src.au.id.jericho.lib.html.CharacterEntityReference Maven / Gradle / Ivy
// Jericho HTML Parser - Java based library for analysing and manipulating HTML
// Version 1.5
// Copyright (C) 2004 Martin Jericho
// http://jerichohtml.sourceforge.net/
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
// http://www.gnu.org/copyleft/lesser.html
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
package au.id.jericho.lib.html;
import java.util.*;
/**
* Represents an HTML Character Entity Reference.
*
* Click here to scroll down to the method summary.
*
* The full list of HTML character entity references can be found at the following URL:
* http://www.w3.org/TR/REC-html40/sgml/entities.html.
*
* Static methods to {@linkplain #encode(CharSequence) encode} and {@linkplain #decode(CharSequence) decode} strings
* and single characters can be found in the {@link CharacterReference} superclass.
*
* The {@link #_apos '} entity reference is however not defined for use in HTML.
* It is defined in the XHTML Special Characters Entity Set,
* and is the only one that is not included in both.
* For this reason, the ' entity reference is recognised by this library in decoding functions, but in encoding functions
* the numeric character reference ' is used instead.
* Most modern browsers support it in both XHTML and HTML, with the notable exception
* of Microsoft Internet Explorer 6.0, which doesn't support it in either.
*
* CharacterEntityReference objects are created using one of the following methods:
*
* - {@link CharacterReference#parse(CharSequence characterReferenceText)}
*
- {@link Source#findNextCharacterReference(int pos)}
*
- {@link Source#findPreviousCharacterReference(int pos)}
*
- {@link Segment#findAllCharacterReferences()}
*
*
* @see CharacterReference
*/
public class CharacterEntityReference extends CharacterReference {
private String name;
/** =   -- no-break space = non-breaking space, U+00A0 ISOnum. */
public static final char _nbsp='\u00A0';
/** ¡ ¡ = ¡ -- inverted exclamation mark, U+00A1 ISOnum. */
public static final char _iexcl='\u00A1';
/** ¢ ¢ = ¢ -- cent sign, U+00A2 ISOnum. */
public static final char _cent='\u00A2';
/** £ £ = £ -- pound sign, U+00A3 ISOnum. */
public static final char _pound='\u00A3';
/** ¤ ¤ = ¤ -- currency sign, U+00A4 ISOnum. */
public static final char _curren='\u00A4';
/** ¥ ¥ = ¥ -- yen sign = yuan sign, U+00A5 ISOnum. */
public static final char _yen='\u00A5';
/** ¦ ¦ = ¦ -- broken bar = broken vertical bar, U+00A6 ISOnum. */
public static final char _brvbar='\u00A6';
/** § § = § -- section sign, U+00A7 ISOnum. */
public static final char _sect='\u00A7';
/** ¨ ¨ = ¨ -- diaeresis = spacing diaeresis, U+00A8 ISOdia. */
public static final char _uml='\u00A8';
/** © © = © -- copyright sign, U+00A9 ISOnum. */
public static final char _copy='\u00A9';
/** ª ª = ª -- feminine ordinal indicator, U+00AA ISOnum. */
public static final char _ordf='\u00AA';
/** « « = « -- left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum. */
public static final char _laquo='\u00AB';
/** ¬ ¬ = ¬ -- not sign = angled dash, U+00AC ISOnum. */
public static final char _not='\u00AC';
/** ­ = ­ -- soft hyphen = discretionary hyphen, U+00AD ISOnum. */
public static final char _shy='\u00AD';
/** ® ® = ® -- registered sign = registered trade mark sign, U+00AE ISOnum. */
public static final char _reg='\u00AE';
/** ¯ ¯ = ¯ -- macron = spacing macron = overline = APL overbar, U+00AF ISOdia. */
public static final char _macr='\u00AF';
/** ° ° = ° -- degree sign, U+00B0 ISOnum. */
public static final char _deg='\u00B0';
/** ± ± = ± -- plus-minus sign = plus-or-minus sign, U+00B1 ISOnum. */
public static final char _plusmn='\u00B1';
/** ² ² = ² -- superscript two = superscript digit two = squared, U+00B2 ISOnum. */
public static final char _sup2='\u00B2';
/** ³ ³ = ³ -- superscript three = superscript digit three = cubed, U+00B3 ISOnum. */
public static final char _sup3='\u00B3';
/** ´ ´ = ´ -- acute accent = spacing acute, U+00B4 ISOdia. */
public static final char _acute='\u00B4';
/** µ µ = µ -- micro sign, U+00B5 ISOnum. */
public static final char _micro='\u00B5';
/** ¶ ¶ = ¶ -- pilcrow sign = paragraph sign, U+00B6 ISOnum. */
public static final char _para='\u00B6';
/** · · = · -- middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum. */
public static final char _middot='\u00B7';
/** ¸ ¸ = ¸ -- cedilla = spacing cedilla, U+00B8 ISOdia. */
public static final char _cedil='\u00B8';
/** ¹ ¹ = ¹ -- superscript one = superscript digit one, U+00B9 ISOnum. */
public static final char _sup1='\u00B9';
/** º º = º -- masculine ordinal indicator, U+00BA ISOnum. */
public static final char _ordm='\u00BA';
/** » » = » -- right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum. */
public static final char _raquo='\u00BB';
/** ¼ ¼ = ¼ -- vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum. */
public static final char _frac14='\u00BC';
/** ½ ½ = ½ -- vulgar fraction one half = fraction one half, U+00BD ISOnum. */
public static final char _frac12='\u00BD';
/** ¾ ¾ = ¾ -- vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum. */
public static final char _frac34='\u00BE';
/** ¿ ¿ = ¿ -- inverted question mark = turned question mark, U+00BF ISOnum. */
public static final char _iquest='\u00BF';
/** À À = À -- latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1. */
public static final char _Agrave='\u00C0';
/** Á Á = Á -- latin capital letter A with acute, U+00C1 ISOlat1. */
public static final char _Aacute='\u00C1';
/** Â Â = Â -- latin capital letter A with circumflex, U+00C2 ISOlat1. */
public static final char _Acirc='\u00C2';
/** Ã Ã = Ã -- latin capital letter A with tilde, U+00C3 ISOlat1. */
public static final char _Atilde='\u00C3';
/** Ä Ä = Ä -- latin capital letter A with diaeresis, U+00C4 ISOlat1. */
public static final char _Auml='\u00C4';
/** Å Å = Å -- latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1. */
public static final char _Aring='\u00C5';
/** Æ Æ = Æ -- latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1. */
public static final char _AElig='\u00C6';
/** Ç Ç = Ç -- latin capital letter C with cedilla, U+00C7 ISOlat1. */
public static final char _Ccedil='\u00C7';
/** È È = È -- latin capital letter E with grave, U+00C8 ISOlat1. */
public static final char _Egrave='\u00C8';
/** É É = É -- latin capital letter E with acute, U+00C9 ISOlat1. */
public static final char _Eacute='\u00C9';
/** Ê Ê = Ê -- latin capital letter E with circumflex, U+00CA ISOlat1. */
public static final char _Ecirc='\u00CA';
/** Ë Ë = Ë -- latin capital letter E with diaeresis, U+00CB ISOlat1. */
public static final char _Euml='\u00CB';
/** Ì Ì = Ì -- latin capital letter I with grave, U+00CC ISOlat1. */
public static final char _Igrave='\u00CC';
/** Í Í = Í -- latin capital letter I with acute, U+00CD ISOlat1. */
public static final char _Iacute='\u00CD';
/** Î Î = Î -- latin capital letter I with circumflex, U+00CE ISOlat1. */
public static final char _Icirc='\u00CE';
/** Ï Ï = Ï -- latin capital letter I with diaeresis, U+00CF ISOlat1. */
public static final char _Iuml='\u00CF';
/** Ð Ð = Ð -- latin capital letter ETH, U+00D0 ISOlat1. */
public static final char _ETH='\u00D0';
/** Ñ Ñ = Ñ -- latin capital letter N with tilde, U+00D1 ISOlat1. */
public static final char _Ntilde='\u00D1';
/** Ò Ò = Ò -- latin capital letter O with grave, U+00D2 ISOlat1. */
public static final char _Ograve='\u00D2';
/** Ó Ó = Ó -- latin capital letter O with acute, U+00D3 ISOlat1. */
public static final char _Oacute='\u00D3';
/** Ô Ô = Ô -- latin capital letter O with circumflex, U+00D4 ISOlat1. */
public static final char _Ocirc='\u00D4';
/** Õ Õ = Õ -- latin capital letter O with tilde, U+00D5 ISOlat1. */
public static final char _Otilde='\u00D5';
/** Ö Ö = Ö -- latin capital letter O with diaeresis, U+00D6 ISOlat1. */
public static final char _Ouml='\u00D6';
/** × × = × -- multiplication sign, U+00D7 ISOnum. */
public static final char _times='\u00D7';
/** Ø Ø = Ø -- latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1. */
public static final char _Oslash='\u00D8';
/** Ù Ù = Ù -- latin capital letter U with grave, U+00D9 ISOlat1. */
public static final char _Ugrave='\u00D9';
/** Ú Ú = Ú -- latin capital letter U with acute, U+00DA ISOlat1. */
public static final char _Uacute='\u00DA';
/** Û Û = Û -- latin capital letter U with circumflex, U+00DB ISOlat1. */
public static final char _Ucirc='\u00DB';
/** Ü Ü = Ü -- latin capital letter U with diaeresis, U+00DC ISOlat1. */
public static final char _Uuml='\u00DC';
/** Ý Ý = Ý -- latin capital letter Y with acute, U+00DD ISOlat1. */
public static final char _Yacute='\u00DD';
/** Þ Þ = Þ -- latin capital letter THORN, U+00DE ISOlat1. */
public static final char _THORN='\u00DE';
/** ß ß = ß -- latin small letter sharp s = ess-zed, U+00DF ISOlat1. */
public static final char _szlig='\u00DF';
/** à à = à -- latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1. */
public static final char _agrave='\u00E0';
/** á á = á -- latin small letter a with acute, U+00E1 ISOlat1. */
public static final char _aacute='\u00E1';
/** â â = â -- latin small letter a with circumflex, U+00E2 ISOlat1. */
public static final char _acirc='\u00E2';
/** ã ã = ã -- latin small letter a with tilde, U+00E3 ISOlat1. */
public static final char _atilde='\u00E3';
/** ä ä = ä -- latin small letter a with diaeresis, U+00E4 ISOlat1. */
public static final char _auml='\u00E4';
/** å å = å -- latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1. */
public static final char _aring='\u00E5';
/** æ æ = æ -- latin small letter ae = latin small ligature ae, U+00E6 ISOlat1. */
public static final char _aelig='\u00E6';
/** ç ç = ç -- latin small letter c with cedilla, U+00E7 ISOlat1. */
public static final char _ccedil='\u00E7';
/** è è = è -- latin small letter e with grave, U+00E8 ISOlat1. */
public static final char _egrave='\u00E8';
/** é é = é -- latin small letter e with acute, U+00E9 ISOlat1. */
public static final char _eacute='\u00E9';
/** ê ê = ê -- latin small letter e with circumflex, U+00EA ISOlat1. */
public static final char _ecirc='\u00EA';
/** ë ë = ë -- latin small letter e with diaeresis, U+00EB ISOlat1. */
public static final char _euml='\u00EB';
/** ì ì = ì -- latin small letter i with grave, U+00EC ISOlat1. */
public static final char _igrave='\u00EC';
/** í í = í -- latin small letter i with acute, U+00ED ISOlat1. */
public static final char _iacute='\u00ED';
/** î î = î -- latin small letter i with circumflex, U+00EE ISOlat1. */
public static final char _icirc='\u00EE';
/** ï ï = ï -- latin small letter i with diaeresis, U+00EF ISOlat1. */
public static final char _iuml='\u00EF';
/** ð ð = ð -- latin small letter eth, U+00F0 ISOlat1. */
public static final char _eth='\u00F0';
/** ñ ñ = ñ -- latin small letter n with tilde, U+00F1 ISOlat1. */
public static final char _ntilde='\u00F1';
/** ò ò = ò -- latin small letter o with grave, U+00F2 ISOlat1. */
public static final char _ograve='\u00F2';
/** ó ó = ó -- latin small letter o with acute, U+00F3 ISOlat1. */
public static final char _oacute='\u00F3';
/** ô ô = ô -- latin small letter o with circumflex, U+00F4 ISOlat1. */
public static final char _ocirc='\u00F4';
/** õ õ = õ -- latin small letter o with tilde, U+00F5 ISOlat1. */
public static final char _otilde='\u00F5';
/** ö ö = ö -- latin small letter o with diaeresis, U+00F6 ISOlat1. */
public static final char _ouml='\u00F6';
/** ÷ ÷ = ÷ -- division sign, U+00F7 ISOnum. */
public static final char _divide='\u00F7';
/** ø ø = ø -- latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1. */
public static final char _oslash='\u00F8';
/** ù ù = ù -- latin small letter u with grave, U+00F9 ISOlat1. */
public static final char _ugrave='\u00F9';
/** ú ú = ú -- latin small letter u with acute, U+00FA ISOlat1. */
public static final char _uacute='\u00FA';
/** û û = û -- latin small letter u with circumflex, U+00FB ISOlat1. */
public static final char _ucirc='\u00FB';
/** ü ü = ü -- latin small letter u with diaeresis, U+00FC ISOlat1. */
public static final char _uuml='\u00FC';
/** ý ý = ý -- latin small letter y with acute, U+00FD ISOlat1. */
public static final char _yacute='\u00FD';
/** þ þ = þ -- latin small letter thorn, U+00FE ISOlat1. */
public static final char _thorn='\u00FE';
/** ÿ ÿ = ÿ -- latin small letter y with diaeresis, U+00FF ISOlat1. */
public static final char _yuml='\u00FF';
/** ƒ ƒ = ƒ -- latin small letter f with hook = function = florin, U+0192 ISOtech. */
public static final char _fnof='\u0192';
/** Α Α = Α -- greek capital letter alpha, U+0391. */
public static final char _Alpha='\u0391';
/** Β Β = Β -- greek capital letter beta, U+0392. */
public static final char _Beta='\u0392';
/** Γ Γ = Γ -- greek capital letter gamma, U+0393 ISOgrk3. */
public static final char _Gamma='\u0393';
/** Δ Δ = Δ -- greek capital letter delta, U+0394 ISOgrk3. */
public static final char _Delta='\u0394';
/** Ε Ε = Ε -- greek capital letter epsilon, U+0395. */
public static final char _Epsilon='\u0395';
/** Ζ Ζ = Ζ -- greek capital letter zeta, U+0396. */
public static final char _Zeta='\u0396';
/** Η Η = Η -- greek capital letter eta, U+0397. */
public static final char _Eta='\u0397';
/** Θ Θ = Θ -- greek capital letter theta, U+0398 ISOgrk3. */
public static final char _Theta='\u0398';
/** Ι Ι = Ι -- greek capital letter iota, U+0399. */
public static final char _Iota='\u0399';
/** Κ Κ = Κ -- greek capital letter kappa, U+039A. */
public static final char _Kappa='\u039A';
/** Λ Λ = Λ -- greek capital letter lambda, U+039B ISOgrk3. */
public static final char _Lambda='\u039B';
/** Μ Μ = Μ -- greek capital letter mu, U+039C. */
public static final char _Mu='\u039C';
/** Ν Ν = Ν -- greek capital letter nu, U+039D. */
public static final char _Nu='\u039D';
/** Ξ Ξ = Ξ -- greek capital letter xi, U+039E ISOgrk3. */
public static final char _Xi='\u039E';
/** Ο Ο = Ο -- greek capital letter omicron, U+039F. */
public static final char _Omicron='\u039F';
/** Π Π = Π -- greek capital letter pi, U+03A0 ISOgrk3. */
public static final char _Pi='\u03A0';
/** Ρ Ρ = Ρ -- greek capital letter rho, U+03A1. */
public static final char _Rho='\u03A1';
/** Σ Σ = Σ -- greek capital letter sigma, U+03A3 ISOgrk3. */
public static final char _Sigma='\u03A3';
/** Τ Τ = Τ -- greek capital letter tau, U+03A4. */
public static final char _Tau='\u03A4';
/** Υ Υ = Υ -- greek capital letter upsilon, U+03A5 ISOgrk3. */
public static final char _Upsilon='\u03A5';
/** Φ Φ = Φ -- greek capital letter phi, U+03A6 ISOgrk3. */
public static final char _Phi='\u03A6';
/** Χ Χ = Χ -- greek capital letter chi, U+03A7. */
public static final char _Chi='\u03A7';
/** Ψ Ψ = Ψ -- greek capital letter psi, U+03A8 ISOgrk3. */
public static final char _Psi='\u03A8';
/** Ω Ω = Ω -- greek capital letter omega, U+03A9 ISOgrk3. */
public static final char _Omega='\u03A9';
/** α α = α -- greek small letter alpha, U+03B1 ISOgrk3. */
public static final char _alpha='\u03B1';
/** β β = β -- greek small letter beta, U+03B2 ISOgrk3. */
public static final char _beta='\u03B2';
/** γ γ = γ -- greek small letter gamma, U+03B3 ISOgrk3. */
public static final char _gamma='\u03B3';
/** δ δ = δ -- greek small letter delta, U+03B4 ISOgrk3. */
public static final char _delta='\u03B4';
/** ε ε = ε -- greek small letter epsilon, U+03B5 ISOgrk3. */
public static final char _epsilon='\u03B5';
/** ζ ζ = ζ -- greek small letter zeta, U+03B6 ISOgrk3. */
public static final char _zeta='\u03B6';
/** η η = η -- greek small letter eta, U+03B7 ISOgrk3. */
public static final char _eta='\u03B7';
/** θ θ = θ -- greek small letter theta, U+03B8 ISOgrk3. */
public static final char _theta='\u03B8';
/** ι ι = ι -- greek small letter iota, U+03B9 ISOgrk3. */
public static final char _iota='\u03B9';
/** κ κ = κ -- greek small letter kappa, U+03BA ISOgrk3. */
public static final char _kappa='\u03BA';
/** λ λ = λ -- greek small letter lambda, U+03BB ISOgrk3. */
public static final char _lambda='\u03BB';
/** μ μ = μ -- greek small letter mu, U+03BC ISOgrk3. */
public static final char _mu='\u03BC';
/** ν ν = ν -- greek small letter nu, U+03BD ISOgrk3. */
public static final char _nu='\u03BD';
/** ξ ξ = ξ -- greek small letter xi, U+03BE ISOgrk3. */
public static final char _xi='\u03BE';
/** ο ο = ο -- greek small letter omicron, U+03BF NEW. */
public static final char _omicron='\u03BF';
/** π π = π -- greek small letter pi, U+03C0 ISOgrk3. */
public static final char _pi='\u03C0';
/** ρ ρ = ρ -- greek small letter rho, U+03C1 ISOgrk3. */
public static final char _rho='\u03C1';
/** ς ς = ς -- greek small letter final sigma, U+03C2 ISOgrk3. */
public static final char _sigmaf='\u03C2';
/** σ σ = σ -- greek small letter sigma, U+03C3 ISOgrk3. */
public static final char _sigma='\u03C3';
/** τ τ = τ -- greek small letter tau, U+03C4 ISOgrk3. */
public static final char _tau='\u03C4';
/** υ υ = υ -- greek small letter upsilon, U+03C5 ISOgrk3. */
public static final char _upsilon='\u03C5';
/** φ φ = φ -- greek small letter phi, U+03C6 ISOgrk3. */
public static final char _phi='\u03C6';
/** χ χ = χ -- greek small letter chi, U+03C7 ISOgrk3. */
public static final char _chi='\u03C7';
/** ψ ψ = ψ -- greek small letter psi, U+03C8 ISOgrk3. */
public static final char _psi='\u03C8';
/** ω ω = ω -- greek small letter omega, U+03C9 ISOgrk3. */
public static final char _omega='\u03C9';
/** ϑ ϑ = ϑ -- greek small letter theta symbol, U+03D1 NEW. */
public static final char _thetasym='\u03D1';
/** ϒ ϒ = ϒ -- greek upsilon with hook symbol, U+03D2 NEW. */
public static final char _upsih='\u03D2';
/** ϖ ϖ = ϖ -- greek pi symbol, U+03D6 ISOgrk3. */
public static final char _piv='\u03D6';
/** • • = • -- bullet = black small circle, U+2022 ISOpub
(see comments).bullet is NOT the same as bullet operator, U+2219
*/
public static final char _bull='\u2022';
/** … … = … -- horizontal ellipsis = three dot leader, U+2026 ISOpub. */
public static final char _hellip='\u2026';
/** ′ ′ = ′ -- prime = minutes = feet, U+2032 ISOtech. */
public static final char _prime='\u2032';
/** ″ ″ = ″ -- double prime = seconds = inches, U+2033 ISOtech. */
public static final char _Prime='\u2033';
/** ‾ ‾ = ‾ -- overline = spacing overscore, U+203E NEW. */
public static final char _oline='\u203E';
/** ⁄ ⁄ = ⁄ -- fraction slash, U+2044 NEW. */
public static final char _frasl='\u2044';
/** ℘ ℘ = ℘ -- script capital P = power set = Weierstrass p, U+2118 ISOamso. */
public static final char _weierp='\u2118';
/** ℑ ℑ = ℑ -- black-letter capital I = imaginary part, U+2111 ISOamso. */
public static final char _image='\u2111';
/** ℜ ℜ = ℜ -- black-letter capital R = real part symbol, U+211C ISOamso. */
public static final char _real='\u211C';
/** ™ ™ = ™ -- trade mark sign, U+2122 ISOnum. */
public static final char _trade='\u2122';
/** ℵ ℵ = ℵ -- alef symbol = first transfinite cardinal, U+2135 NEW
(see comments).alef symbol is NOT the same as hebrew letter alef, U+05D0 although the same glyph could be used to depict both characters
*/
public static final char _alefsym='\u2135';
/** ← ← = ← -- leftwards arrow, U+2190 ISOnum. */
public static final char _larr='\u2190';
/** ↑ ↑ = ↑ -- upwards arrow, U+2191 ISOnum. */
public static final char _uarr='\u2191';
/** → → = → -- rightwards arrow, U+2192 ISOnum. */
public static final char _rarr='\u2192';
/** ↓ ↓ = ↓ -- downwards arrow, U+2193 ISOnum. */
public static final char _darr='\u2193';
/** ↔ ↔ = ↔ -- left right arrow, U+2194 ISOamsa. */
public static final char _harr='\u2194';
/** ↵ ↵ = ↵ -- downwards arrow with corner leftwards = carriage return, U+21B5 NEW. */
public static final char _crarr='\u21B5';
/** ⇐ ⇐ = ⇐ -- leftwards double arrow, U+21D0 ISOtech
(see comments).ISO 10646 does not say that lArr is the same as the 'is implied by' arrow but also does not have any other character for that function. So ? lArr can be used for 'is implied by' as ISOtech suggests
*/
public static final char _lArr='\u21D0';
/** ⇑ ⇑ = ⇑ -- upwards double arrow, U+21D1 ISOamsa. */
public static final char _uArr='\u21D1';
/** ⇒ ⇒ = ⇒ -- rightwards double arrow, U+21D2 ISOtech
(see comments).ISO 10646 does not say this is the 'implies' character but does not have another character with this function so ? rArr can be used for 'implies' as ISOtech suggests
*/
public static final char _rArr='\u21D2';
/** ⇓ ⇓ = ⇓ -- downwards double arrow, U+21D3 ISOamsa. */
public static final char _dArr='\u21D3';
/** ⇔ ⇔ = ⇔ -- left right double arrow, U+21D4 ISOamsa. */
public static final char _hArr='\u21D4';
/** ∀ ∀ = ∀ -- for all, U+2200 ISOtech. */
public static final char _forall='\u2200';
/** ∂ ∂ = ∂ -- partial differential, U+2202 ISOtech. */
public static final char _part='\u2202';
/** ∃ ∃ = ∃ -- there exists, U+2203 ISOtech. */
public static final char _exist='\u2203';
/** ∅ ∅ = ∅ -- empty set = null set = diameter, U+2205 ISOamso. */
public static final char _empty='\u2205';
/** ∇ ∇ = ∇ -- nabla = backward difference, U+2207 ISOtech. */
public static final char _nabla='\u2207';
/** ∈ ∈ = ∈ -- element of, U+2208 ISOtech. */
public static final char _isin='\u2208';
/** ∉ ∉ = ∉ -- not an element of, U+2209 ISOtech. */
public static final char _notin='\u2209';
/** ∋ ∋ = ∋ -- contains as member, U+220B ISOtech
(see comments).should there be a more memorable name than 'ni'?
*/
public static final char _ni='\u220B';
/** ∏ ∏ = ∏ -- n-ary product = product sign, U+220F ISOamsb
(see comments).prod is NOT the same character as U+03A0 'greek capital letter pi' though the same glyph might be used for both
*/
public static final char _prod='\u220F';
/** ∑ ∑ = ∑ -- n-ary summation, U+2211 ISOamsb
(see comments).sum is NOT the same character as U+03A3 'greek capital letter sigma' though the same glyph might be used for both
*/
public static final char _sum='\u2211';
/** − − = − -- minus sign, U+2212 ISOtech. */
public static final char _minus='\u2212';
/** ∗ ∗ = ∗ -- asterisk operator, U+2217 ISOtech. */
public static final char _lowast='\u2217';
/** √ √ = √ -- square root = radical sign, U+221A ISOtech. */
public static final char _radic='\u221A';
/** ∝ ∝ = ∝ -- proportional to, U+221D ISOtech. */
public static final char _prop='\u221D';
/** ∞ ∞ = ∞ -- infinity, U+221E ISOtech. */
public static final char _infin='\u221E';
/** ∠ ∠ = ∠ -- angle, U+2220 ISOamso. */
public static final char _ang='\u2220';
/** ∧ ∧ = ∧ -- logical and = wedge, U+2227 ISOtech. */
public static final char _and='\u2227';
/** ∨ ∨ = ∨ -- logical or = vee, U+2228 ISOtech. */
public static final char _or='\u2228';
/** ∩ ∩ = ∩ -- intersection = cap, U+2229 ISOtech. */
public static final char _cap='\u2229';
/** ∪ ∪ = ∪ -- union = cup, U+222A ISOtech. */
public static final char _cup='\u222A';
/** ∫ ∫ = ∫ -- integral, U+222B ISOtech. */
public static final char _int='\u222B';
/** ∴ ∴ = ∴ -- therefore, U+2234 ISOtech. */
public static final char _there4='\u2234';
/** ∼ ∼ = ∼ -- tilde operator = varies with = similar to, U+223C ISOtech
(see comments).tilde operator is NOT the same character as the tilde, U+007E, although the same glyph might be used to represent both
*/
public static final char _sim='\u223C';
/** ≅ ≅ = ≅ -- approximately equal to, U+2245 ISOtech. */
public static final char _cong='\u2245';
/** ≈ ≈ = ≈ -- almost equal to = asymptotic to, U+2248 ISOamsr. */
public static final char _asymp='\u2248';
/** ≠ ≠ = ≠ -- not equal to, U+2260 ISOtech. */
public static final char _ne='\u2260';
/** ≡ ≡ = ≡ -- identical to, U+2261 ISOtech. */
public static final char _equiv='\u2261';
/** ≤ ≤ = ≤ -- less-than or equal to, U+2264 ISOtech. */
public static final char _le='\u2264';
/** ≥ ≥ = ≥ -- greater-than or equal to, U+2265 ISOtech. */
public static final char _ge='\u2265';
/** ⊂ ⊂ = ⊂ -- subset of, U+2282 ISOtech. */
public static final char _sub='\u2282';
/** ⊃ ⊃ = ⊃ -- superset of, U+2283 ISOtech
(see comments).note that nsup, 'not a superset of, U+2283' is not covered by the Symbol font encoding and is not included. Should it be, for symmetry? It is in ISOamsn
*/
public static final char _sup='\u2283';
/** ⊄ ⊄ = ⊄ -- not a subset of, U+2284 ISOamsn. */
public static final char _nsub='\u2284';
/** ⊆ ⊆ = ⊆ -- subset of or equal to, U+2286 ISOtech. */
public static final char _sube='\u2286';
/** ⊇ ⊇ = ⊇ -- superset of or equal to, U+2287 ISOtech. */
public static final char _supe='\u2287';
/** ⊕ ⊕ = ⊕ -- circled plus = direct sum, U+2295 ISOamsb. */
public static final char _oplus='\u2295';
/** ⊗ ⊗ = ⊗ -- circled times = vector product, U+2297 ISOamsb. */
public static final char _otimes='\u2297';
/** ⊥ ⊥ = ⊥ -- up tack = orthogonal to = perpendicular, U+22A5 ISOtech. */
public static final char _perp='\u22A5';
/** ⋅ ⋅ = ⋅ -- dot operator, U+22C5 ISOamsb
(see comments).dot operator is NOT the same character as U+00B7 middle dot
*/
public static final char _sdot='\u22C5';
/** ⌈ ⌈ = ⌈ -- left ceiling = APL upstile, U+2308 ISOamsc. */
public static final char _lceil='\u2308';
/** ⌉ ⌉ = ⌉ -- right ceiling, U+2309 ISOamsc. */
public static final char _rceil='\u2309';
/** ⌊ ⌊ = ⌊ -- left floor = APL downstile, U+230A ISOamsc. */
public static final char _lfloor='\u230A';
/** ⌋ ⌋ = ⌋ -- right floor, U+230B ISOamsc. */
public static final char _rfloor='\u230B';
/** ⟨ ⟨ = 〈 -- left-pointing angle bracket = bra, U+2329 ISOtech
(see comments).lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation mark'
*/
public static final char _lang='\u2329';
/** ⟩ ⟩ = 〉 -- right-pointing angle bracket = ket, U+232A ISOtech
(see comments).rang is NOT the same character as U+003E 'greater than' or U+203A 'single right-pointing angle quotation mark'
*/
public static final char _rang='\u232A';
/** ◊ ◊ = ◊ -- lozenge, U+25CA ISOpub. */
public static final char _loz='\u25CA';
/** ♠ ♠ = ♠ -- black spade suit, U+2660 ISOpub
(see comments).black here seems to mean filled as opposed to hollow
*/
public static final char _spades='\u2660';
/** ♣ ♣ = ♣ -- black club suit = shamrock, U+2663 ISOpub. */
public static final char _clubs='\u2663';
/** ♥ ♥ = ♥ -- black heart suit = valentine, U+2665 ISOpub. */
public static final char _hearts='\u2665';
/** ♦ ♦ = ♦ -- black diamond suit, U+2666 ISOpub. */
public static final char _diams='\u2666';
/** " " = " -- quotation mark = APL quote, U+0022 ISOnum. */
public static final char _quot='\u0022';
/** & & = & -- ampersand, U+0026 ISOnum. */
public static final char _amp='\u0026';
/** < < = < -- less-than sign, U+003C ISOnum. */
public static final char _lt='\u003C';
/** > > = > -- greater-than sign, U+003E ISOnum. */
public static final char _gt='\u003E';
/** ΠΠ= Π-- latin capital ligature OE, U+0152 ISOlat2. */
public static final char _OElig='\u0152';
/** œ œ = œ -- latin small ligature oe, U+0153 ISOlat2
(see comments).ligature is a misnomer, this is a separate character in some languages
*/
public static final char _oelig='\u0153';
/** Š Š = Š -- latin capital letter S with caron, U+0160 ISOlat2. */
public static final char _Scaron='\u0160';
/** š š = š -- latin small letter s with caron, U+0161 ISOlat2. */
public static final char _scaron='\u0161';
/** Ÿ Ÿ = Ÿ -- latin capital letter Y with diaeresis, U+0178 ISOlat2. */
public static final char _Yuml='\u0178';
/** ˆ ˆ = ˆ -- modifier letter circumflex accent, U+02C6 ISOpub. */
public static final char _circ='\u02C6';
/** ˜ ˜ = ˜ -- small tilde, U+02DC ISOdia. */
public static final char _tilde='\u02DC';
/**   =   -- en space, U+2002 ISOpub. */
public static final char _ensp='\u2002';
/**   =   -- em space, U+2003 ISOpub. */
public static final char _emsp='\u2003';
/**   =   -- thin space, U+2009 ISOpub. */
public static final char _thinsp='\u2009';
/** ‌ = ‌ -- zero width non-joiner, U+200C NEW RFC 2070. */
public static final char _zwnj='\u200C';
/** ‍ = ‍ -- zero width joiner, U+200D NEW RFC 2070. */
public static final char _zwj='\u200D';
/** ‎ = ‎ -- left-to-right mark, U+200E NEW RFC 2070. */
public static final char _lrm='\u200E';
/** ‏ = ‏ -- right-to-left mark, U+200F NEW RFC 2070. */
public static final char _rlm='\u200F';
/** – – = – -- en dash, U+2013 ISOpub. */
public static final char _ndash='\u2013';
/** — — = — -- em dash, U+2014 ISOpub. */
public static final char _mdash='\u2014';
/** ‘ ‘ = ‘ -- left single quotation mark, U+2018 ISOnum. */
public static final char _lsquo='\u2018';
/** ’ ’ = ’ -- right single quotation mark, U+2019 ISOnum. */
public static final char _rsquo='\u2019';
/** ‚ ‚ = ‚ -- single low-9 quotation mark, U+201A NEW. */
public static final char _sbquo='\u201A';
/** “ “ = “ -- left double quotation mark, U+201C ISOnum. */
public static final char _ldquo='\u201C';
/** ” ” = ” -- right double quotation mark, U+201D ISOnum. */
public static final char _rdquo='\u201D';
/** „ „ = „ -- double low-9 quotation mark, U+201E NEW. */
public static final char _bdquo='\u201E';
/** † † = † -- dagger, U+2020 ISOpub. */
public static final char _dagger='\u2020';
/** ‡ ‡ = ‡ -- double dagger, U+2021 ISOpub. */
public static final char _Dagger='\u2021';
/** ‰ ‰ = ‰ -- per mille sign, U+2030 ISOtech. */
public static final char _permil='\u2030';
/** ‹ ‹ = ‹ -- single left-pointing angle quotation mark, U+2039 ISO proposed
(see comments).lsaquo is proposed but not yet ISO standardized
*/
public static final char _lsaquo='\u2039';
/** › › = › -- single right-pointing angle quotation mark, U+203A ISO proposed
(see comments).rsaquo is proposed but not yet ISO standardized
*/
public static final char _rsaquo='\u203A';
/** € € = € -- euro sign, U+20AC NEW. */
public static final char _euro='\u20AC';
/**
* ' ' = ' -- apostrophe = APL quote, U+0027 ISOnum
(see comments).
* apos is only defined for use in XHTML (see the XHTML Special Characters Entity Set), but not in HTML.
* @see CharacterReference#ApostropheEncoded
*/
public static final char _apos='\'';
private static Map NAME_TO_CODE_POINT_MAP=new HashMap(337,1.0F); // 253 entities in total
private static IntStringHashMap CODE_POINT_TO_NAME_MAP;
private static int MAX_NAME_LENGTH=0;
static {
NAME_TO_CODE_POINT_MAP.put("nbsp",new Integer(_nbsp));
NAME_TO_CODE_POINT_MAP.put("iexcl",new Integer(_iexcl));
NAME_TO_CODE_POINT_MAP.put("cent",new Integer(_cent));
NAME_TO_CODE_POINT_MAP.put("pound",new Integer(_pound));
NAME_TO_CODE_POINT_MAP.put("curren",new Integer(_curren));
NAME_TO_CODE_POINT_MAP.put("yen",new Integer(_yen));
NAME_TO_CODE_POINT_MAP.put("brvbar",new Integer(_brvbar));
NAME_TO_CODE_POINT_MAP.put("sect",new Integer(_sect));
NAME_TO_CODE_POINT_MAP.put("uml",new Integer(_uml));
NAME_TO_CODE_POINT_MAP.put("copy",new Integer(_copy));
NAME_TO_CODE_POINT_MAP.put("ordf",new Integer(_ordf));
NAME_TO_CODE_POINT_MAP.put("laquo",new Integer(_laquo));
NAME_TO_CODE_POINT_MAP.put("not",new Integer(_not));
NAME_TO_CODE_POINT_MAP.put("shy",new Integer(_shy));
NAME_TO_CODE_POINT_MAP.put("reg",new Integer(_reg));
NAME_TO_CODE_POINT_MAP.put("macr",new Integer(_macr));
NAME_TO_CODE_POINT_MAP.put("deg",new Integer(_deg));
NAME_TO_CODE_POINT_MAP.put("plusmn",new Integer(_plusmn));
NAME_TO_CODE_POINT_MAP.put("sup2",new Integer(_sup2));
NAME_TO_CODE_POINT_MAP.put("sup3",new Integer(_sup3));
NAME_TO_CODE_POINT_MAP.put("acute",new Integer(_acute));
NAME_TO_CODE_POINT_MAP.put("micro",new Integer(_micro));
NAME_TO_CODE_POINT_MAP.put("para",new Integer(_para));
NAME_TO_CODE_POINT_MAP.put("middot",new Integer(_middot));
NAME_TO_CODE_POINT_MAP.put("cedil",new Integer(_cedil));
NAME_TO_CODE_POINT_MAP.put("sup1",new Integer(_sup1));
NAME_TO_CODE_POINT_MAP.put("ordm",new Integer(_ordm));
NAME_TO_CODE_POINT_MAP.put("raquo",new Integer(_raquo));
NAME_TO_CODE_POINT_MAP.put("frac14",new Integer(_frac14));
NAME_TO_CODE_POINT_MAP.put("frac12",new Integer(_frac12));
NAME_TO_CODE_POINT_MAP.put("frac34",new Integer(_frac34));
NAME_TO_CODE_POINT_MAP.put("iquest",new Integer(_iquest));
NAME_TO_CODE_POINT_MAP.put("Agrave",new Integer(_Agrave));
NAME_TO_CODE_POINT_MAP.put("Aacute",new Integer(_Aacute));
NAME_TO_CODE_POINT_MAP.put("Acirc",new Integer(_Acirc));
NAME_TO_CODE_POINT_MAP.put("Atilde",new Integer(_Atilde));
NAME_TO_CODE_POINT_MAP.put("Auml",new Integer(_Auml));
NAME_TO_CODE_POINT_MAP.put("Aring",new Integer(_Aring));
NAME_TO_CODE_POINT_MAP.put("AElig",new Integer(_AElig));
NAME_TO_CODE_POINT_MAP.put("Ccedil",new Integer(_Ccedil));
NAME_TO_CODE_POINT_MAP.put("Egrave",new Integer(_Egrave));
NAME_TO_CODE_POINT_MAP.put("Eacute",new Integer(_Eacute));
NAME_TO_CODE_POINT_MAP.put("Ecirc",new Integer(_Ecirc));
NAME_TO_CODE_POINT_MAP.put("Euml",new Integer(_Euml));
NAME_TO_CODE_POINT_MAP.put("Igrave",new Integer(_Igrave));
NAME_TO_CODE_POINT_MAP.put("Iacute",new Integer(_Iacute));
NAME_TO_CODE_POINT_MAP.put("Icirc",new Integer(_Icirc));
NAME_TO_CODE_POINT_MAP.put("Iuml",new Integer(_Iuml));
NAME_TO_CODE_POINT_MAP.put("ETH",new Integer(_ETH));
NAME_TO_CODE_POINT_MAP.put("Ntilde",new Integer(_Ntilde));
NAME_TO_CODE_POINT_MAP.put("Ograve",new Integer(_Ograve));
NAME_TO_CODE_POINT_MAP.put("Oacute",new Integer(_Oacute));
NAME_TO_CODE_POINT_MAP.put("Ocirc",new Integer(_Ocirc));
NAME_TO_CODE_POINT_MAP.put("Otilde",new Integer(_Otilde));
NAME_TO_CODE_POINT_MAP.put("Ouml",new Integer(_Ouml));
NAME_TO_CODE_POINT_MAP.put("times",new Integer(_times));
NAME_TO_CODE_POINT_MAP.put("Oslash",new Integer(_Oslash));
NAME_TO_CODE_POINT_MAP.put("Ugrave",new Integer(_Ugrave));
NAME_TO_CODE_POINT_MAP.put("Uacute",new Integer(_Uacute));
NAME_TO_CODE_POINT_MAP.put("Ucirc",new Integer(_Ucirc));
NAME_TO_CODE_POINT_MAP.put("Uuml",new Integer(_Uuml));
NAME_TO_CODE_POINT_MAP.put("Yacute",new Integer(_Yacute));
NAME_TO_CODE_POINT_MAP.put("THORN",new Integer(_THORN));
NAME_TO_CODE_POINT_MAP.put("szlig",new Integer(_szlig));
NAME_TO_CODE_POINT_MAP.put("agrave",new Integer(_agrave));
NAME_TO_CODE_POINT_MAP.put("aacute",new Integer(_aacute));
NAME_TO_CODE_POINT_MAP.put("acirc",new Integer(_acirc));
NAME_TO_CODE_POINT_MAP.put("atilde",new Integer(_atilde));
NAME_TO_CODE_POINT_MAP.put("auml",new Integer(_auml));
NAME_TO_CODE_POINT_MAP.put("aring",new Integer(_aring));
NAME_TO_CODE_POINT_MAP.put("aelig",new Integer(_aelig));
NAME_TO_CODE_POINT_MAP.put("ccedil",new Integer(_ccedil));
NAME_TO_CODE_POINT_MAP.put("egrave",new Integer(_egrave));
NAME_TO_CODE_POINT_MAP.put("eacute",new Integer(_eacute));
NAME_TO_CODE_POINT_MAP.put("ecirc",new Integer(_ecirc));
NAME_TO_CODE_POINT_MAP.put("euml",new Integer(_euml));
NAME_TO_CODE_POINT_MAP.put("igrave",new Integer(_igrave));
NAME_TO_CODE_POINT_MAP.put("iacute",new Integer(_iacute));
NAME_TO_CODE_POINT_MAP.put("icirc",new Integer(_icirc));
NAME_TO_CODE_POINT_MAP.put("iuml",new Integer(_iuml));
NAME_TO_CODE_POINT_MAP.put("eth",new Integer(_eth));
NAME_TO_CODE_POINT_MAP.put("ntilde",new Integer(_ntilde));
NAME_TO_CODE_POINT_MAP.put("ograve",new Integer(_ograve));
NAME_TO_CODE_POINT_MAP.put("oacute",new Integer(_oacute));
NAME_TO_CODE_POINT_MAP.put("ocirc",new Integer(_ocirc));
NAME_TO_CODE_POINT_MAP.put("otilde",new Integer(_otilde));
NAME_TO_CODE_POINT_MAP.put("ouml",new Integer(_ouml));
NAME_TO_CODE_POINT_MAP.put("divide",new Integer(_divide));
NAME_TO_CODE_POINT_MAP.put("oslash",new Integer(_oslash));
NAME_TO_CODE_POINT_MAP.put("ugrave",new Integer(_ugrave));
NAME_TO_CODE_POINT_MAP.put("uacute",new Integer(_uacute));
NAME_TO_CODE_POINT_MAP.put("ucirc",new Integer(_ucirc));
NAME_TO_CODE_POINT_MAP.put("uuml",new Integer(_uuml));
NAME_TO_CODE_POINT_MAP.put("yacute",new Integer(_yacute));
NAME_TO_CODE_POINT_MAP.put("thorn",new Integer(_thorn));
NAME_TO_CODE_POINT_MAP.put("yuml",new Integer(_yuml));
NAME_TO_CODE_POINT_MAP.put("fnof",new Integer(_fnof));
NAME_TO_CODE_POINT_MAP.put("Alpha",new Integer(_Alpha));
NAME_TO_CODE_POINT_MAP.put("Beta",new Integer(_Beta));
NAME_TO_CODE_POINT_MAP.put("Gamma",new Integer(_Gamma));
NAME_TO_CODE_POINT_MAP.put("Delta",new Integer(_Delta));
NAME_TO_CODE_POINT_MAP.put("Epsilon",new Integer(_Epsilon));
NAME_TO_CODE_POINT_MAP.put("Zeta",new Integer(_Zeta));
NAME_TO_CODE_POINT_MAP.put("Eta",new Integer(_Eta));
NAME_TO_CODE_POINT_MAP.put("Theta",new Integer(_Theta));
NAME_TO_CODE_POINT_MAP.put("Iota",new Integer(_Iota));
NAME_TO_CODE_POINT_MAP.put("Kappa",new Integer(_Kappa));
NAME_TO_CODE_POINT_MAP.put("Lambda",new Integer(_Lambda));
NAME_TO_CODE_POINT_MAP.put("Mu",new Integer(_Mu));
NAME_TO_CODE_POINT_MAP.put("Nu",new Integer(_Nu));
NAME_TO_CODE_POINT_MAP.put("Xi",new Integer(_Xi));
NAME_TO_CODE_POINT_MAP.put("Omicron",new Integer(_Omicron));
NAME_TO_CODE_POINT_MAP.put("Pi",new Integer(_Pi));
NAME_TO_CODE_POINT_MAP.put("Rho",new Integer(_Rho));
NAME_TO_CODE_POINT_MAP.put("Sigma",new Integer(_Sigma));
NAME_TO_CODE_POINT_MAP.put("Tau",new Integer(_Tau));
NAME_TO_CODE_POINT_MAP.put("Upsilon",new Integer(_Upsilon));
NAME_TO_CODE_POINT_MAP.put("Phi",new Integer(_Phi));
NAME_TO_CODE_POINT_MAP.put("Chi",new Integer(_Chi));
NAME_TO_CODE_POINT_MAP.put("Psi",new Integer(_Psi));
NAME_TO_CODE_POINT_MAP.put("Omega",new Integer(_Omega));
NAME_TO_CODE_POINT_MAP.put("alpha",new Integer(_alpha));
NAME_TO_CODE_POINT_MAP.put("beta",new Integer(_beta));
NAME_TO_CODE_POINT_MAP.put("gamma",new Integer(_gamma));
NAME_TO_CODE_POINT_MAP.put("delta",new Integer(_delta));
NAME_TO_CODE_POINT_MAP.put("epsilon",new Integer(_epsilon));
NAME_TO_CODE_POINT_MAP.put("zeta",new Integer(_zeta));
NAME_TO_CODE_POINT_MAP.put("eta",new Integer(_eta));
NAME_TO_CODE_POINT_MAP.put("theta",new Integer(_theta));
NAME_TO_CODE_POINT_MAP.put("iota",new Integer(_iota));
NAME_TO_CODE_POINT_MAP.put("kappa",new Integer(_kappa));
NAME_TO_CODE_POINT_MAP.put("lambda",new Integer(_lambda));
NAME_TO_CODE_POINT_MAP.put("mu",new Integer(_mu));
NAME_TO_CODE_POINT_MAP.put("nu",new Integer(_nu));
NAME_TO_CODE_POINT_MAP.put("xi",new Integer(_xi));
NAME_TO_CODE_POINT_MAP.put("omicron",new Integer(_omicron));
NAME_TO_CODE_POINT_MAP.put("pi",new Integer(_pi));
NAME_TO_CODE_POINT_MAP.put("rho",new Integer(_rho));
NAME_TO_CODE_POINT_MAP.put("sigmaf",new Integer(_sigmaf));
NAME_TO_CODE_POINT_MAP.put("sigma",new Integer(_sigma));
NAME_TO_CODE_POINT_MAP.put("tau",new Integer(_tau));
NAME_TO_CODE_POINT_MAP.put("upsilon",new Integer(_upsilon));
NAME_TO_CODE_POINT_MAP.put("phi",new Integer(_phi));
NAME_TO_CODE_POINT_MAP.put("chi",new Integer(_chi));
NAME_TO_CODE_POINT_MAP.put("psi",new Integer(_psi));
NAME_TO_CODE_POINT_MAP.put("omega",new Integer(_omega));
NAME_TO_CODE_POINT_MAP.put("thetasym",new Integer(_thetasym));
NAME_TO_CODE_POINT_MAP.put("upsih",new Integer(_upsih));
NAME_TO_CODE_POINT_MAP.put("piv",new Integer(_piv));
NAME_TO_CODE_POINT_MAP.put("bull",new Integer(_bull));
NAME_TO_CODE_POINT_MAP.put("hellip",new Integer(_hellip));
NAME_TO_CODE_POINT_MAP.put("prime",new Integer(_prime));
NAME_TO_CODE_POINT_MAP.put("Prime",new Integer(_Prime));
NAME_TO_CODE_POINT_MAP.put("oline",new Integer(_oline));
NAME_TO_CODE_POINT_MAP.put("frasl",new Integer(_frasl));
NAME_TO_CODE_POINT_MAP.put("weierp",new Integer(_weierp));
NAME_TO_CODE_POINT_MAP.put("image",new Integer(_image));
NAME_TO_CODE_POINT_MAP.put("real",new Integer(_real));
NAME_TO_CODE_POINT_MAP.put("trade",new Integer(_trade));
NAME_TO_CODE_POINT_MAP.put("alefsym",new Integer(_alefsym));
NAME_TO_CODE_POINT_MAP.put("larr",new Integer(_larr));
NAME_TO_CODE_POINT_MAP.put("uarr",new Integer(_uarr));
NAME_TO_CODE_POINT_MAP.put("rarr",new Integer(_rarr));
NAME_TO_CODE_POINT_MAP.put("darr",new Integer(_darr));
NAME_TO_CODE_POINT_MAP.put("harr",new Integer(_harr));
NAME_TO_CODE_POINT_MAP.put("crarr",new Integer(_crarr));
NAME_TO_CODE_POINT_MAP.put("lArr",new Integer(_lArr));
NAME_TO_CODE_POINT_MAP.put("uArr",new Integer(_uArr));
NAME_TO_CODE_POINT_MAP.put("rArr",new Integer(_rArr));
NAME_TO_CODE_POINT_MAP.put("dArr",new Integer(_dArr));
NAME_TO_CODE_POINT_MAP.put("hArr",new Integer(_hArr));
NAME_TO_CODE_POINT_MAP.put("forall",new Integer(_forall));
NAME_TO_CODE_POINT_MAP.put("part",new Integer(_part));
NAME_TO_CODE_POINT_MAP.put("exist",new Integer(_exist));
NAME_TO_CODE_POINT_MAP.put("empty",new Integer(_empty));
NAME_TO_CODE_POINT_MAP.put("nabla",new Integer(_nabla));
NAME_TO_CODE_POINT_MAP.put("isin",new Integer(_isin));
NAME_TO_CODE_POINT_MAP.put("notin",new Integer(_notin));
NAME_TO_CODE_POINT_MAP.put("ni",new Integer(_ni));
NAME_TO_CODE_POINT_MAP.put("prod",new Integer(_prod));
NAME_TO_CODE_POINT_MAP.put("sum",new Integer(_sum));
NAME_TO_CODE_POINT_MAP.put("minus",new Integer(_minus));
NAME_TO_CODE_POINT_MAP.put("lowast",new Integer(_lowast));
NAME_TO_CODE_POINT_MAP.put("radic",new Integer(_radic));
NAME_TO_CODE_POINT_MAP.put("prop",new Integer(_prop));
NAME_TO_CODE_POINT_MAP.put("infin",new Integer(_infin));
NAME_TO_CODE_POINT_MAP.put("ang",new Integer(_ang));
NAME_TO_CODE_POINT_MAP.put("and",new Integer(_and));
NAME_TO_CODE_POINT_MAP.put("or",new Integer(_or));
NAME_TO_CODE_POINT_MAP.put("cap",new Integer(_cap));
NAME_TO_CODE_POINT_MAP.put("cup",new Integer(_cup));
NAME_TO_CODE_POINT_MAP.put("int",new Integer(_int));
NAME_TO_CODE_POINT_MAP.put("there4",new Integer(_there4));
NAME_TO_CODE_POINT_MAP.put("sim",new Integer(_sim));
NAME_TO_CODE_POINT_MAP.put("cong",new Integer(_cong));
NAME_TO_CODE_POINT_MAP.put("asymp",new Integer(_asymp));
NAME_TO_CODE_POINT_MAP.put("ne",new Integer(_ne));
NAME_TO_CODE_POINT_MAP.put("equiv",new Integer(_equiv));
NAME_TO_CODE_POINT_MAP.put("le",new Integer(_le));
NAME_TO_CODE_POINT_MAP.put("ge",new Integer(_ge));
NAME_TO_CODE_POINT_MAP.put("sub",new Integer(_sub));
NAME_TO_CODE_POINT_MAP.put("sup",new Integer(_sup));
NAME_TO_CODE_POINT_MAP.put("nsub",new Integer(_nsub));
NAME_TO_CODE_POINT_MAP.put("sube",new Integer(_sube));
NAME_TO_CODE_POINT_MAP.put("supe",new Integer(_supe));
NAME_TO_CODE_POINT_MAP.put("oplus",new Integer(_oplus));
NAME_TO_CODE_POINT_MAP.put("otimes",new Integer(_otimes));
NAME_TO_CODE_POINT_MAP.put("perp",new Integer(_perp));
NAME_TO_CODE_POINT_MAP.put("sdot",new Integer(_sdot));
NAME_TO_CODE_POINT_MAP.put("lceil",new Integer(_lceil));
NAME_TO_CODE_POINT_MAP.put("rceil",new Integer(_rceil));
NAME_TO_CODE_POINT_MAP.put("lfloor",new Integer(_lfloor));
NAME_TO_CODE_POINT_MAP.put("rfloor",new Integer(_rfloor));
NAME_TO_CODE_POINT_MAP.put("lang",new Integer(_lang));
NAME_TO_CODE_POINT_MAP.put("rang",new Integer(_rang));
NAME_TO_CODE_POINT_MAP.put("loz",new Integer(_loz));
NAME_TO_CODE_POINT_MAP.put("spades",new Integer(_spades));
NAME_TO_CODE_POINT_MAP.put("clubs",new Integer(_clubs));
NAME_TO_CODE_POINT_MAP.put("hearts",new Integer(_hearts));
NAME_TO_CODE_POINT_MAP.put("diams",new Integer(_diams));
NAME_TO_CODE_POINT_MAP.put("quot",new Integer(_quot));
NAME_TO_CODE_POINT_MAP.put("amp",new Integer(_amp));
NAME_TO_CODE_POINT_MAP.put("lt",new Integer(_lt));
NAME_TO_CODE_POINT_MAP.put("gt",new Integer(_gt));
NAME_TO_CODE_POINT_MAP.put("OElig",new Integer(_OElig));
NAME_TO_CODE_POINT_MAP.put("oelig",new Integer(_oelig));
NAME_TO_CODE_POINT_MAP.put("Scaron",new Integer(_Scaron));
NAME_TO_CODE_POINT_MAP.put("scaron",new Integer(_scaron));
NAME_TO_CODE_POINT_MAP.put("Yuml",new Integer(_Yuml));
NAME_TO_CODE_POINT_MAP.put("circ",new Integer(_circ));
NAME_TO_CODE_POINT_MAP.put("tilde",new Integer(_tilde));
NAME_TO_CODE_POINT_MAP.put("ensp",new Integer(_ensp));
NAME_TO_CODE_POINT_MAP.put("emsp",new Integer(_emsp));
NAME_TO_CODE_POINT_MAP.put("thinsp",new Integer(_thinsp));
NAME_TO_CODE_POINT_MAP.put("zwnj",new Integer(_zwnj));
NAME_TO_CODE_POINT_MAP.put("zwj",new Integer(_zwj));
NAME_TO_CODE_POINT_MAP.put("lrm",new Integer(_lrm));
NAME_TO_CODE_POINT_MAP.put("rlm",new Integer(_rlm));
NAME_TO_CODE_POINT_MAP.put("ndash",new Integer(_ndash));
NAME_TO_CODE_POINT_MAP.put("mdash",new Integer(_mdash));
NAME_TO_CODE_POINT_MAP.put("lsquo",new Integer(_lsquo));
NAME_TO_CODE_POINT_MAP.put("rsquo",new Integer(_rsquo));
NAME_TO_CODE_POINT_MAP.put("sbquo",new Integer(_sbquo));
NAME_TO_CODE_POINT_MAP.put("ldquo",new Integer(_ldquo));
NAME_TO_CODE_POINT_MAP.put("rdquo",new Integer(_rdquo));
NAME_TO_CODE_POINT_MAP.put("bdquo",new Integer(_bdquo));
NAME_TO_CODE_POINT_MAP.put("dagger",new Integer(_dagger));
NAME_TO_CODE_POINT_MAP.put("Dagger",new Integer(_Dagger));
NAME_TO_CODE_POINT_MAP.put("permil",new Integer(_permil));
NAME_TO_CODE_POINT_MAP.put("lsaquo",new Integer(_lsaquo));
NAME_TO_CODE_POINT_MAP.put("rsaquo",new Integer(_rsaquo));
NAME_TO_CODE_POINT_MAP.put("euro",new Integer(_euro));
NAME_TO_CODE_POINT_MAP.put("apos",new Integer(_apos));
CODE_POINT_TO_NAME_MAP=new IntStringHashMap(NAME_TO_CODE_POINT_MAP.size());
for (Iterator i=NAME_TO_CODE_POINT_MAP.entrySet().iterator(); i.hasNext();) {
Map.Entry entry=(Map.Entry)i.next();
String name=(String)entry.getKey();
if (MAX_NAME_LENGTH
*
* - Example:
* ((CharacterEntityReference)CharacterReference.parse(">")).getName() returns "gt"
* @return the name of this character entity reference.
* @see #getName(int codePoint)
*/
public String getName() {
return name;
}
/**
* Returns the character entity reference name of the specified character.
*
* Since all character entity references represent Unicode BMP code points,
* the functionality of this method is identical to that of {@link #getName(int codePoint)}.
*
*
* - Example:
* CharacterEntityReference.getName('>') returns "gt"
* @return the character entity reference name of the specified character, or null if none exists.
*/
public static String getName(char ch) {
return getName((int)ch);
}
/**
* Returns the character entity reference name of the specified Unicode code point.
*
* Since all character entity references represent Unicode BMP code points,
* the functionality of this method is identical to that of {@link #getName(char ch)}.
*
*
* - Example:
* CharacterEntityReference.getName(62) returns "gt"
* @return the character entity reference name of the specified Unicode code point, or null if none exists.
*/
public static String getName(int codePoint) {
return CODE_POINT_TO_NAME_MAP.get(codePoint);
}
/**
* Returns the Unicode code point of the specified character entity reference name.
*
* If the string does not represent a valid character entity reference name, this method returns {@link #INVALID_CODE_POINT INVALID_CODE_POINT}.
*
* Although character entity reference names are case sensitive, and in some cases differ from other entity references only by their case,
* some browsers will also recognise them in a case-insensitive way.
* For this reason, all decoding methods in this library will recognise character entity reference names even if they are in the wrong case.
*
*
* - Example:
* CharacterEntityReference.getCodePointFromName("gt") returns 62
* @return the Unicode code point of the specified character entity reference name, or {@link #INVALID_CODE_POINT INVALID_CODE_POINT} if the string does not represent a valid character entity reference name.
*/
public static int getCodePointFromName(String name) {
Integer codePoint=(Integer)NAME_TO_CODE_POINT_MAP.get(name);
if (codePoint==null) {
// Most browsers will recognise character entity references even if they have the wrong case, so check for this as well:
String lowerCaseName=name.toLowerCase();
if (lowerCaseName!=name) codePoint=(Integer)NAME_TO_CODE_POINT_MAP.get(lowerCaseName);
}
return (codePoint!=null) ? codePoint.intValue() : INVALID_CODE_POINT;
}
/**
* Returns the correct encoded form of this character entity reference.
*
* Note that the returned string is not necessarily the same as the original source text used to create this object.
* This library will recognise certain invalid forms of character references, as detailed in the {@link #decode(CharSequence) decode(String encodedString)} method.
*
* To retrieve the original source text, use the {@link #toString() toString()} method instead.
*
*
* - Example:
* CharacterReference.parse(">").getCharacterReferenceString() returns ">"
*
* @return the correct encoded form of this character entity reference.
* @see CharacterReference#getCharacterReferenceString(int codePoint)
*/
public String getCharacterReferenceString() {
return getCharacterReferenceString(name);
}
/**
* Returns the character entity reference encoded form of the specified Unicode code point.
*
* If the specified code point does not have an equivalent character entity reference, this method returns null.
* To get either the entity or numeric reference encoded form, use the {@link CharacterReference#getCharacterReferenceString(int codePoint)} method instead.
*
*
* - Examples:
* CharacterEntityReference.getCharacterReferenceString(62) returns ">"CharacterEntityReference.getCharacterReferenceString(9786) returns null
*
* @return the character entity reference encoded form of the specified Unicode code point, or null if none exists.
* @see CharacterReference#getCharacterReferenceString(int codePoint)
*/
public static String getCharacterReferenceString(int codePoint) {
if (codePoint>Character.MAX_VALUE) return null;
String name=getName(codePoint);
return name!=null ? getCharacterReferenceString(name) : null;
}
/**
* Returns a Map of character entity reference names (String) to code points (Integer).
* @return a Map of character entity reference names to code points.
**/
public static Map getNameToCodePointMap() {
return NAME_TO_CODE_POINT_MAP;
}
private static String getCharacterReferenceString(String name) {
return appendCharacterReferenceString(new StringBuffer(),name).toString();
}
protected static final StringBuffer appendCharacterReferenceString(StringBuffer sb, String name) {
return sb.append('&').append(name).append(';');
}
static CharacterReference construct(Source source, int begin) {
// only called from CharacterReference.construct(), so we can assume that first character is '&'
String name;
int nameBegin=begin+1;
int maxNameEnd=nameBegin+MAX_NAME_LENGTH;
int maxSourcePos=source.length()-1;
int end;
int x=nameBegin;
boolean invalidTermination=false;
while (true) {
char ch=source.charAt(x);
if (ch==';') {
end=x+1;
name=source.subSequence(nameBegin,x).toString();
break;
}
if (!isValidNameCharacter(ch)) {
// At this point, ch is determined to be an invalid character, meaning the source document is not valid HTML.
invalidTermination=true;
} else if (x==maxSourcePos) {
// At this point, we have a valid name character but are at the last position in the source text without the terminating semicolon.
// treat this the same as hitting an invalid name character.
invalidTermination=true;
x++; // include this character in the name
}
if (invalidTermination) {
// In this situation we are free to either reject the character entity reference outright, or try to resolve it anyway as some browsers do.
// IE will reject "uncommon" references in this situation (even if followed by whitespace), but accept "common" ones, even if they have no semicolon and are followed by more alphabetic characters. (eg "<a" resolves to "maxNameEnd) return null;
}
int codePoint=getCodePointFromName(name);
return (codePoint==INVALID_CODE_POINT) ? null : new CharacterEntityReference(source,begin,end,codePoint);
}
private static final boolean isValidNameCharacter(char ch) {
return ch>='A' && ch<='z' && (ch<='Z' || ch>='a');
}
public String getDebugInfo() {
StringBuffer sb=new StringBuffer();
sb.append('"');
appendCharacterReferenceString(sb,name);
sb.append("\" ");
appendUnicodeText(sb,codePoint);
sb.append(' ').append(super.getDebugInfo());
return sb.toString();
}
}