U+039E ISOgrk3 --> 165 {"\u039F", "Ο"}, // greek capital letter omicron, U+039F --> 166 {"\u03A0", "Π"}, // greek capital letter pi, U+03A0 ISOgrk3 --> 167 {"\u03A1", "Ρ"}, // greek capital letter rho, U+03A1 --> 168 // <!-- there is no Sigmaf, and no U+03A2 character either --> 169 {"\u03A3", "Σ"}, // greek capital letter sigma,U+03A3 ISOgrk3 --> 170 {"\u03A4", "Τ"}, // greek capital letter tau, U+03A4 --> 171 {"\u03A5", "Υ"}, // greek capital letter upsilon,U+03A5 ISOgrk3 --> 172 {"\u03A6", "Φ"}, // greek capital letter phi,U+03A6 ISOgrk3 --> 173 {"\u03A7", "Χ"}, // greek capital letter chi, U+03A7 --> 174 {"\u03A8", "Ψ"}, // greek capital letter psi,U+03A8 ISOgrk3 --> 175 {"\u03A9", "Ω"}, // greek capital letter omega,U+03A9 ISOgrk3 --> 176 {"\u03B1", "α"}, // greek small letter alpha,U+03B1 ISOgrk3 --> 177 {"\u03B2", "β"}, // greek small letter beta, U+03B2 ISOgrk3 --> 178 {"\u03B3", "γ"}, // greek small letter gamma,U+03B3 ISOgrk3 --> 179 {"\u03B4", "δ"}, // greek small letter delta,U+03B4 ISOgrk3 --> 180 {"\u03B5", "ε"}, // greek small letter epsilon,U+03B5 ISOgrk3 --> 181 {"\u03B6", "ζ"}, // greek small letter zeta, U+03B6 ISOgrk3 --> 182 {"\u03B7", "η"}, // greek small letter eta, U+03B7 ISOgrk3 --> 183 {"\u03B8", "θ"}, // greek small letter theta,U+03B8 ISOgrk3 --> 184 {"\u03B9", "ι"}, // greek small letter iota, U+03B9 ISOgrk3 --> 185 {"\u03BA", "κ"}, // greek small letter kappa,U+03BA ISOgrk3 --> 186 {"\u03BB", "λ"}, // greek small letter lambda,U+03BB ISOgrk3 --> 187 {"\u03BC", "μ"}, // greek small letter mu, U+03BC ISOgrk3 --> 188 {"\u03BD", "ν"}, // greek small letter nu, U+03BD ISOgrk3 --> 189 {"\u03BE", "ξ"}, // greek small letter xi, U+03BE ISOgrk3 --> 190 {"\u03BF", "ο"}, // greek small letter omicron, U+03BF NEW --> 191 {"\u03C0", "π"}, // greek small letter pi, U+03C0 ISOgrk3 --> 192 {"\u03C1", "ρ"}, // greek small letter rho, U+03C1 ISOgrk3 --> 193 {"\u03C2", "ς"}, // greek small letter final sigma,U+03C2 ISOgrk3 --> 194 {"\u03C3", "σ"}, // greek small letter sigma,U+03C3 ISOgrk3 --> 195 {"\u03C4", "τ"}, // greek small letter tau, U+03C4 ISOgrk3 --> 196 {"\u03C5", "υ"}, // greek small letter upsilon,U+03C5 ISOgrk3 --> 197 {"\u03C6", "φ"}, // greek small letter phi, U+03C6 ISOgrk3 --> 198 {"\u03C7", "χ"}, // greek small letter chi, U+03C7 ISOgrk3 --> 199 {"\u03C8", "ψ"}, // greek small letter psi, U+03C8 ISOgrk3 --> 200 {"\u03C9", "ω"}, // greek small letter omega,U+03C9 ISOgrk3 --> 201 {"\u03D1", "ϑ"}, // greek small letter theta symbol,U+03D1 NEW --> 202 {"\u03D2", "ϒ"}, // greek upsilon with hook symbol,U+03D2 NEW --> 203 {"\u03D6", "ϖ"}, // greek pi symbol, U+03D6 ISOgrk3 --> 204 // <!-- General Punctuation --> 205 {"\u2022", "•"}, // bullet = black small circle,U+2022 ISOpub --> 206 // <!-- bullet is NOT the same as bullet operator, U+2219 --> 207 {"\u2026", "…"}, // horizontal ellipsis = three dot leader,U+2026 ISOpub --> 208 {"\u2032", "′"}, // prime = minutes = feet, U+2032 ISOtech --> 209 {"\u2033", "″"}, // double prime = seconds = inches,U+2033 ISOtech --> 210 {"\u203E", "‾"}, // overline = spacing overscore,U+203E NEW --> 211 {"\u2044", "⁄"}, // fraction slash, U+2044 NEW --> 212 // <!-- Letterlike Symbols --> 213 {"\u2118", "℘"}, // script capital P = power set= Weierstrass p, U+2118 ISOamso --> 214 {"\u2111", "ℑ"}, // blackletter capital I = imaginary part,U+2111 ISOamso --> 215 {"\u211C", "ℜ"}, // blackletter capital R = real part symbol,U+211C ISOamso --> 216 {"\u2122", "™"}, // trade mark sign, U+2122 ISOnum --> 217 {"\u2135", "ℵ"}, // alef symbol = first transfinite cardinal,U+2135 NEW --> 218 // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the 219 // same glyph could be used to depict both characters --> 220 // <!-- Arrows --> 221 {"\u2190", "←"}, // leftwards arrow, U+2190 ISOnum --> 222 {"\u2191", "↑"}, // upwards arrow, U+2191 ISOnum--> 223 {"\u2192", "→"}, // rightwards arrow, U+2192 ISOnum --> 224 {"\u2193", "↓"}, // downwards arrow, U+2193 ISOnum --> 225 {"\u2194", "↔"}, // left right arrow, U+2194 ISOamsa --> 226 {"\u21B5", "↵"}, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW --> 227 {"\u21D0", "⇐"}, // leftwards double arrow, U+21D0 ISOtech --> 228 // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by' 229 // arrow but also does not have any other character for that function. 230 // So ? lArr canbe used for 'is implied by' as ISOtech suggests --> 231 {"\u21D1", "⇑"}, // upwards double arrow, U+21D1 ISOamsa --> 232 {"\u21D2", "⇒"}, // rightwards double arrow,U+21D2 ISOtech --> 233 // <!-- ISO 10646 does not say this is the 'implies' character but does not 234 // have another character with this function so ?rArr can be used for 235 // 'implies' as ISOtech suggests --> 236 {"\u21D3", "⇓"}, // downwards double arrow, U+21D3 ISOamsa --> 237 {"\u21D4", "⇔"}, // left right double arrow,U+21D4 ISOamsa --> 238 // <!-- Mathematical Operators --> 239 {"\u2200", "∀"}, // for all, U+2200 ISOtech --> 240 {"\u2202", "∂"}, // partial differential, U+2202 ISOtech --> 241 {"\u2203", "∃"}, // there exists, U+2203 ISOtech --> 242 {"\u2205", "∅"}, // empty set = null set = diameter,U+2205 ISOamso --> 243 {"\u2207", "∇"}, // nabla = backward difference,U+2207 ISOtech --> 244 {"\u2208", "∈"}, // element of, U+2208 ISOtech --> 245 {"\u2209", "∉"}, // not an element of, U+2209 ISOtech --> 246 {"\u220B", "∋"}, // contains as member, U+220B ISOtech --> 247 // <!-- should there be a more memorable name than 'ni'? --> 248 {"\u220F", "∏"}, // n-ary product = product sign,U+220F ISOamsb --> 249 // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi' 250 // though the same glyph might be used for both --> 251 {"\u2211", "∑"}, // n-ary summation, U+2211 ISOamsb --> 252 // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma' 253 // though the same glyph might be used for both --> 254 {"\u2212", "−"}, // minus sign, U+2212 ISOtech --> 255 {"\u2217", "∗"}, // asterisk operator, U+2217 ISOtech --> 256 {"\u221A", "√"}, // square root = radical sign,U+221A ISOtech --> 257 {"\u221D", "∝"}, // proportional to, U+221D ISOtech --> 258 {"\u221E", "∞"}, // infinity, U+221E ISOtech --> 259 {"\u2220", "∠"}, // angle, U+2220 ISOamso --> 260 {"\u2227", "∧"}, // logical and = wedge, U+2227 ISOtech --> 261 {"\u2228", "∨"}, // logical or = vee, U+2228 ISOtech --> 262 {"\u2229", "∩"}, // intersection = cap, U+2229 ISOtech --> 263 {"\u222A", "∪"}, // union = cup, U+222A ISOtech --> 264 {"\u222B", "∫"}, // integral, U+222B ISOtech --> 265 {"\u2234", "∴"}, // therefore, U+2234 ISOtech --> 266 {"\u223C", "∼"}, // tilde operator = varies with = similar to,U+223C ISOtech --> 267 // <!-- tilde operator is NOT the same character as the tilde, U+007E,although 268 // the same glyph might be used to represent both --> 269 {"\u2245", "≅"}, // approximately equal to, U+2245 ISOtech --> 270 {"\u2248", "≈"}, // almost equal to = asymptotic to,U+2248 ISOamsr --> 271 {"\u2260", "≠"}, // not equal to, U+2260 ISOtech --> 272 {"\u2261", "≡"}, // identical to, U+2261 ISOtech --> 273 {"\u2264", "≤"}, // less-than or equal to, U+2264 ISOtech --> 274 {"\u2265", "≥"}, // greater-than or equal to,U+2265 ISOtech --> 275 {"\u2282", "⊂"}, // subset of, U+2282 ISOtech --> 276 {"\u2283", "⊃"}, // superset of, U+2283 ISOtech --> 277 // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the 278 // Symbol font encoding and is not included. Should it be, for symmetry? 279 // It is in ISOamsn -->, 280 {"\u2284", "⊄"}, // not a subset of, U+2284 ISOamsn --> 281 {"\u2286", "⊆"}, // subset of or equal to, U+2286 ISOtech --> 282 {"\u2287", "⊇"}, // superset of or equal to,U+2287 ISOtech --> 283 {"\u2295", "⊕"}, // circled plus = direct sum,U+2295 ISOamsb --> 284 {"\u2297", "⊗"}, // circled times = vector product,U+2297 ISOamsb --> 285 {"\u22A5", "⊥"}, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech --> 286 {"\u22C5", "⋅"}, // dot operator, U+22C5 ISOamsb --> 287 // <!-- dot operator is NOT the same character as U+00B7 middle dot --> 288 // <!-- Miscellaneous Technical --> 289 {"\u2308", "⌈"}, // left ceiling = apl upstile,U+2308 ISOamsc --> 290 {"\u2309", "⌉"}, // right ceiling, U+2309 ISOamsc --> 291 {"\u230A", "⌊"}, // left floor = apl downstile,U+230A ISOamsc --> 292 {"\u230B", "⌋"}, // right floor, U+230B ISOamsc --> 293 {"\u2329", "⟨"}, // left-pointing angle bracket = bra,U+2329 ISOtech --> 294 // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation 295 // mark' --> 296 {"\u232A", "⟩"}, // right-pointing angle bracket = ket,U+232A ISOtech --> 297 // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A 298 // 'single right-pointing angle quotation mark' --> 299 // <!-- Geometric Shapes --> 300 {"\u25CA", "◊"}, // lozenge, U+25CA ISOpub --> 301 // <!-- Miscellaneous Symbols --> 302 {"\u2660", "♠"}, // black spade suit, U+2660 ISOpub --> 303 // <!-- black here seems to mean filled as opposed to hollow --> 304 {"\u2663", "♣"}, // black club suit = shamrock,U+2663 ISOpub --> 305 {"\u2665", "♥"}, // black heart suit = valentine,U+2665 ISOpub --> 306 {"\u2666", "♦"}, // black diamond suit, U+2666 ISOpub --> 307 308 // <!-- Latin Extended-A --> 309 {"\u0152", "Œ"}, // -- latin capital ligature OE,U+0152 ISOlat2 --> 310 {"\u0153", "œ"}, // -- latin small ligature oe, U+0153 ISOlat2 --> 311 // <!-- ligature is a misnomer, this is a separate character in some languages --> 312 {"\u0160", "Š"}, // -- latin capital letter S with caron,U+0160 ISOlat2 --> 313 {"\u0161", "š"}, // -- latin small letter s with caron,U+0161 ISOlat2 --> 314 {"\u0178", "Ÿ"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 --> 315 // <!-- Spacing Modifier Letters --> 316 {"\u02C6", "ˆ"}, // -- modifier letter circumflex accent,U+02C6 ISOpub --> 317 {"\u02DC", "˜"}, // small tilde, U+02DC ISOdia --> 318 // <!-- General Punctuation --> 319 {"\u2002", " "}, // en space, U+2002 ISOpub --> 320 {"\u2003", " "}, // em space, U+2003 ISOpub --> 321 {"\u2009", " "}, // thin space, U+2009 ISOpub --> 322 {"\u200C", "‌"}, // zero width non-joiner,U+200C NEW RFC 2070 --> 323 {"\u200D", "‍"}, // zero width joiner, U+200D NEW RFC 2070 --> 324 {"\u200E", "‎"}, // left-to-right mark, U+200E NEW RFC 2070 --> 325 {"\u200F", "‏"}, // right-to-left mark, U+200F NEW RFC 2070 --> 326 {"\u2013", "–"}, // en dash, U+2013 ISOpub --> 327 {"\u2014", "—"}, // em dash, U+2014 ISOpub --> 328 {"\u2018", "‘"}, // left single quotation mark,U+2018 ISOnum --> 329 {"\u2019", "’"}, // right single quotation mark,U+2019 ISOnum --> 330 {"\u201A", "‚"}, // single low-9 quotation mark, U+201A NEW --> 331 {"\u201C", "“"}, // left double quotation mark,U+201C ISOnum --> 332 {"\u201D", "”"}, // right double quotation mark,U+201D ISOnum --> 333 {"\u201E", "„"}, // double low-9 quotation mark, U+201E NEW --> 334 {"\u2020", "†"}, // dagger, U+2020 ISOpub --> 335 {"\u2021", "‡"}, // double dagger, U+2021 ISOpub --> 336 {"\u2030", "‰"}, // per mille sign, U+2030 ISOtech --> 337 {"\u2039", "‹"}, // single left-pointing angle quotation mark,U+2039 ISO proposed --> 338 // <!-- lsaquo is proposed but not yet ISO standardized --> 339 {"\u203A", "›"}, // single right-pointing angle quotation mark,U+203A ISO proposed --> 340 // <!-- rsaquo is proposed but not yet ISO standardized --> 341 {"\u20AC", "€"}, // -- euro sign, U+20AC NEW --> 342 }; 343 344 /** 345 * Reverse of {@link #HTML40_EXTENDED_ESCAPE()} for unescaping purposes. 346 * @return the mapping table 347 */ 348 public static String[][] HTML40_EXTENDED_UNESCAPE() { return HTML40_EXTENDED_UNESCAPE.clone(); } 349 private static final String[][] HTML40_EXTENDED_UNESCAPE = invert(HTML40_EXTENDED_ESCAPE); 350 351 /** 352 * Mapping to escape the basic XML and HTML character entities. 353 * 354 * Namely: {@code " & < >} 355 * @return the mapping table 356 */ 357 public static String[][] BASIC_ESCAPE() { return BASIC_ESCAPE.clone(); } 358 private static final String[][] BASIC_ESCAPE = { 359 {"\"", """}, // " - double-quote 360 {"&", "&"}, // & - ampersand 361 {"<", "<"}, // < - less-than 362 {">", ">"}, // > - greater-than 363 }; 364 365 /** 366 * Reverse of {@link #BASIC_ESCAPE()} for unescaping purposes. 367 * @return the mapping table 368 */ 369 public static String[][] BASIC_UNESCAPE() { return BASIC_UNESCAPE.clone(); } 370 private static final String[][] BASIC_UNESCAPE = invert(BASIC_ESCAPE); 371 372 /** 373 * Mapping to escape the apostrophe character to its XML character entity. 374 * @return the mapping table 375 */ 376 public static String[][] APOS_ESCAPE() { return APOS_ESCAPE.clone(); } 377 private static final String[][] APOS_ESCAPE = { 378 {"'", "'"}, // XML apostrophe 379 }; 380 381 /** 382 * Reverse of {@link #APOS_ESCAPE()} for unescaping purposes. 383 * @return the mapping table 384 */ 385 public static String[][] APOS_UNESCAPE() { return APOS_UNESCAPE.clone(); } 386 private static final String[][] APOS_UNESCAPE = invert(APOS_ESCAPE); 387 388 /** 389 * Mapping to escape the Java control characters. 390 * 391 * Namely: {@code \b \n \t \f \r} 392 * @return the mapping table 393 */ 394 public static String[][] JAVA_CTRL_CHARS_ESCAPE() { return JAVA_CTRL_CHARS_ESCAPE.clone(); } 395 private static final String[][] JAVA_CTRL_CHARS_ESCAPE = { 396 {"\b", "\\b"}, 397 {"\n", "\\n"}, 398 {"\t", "\\t"}, 399 {"\f", "\\f"}, 400 {"\r", "\\r"} 401 }; 402 403 /** 404 * Reverse of {@link #JAVA_CTRL_CHARS_ESCAPE()} for unescaping purposes. 405 * @return the mapping table 406 */ 407 public static String[][] JAVA_CTRL_CHARS_UNESCAPE() { return JAVA_CTRL_CHARS_UNESCAPE.clone(); } 408 private static final String[][] JAVA_CTRL_CHARS_UNESCAPE = invert(JAVA_CTRL_CHARS_ESCAPE); 409 410 /** 411 * Used to invert an escape array into an unescape array 412 * @param array String[][] to be inverted 413 * @return String[][] inverted array 414 */ 415 public static String[][] invert(final String[][] array) { 416 final String[][] newarray = new String[array.length][2]; 417 for(int i = 0; i<array.length; i++) { 418 newarray[i][0] = array[i][1]; 419 newarray[i][1] = array[i][0]; 420 } 421 return newarray; 422 } 423 424 }