private static HashMap unicodeMappings = new HashMap();

    private static Map unicodeMappings = new HashMap();

    /**

     *  Return the Map file of HTML escape to unicode mappings.

     *  Currently protected as only the test cases needs access.

     *

     *@return  The map where the key is the html and value is the Unicode.

     */

    protected static Map getUnicodeMappings(){

	    return unicodeMappings;

	}

     *  unicode version of it.

     *  unicode version of it.  It seems like CASE matters, for instance there are as HTML

     *  escapes both ← and ⇐, which are different.  Not sure if we want to deal

     *  with those or not...

            if ( s.toLowerCase().indexOf( key ) != -1 )

            if ( s.indexOf( key ) != -1 )

        unicodeMappings.put( "α",   "\u03B1" );

        // Portions © International Organization for Standardization 1986

        unicodeMappings.put( "β",    "\u03B2" );

        // Permission to copy in any form is granted for use with

        unicodeMappings.put( "γ",   "\u03B3" );

        // conforming SGML systems and applications as defined in

        unicodeMappings.put( "δ",   "\u03B4" );

        // ISO 8879, provided this notice is included in all copies.

        unicodeMappings.put( "ε", "\u03B5" );

        // Character entity set. Typical invocation:

        unicodeMappings.put( "ζ",    "\u03B6" );

        // <!ENTITY % HTMLlat1 PUBLIC

        unicodeMappings.put( "η",     "\u03B7" );

        // "-//W3C//ENTITIES Latin 1//EN//HTML">

        unicodeMappings.put( "θ",   "\u03B8" );

        // %HTMLlat1;

        unicodeMappings.put( "ι",    "\u03B9" );

        unicodeMappings.put (" ",     "\u00a0"); // no-break space = non-breaking space, U+00A0 ISOnum

        unicodeMappings.put( "κ",   "\u03BA" );

        unicodeMappings.put ("¡",    "\u00a1"); // inverted exclamation mark, U+00A1 ISOnum

        unicodeMappings.put( "λ",  "\u03BB" );

        unicodeMappings.put ("¢",     "\u00a2"); // cent sign, U+00A2 ISOnum

        unicodeMappings.put( "μ",      "\u03BC" );

        unicodeMappings.put ("£",    "\u00a3"); // pound sign, U+00A3 ISOnum

        unicodeMappings.put( "ν",      "\u03BD" );

        unicodeMappings.put ("¤",   "\u00a4"); // currency sign, U+00A4 ISOnum

        unicodeMappings.put( "ξ",      "\u03BE" );

        unicodeMappings.put ("¥",      "\u00a5"); // yen sign = yuan sign, U+00A5 ISOnum

        unicodeMappings.put( "ο", "\u03BF" );

        unicodeMappings.put ("¦",   "\u00a6"); // broken bar = broken vertical bar, U+00A6 ISOnum

        unicodeMappings.put ("§",     "\u00a7"); // section sign, U+00A7 ISOnum

        unicodeMappings.put ("¨",      "\u00a8"); // diaeresis = spacing diaeresis, U+00A8 ISOdia

        unicodeMappings.put ("©",     "\u00a9"); // copyright sign, U+00A9 ISOnum

        unicodeMappings.put ("ª",     "\u00aa"); // feminine ordinal indicator, U+00AA ISOnum

        unicodeMappings.put ("«",    "\u00ab"); // left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum

        unicodeMappings.put ("¬",      "\u00ac"); // not sign, U+00AC ISOnum

        unicodeMappings.put ("­",      "\u00ad"); // soft hyphen = discretionary hyphen, U+00AD ISOnum

        unicodeMappings.put ("®",      "\u00ae"); // registered sign = registered trade mark sign, U+00AE ISOnum

        unicodeMappings.put ("¯",     "\u00af"); // macron = spacing macron = overline = APL overbar, U+00AF ISOdia

        unicodeMappings.put ("°",      "\u00b0"); // degree sign, U+00B0 ISOnum

        unicodeMappings.put ("±",   "\u00b1"); // plus-minus sign = plus-or-minus sign, U+00B1 ISOnum

        unicodeMappings.put ("²",     "\u00b2"); // superscript two = superscript digit two = squared, U+00B2 ISOnum

        unicodeMappings.put ("³",     "\u00b3"); // superscript three = superscript digit three = cubed, U+00B3 ISOnum

        unicodeMappings.put ("´",    "\u00b4"); // acute accent = spacing acute, U+00B4 ISOdia

        unicodeMappings.put ("µ",    "\u00b5"); // micro sign, U+00B5 ISOnum

        unicodeMappings.put ("¶",     "\u00b6"); // pilcrow sign = paragraph sign, U+00B6 ISOnum

        unicodeMappings.put ("·",   "\u00b7"); // middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum

        unicodeMappings.put ("¸",    "\u00b8"); // cedilla = spacing cedilla, U+00B8 ISOdia

        unicodeMappings.put ("¹",     "\u00b9"); // superscript one = superscript digit one, U+00B9 ISOnum

        unicodeMappings.put ("º",     "\u00ba"); // masculine ordinal indicator, U+00BA ISOnum

        unicodeMappings.put ("»",    "\u00bb"); // right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum

        unicodeMappings.put ("¼",   "\u00bc"); // vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum

        unicodeMappings.put ("½",   "\u00bd"); // vulgar fraction one half = fraction one half, U+00BD ISOnum

        unicodeMappings.put ("¾",   "\u00be"); // vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum

        unicodeMappings.put ("¿",   "\u00bf"); // inverted question mark = turned question mark, U+00BF ISOnum

        unicodeMappings.put ("À",   "\u00c0"); // latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1

        unicodeMappings.put ("Á",   "\u00c1"); // latin capital letter A with acute, U+00C1 ISOlat1

        unicodeMappings.put ("Â",    "\u00c2"); // latin capital letter A with circumflex, U+00C2 ISOlat1

        unicodeMappings.put ("Ã",   "\u00c3"); // latin capital letter A with tilde, U+00C3 ISOlat1

        unicodeMappings.put ("Ä",     "\u00c4"); // latin capital letter A with diaeresis, U+00C4 ISOlat1

        unicodeMappings.put ("Å",    "\u00c5"); // latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1

        unicodeMappings.put ("Æ",    "\u00c6"); // latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1

        unicodeMappings.put ("Ç",   "\u00c7"); // latin capital letter C with cedilla, U+00C7 ISOlat1

        unicodeMappings.put ("È",   "\u00c8"); // latin capital letter E with grave, U+00C8 ISOlat1

        unicodeMappings.put ("É",   "\u00c9"); // latin capital letter E with acute, U+00C9 ISOlat1

        unicodeMappings.put ("Ê",    "\u00ca"); // latin capital letter E with circumflex, U+00CA ISOlat1

        unicodeMappings.put ("Ë",     "\u00cb"); // latin capital letter E with diaeresis, U+00CB ISOlat1

        unicodeMappings.put ("Ì",   "\u00cc"); // latin capital letter I with grave, U+00CC ISOlat1

        unicodeMappings.put ("Í",   "\u00cd"); // latin capital letter I with acute, U+00CD ISOlat1

        unicodeMappings.put ("Î",    "\u00ce"); // latin capital letter I with circumflex, U+00CE ISOlat1

        unicodeMappings.put ("Ï",     "\u00cf"); // latin capital letter I with diaeresis, U+00CF ISOlat1

        unicodeMappings.put ("Ð",      "\u00d0"); // latin capital letter ETH, U+00D0 ISOlat1

        unicodeMappings.put ("Ñ",   "\u00d1"); // latin capital letter N with tilde, U+00D1 ISOlat1

        unicodeMappings.put ("Ò",   "\u00d2"); // latin capital letter O with grave, U+00D2 ISOlat1

        unicodeMappings.put ("Ó",   "\u00d3"); // latin capital letter O with acute, U+00D3 ISOlat1

        unicodeMappings.put ("Ô",    "\u00d4"); // latin capital letter O with circumflex, U+00D4 ISOlat1

        unicodeMappings.put ("Õ",   "\u00d5"); // latin capital letter O with tilde, U+00D5 ISOlat1

        unicodeMappings.put ("Ö",     "\u00d6"); // latin capital letter O with diaeresis, U+00D6 ISOlat1

        unicodeMappings.put ("×",    "\u00d7"); // multiplication sign, U+00D7 ISOnum

        unicodeMappings.put ("Ø",   "\u00d8"); // latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1

        unicodeMappings.put ("Ù",   "\u00d9"); // latin capital letter U with grave, U+00D9 ISOlat1

        unicodeMappings.put ("Ú",   "\u00da"); // latin capital letter U with acute, U+00DA ISOlat1

        unicodeMappings.put ("Û",    "\u00db"); // latin capital letter U with circumflex, U+00DB ISOlat1

        unicodeMappings.put ("Ü",     "\u00dc"); // latin capital letter U with diaeresis, U+00DC ISOlat1

        unicodeMappings.put ("Ý",   "\u00dd"); // latin capital letter Y with acute, U+00DD ISOlat1

        unicodeMappings.put ("Þ",    "\u00de"); // latin capital letter THORN, U+00DE ISOlat1

        unicodeMappings.put ("ß",    "\u00df"); // latin small letter sharp s = ess-zed, U+00DF ISOlat1

        unicodeMappings.put ("à",   "\u00e0"); // latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1

        unicodeMappings.put ("á",   "\u00e1"); // latin small letter a with acute, U+00E1 ISOlat1

        unicodeMappings.put ("â",    "\u00e2"); // latin small letter a with circumflex, U+00E2 ISOlat1

        unicodeMappings.put ("ã",   "\u00e3"); // latin small letter a with tilde, U+00E3 ISOlat1

        unicodeMappings.put ("ä",     "\u00e4"); // latin small letter a with diaeresis, U+00E4 ISOlat1

        unicodeMappings.put ("å",    "\u00e5"); // latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1

        unicodeMappings.put ("æ",    "\u00e6"); // latin small letter ae = latin small ligature ae, U+00E6 ISOlat1

        unicodeMappings.put ("ç",   "\u00e7"); // latin small letter c with cedilla, U+00E7 ISOlat1

        unicodeMappings.put ("è",   "\u00e8"); // latin small letter e with grave, U+00E8 ISOlat1

        unicodeMappings.put ("é",   "\u00e9"); // latin small letter e with acute, U+00E9 ISOlat1

        unicodeMappings.put ("ê",    "\u00ea"); // latin small letter e with circumflex, U+00EA ISOlat1

        unicodeMappings.put ("ë",     "\u00eb"); // latin small letter e with diaeresis, U+00EB ISOlat1

        unicodeMappings.put ("ì",   "\u00ec"); // latin small letter i with grave, U+00EC ISOlat1

        unicodeMappings.put ("í",   "\u00ed"); // latin small letter i with acute, U+00ED ISOlat1

        unicodeMappings.put ("î",    "\u00ee"); // latin small letter i with circumflex, U+00EE ISOlat1

        unicodeMappings.put ("ï",     "\u00ef"); // latin small letter i with diaeresis, U+00EF ISOlat1

        unicodeMappings.put ("ð",      "\u00f0"); // latin small letter eth, U+00F0 ISOlat1

        unicodeMappings.put ("ñ",   "\u00f1"); // latin small letter n with tilde, U+00F1 ISOlat1

        unicodeMappings.put ("ò",   "\u00f2"); // latin small letter o with grave, U+00F2 ISOlat1

        unicodeMappings.put ("ó",   "\u00f3"); // latin small letter o with acute, U+00F3 ISOlat1

        unicodeMappings.put ("ô",    "\u00f4"); // latin small letter o with circumflex, U+00F4 ISOlat1

        unicodeMappings.put ("õ",   "\u00f5"); // latin small letter o with tilde, U+00F5 ISOlat1

        unicodeMappings.put ("ö",     "\u00f6"); // latin small letter o with diaeresis, U+00F6 ISOlat1

        unicodeMappings.put ("÷",   "\u00f7"); // division sign, U+00F7 ISOnum

        unicodeMappings.put ("ø",   "\u00f8"); // latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1

        unicodeMappings.put ("ù",   "\u00f9"); // latin small letter u with grave, U+00F9 ISOlat1

        unicodeMappings.put ("ú",   "\u00fa"); // latin small letter u with acute, U+00FA ISOlat1

        unicodeMappings.put ("û",    "\u00fb"); // latin small letter u with circumflex, U+00FB ISOlat1

        unicodeMappings.put ("ü",     "\u00fc"); // latin small letter u with diaeresis, U+00FC ISOlat1

        unicodeMappings.put ("ý",   "\u00fd"); // latin small letter y with acute, U+00FD ISOlat1

        unicodeMappings.put ("þ",    "\u00fe"); // latin small letter thorn, U+00FE ISOlat1

        unicodeMappings.put ("ÿ",     "\u00ff"); // latin small letter y with diaeresis, U+00FF ISOlat1

        // Mathematical, Greek and Symbolic characters for HTML

        // Character entity set. Typical invocation:

        // <!ENTITY % HTMLsymbol PUBLIC

        // "-//W3C//ENTITIES Symbols//EN//HTML">

        // %HTMLsymbol;

        // Portions © International Organization for Standardization 1986:

        // Permission to copy in any form is granted for use with

        // conforming SGML systems and applications as defined in

        // ISO 8879, provided this notice is included in all copies.

        // Relevant ISO entity set is given unless names are newly introduced.

        // New names (i.e., not in ISO 8879 list) do not clash with any

        // existing ISO 8879 entity names. ISO 10646 character numbers

        // are given for each character, in hex. CDATA values are decimal

        // conversions of the ISO 10646 values and refer to the document

        // character set. Names are ISO 10646 names.

        // Latin Extended-B

        unicodeMappings.put ("ƒ",     "\u0192"); // latin small f with hook = function = florin, U+0192 ISOtech

        // Greek

        unicodeMappings.put ("Α",    "\u0391"); // greek capital letter alpha, U+0391

        unicodeMappings.put ("Β",     "\u0392"); // greek capital letter beta, U+0392

        unicodeMappings.put ("Γ",    "\u0393"); // greek capital letter gamma, U+0393 ISOgrk3

        unicodeMappings.put ("Δ",    "\u0394"); // greek capital letter delta, U+0394 ISOgrk3

        unicodeMappings.put ("Ε",  "\u0395"); // greek capital letter epsilon, U+0395

        unicodeMappings.put ("Ζ",     "\u0396"); // greek capital letter zeta, U+0396

        unicodeMappings.put ("Η",      "\u0397"); // greek capital letter eta, U+0397

        unicodeMappings.put ("Θ",    "\u0398"); // greek capital letter theta, U+0398 ISOgrk3

        unicodeMappings.put ("Ι",     "\u0399"); // greek capital letter iota, U+0399

        unicodeMappings.put ("Κ",    "\u039a"); // greek capital letter kappa, U+039A

        unicodeMappings.put ("Λ",   "\u039b"); // greek capital letter lambda, U+039B ISOgrk3

        unicodeMappings.put ("Μ",       "\u039c"); // greek capital letter mu, U+039C

        unicodeMappings.put ("Ν",       "\u039d"); // greek capital letter nu, U+039D

        unicodeMappings.put ("Ξ",       "\u039e"); // greek capital letter xi, U+039E ISOgrk3

        unicodeMappings.put ("Ο",  "\u039f"); // greek capital letter omicron, U+039F

        unicodeMappings.put ("Π",       "\u03a0"); // greek capital letter pi, U+03A0 ISOgrk3

        unicodeMappings.put ("Ρ",      "\u03a1"); // greek capital letter rho, U+03A1

        // there is no Sigmaf, and no U+03A2 character either

        unicodeMappings.put ("Σ",    "\u03a3"); // greek capital letter sigma, U+03A3 ISOgrk3

        unicodeMappings.put ("Τ",      "\u03a4"); // greek capital letter tau, U+03A4

        unicodeMappings.put ("Υ",  "\u03a5"); // greek capital letter upsilon, U+03A5 ISOgrk3

        unicodeMappings.put ("Φ",      "\u03a6"); // greek capital letter phi, U+03A6 ISOgrk3

        unicodeMappings.put ("Χ",      "\u03a7"); // greek capital letter chi, U+03A7

        unicodeMappings.put ("Ψ",      "\u03a8"); // greek capital letter psi, U+03A8 ISOgrk3

        unicodeMappings.put ("Ω",    "\u03a9"); // greek capital letter omega, U+03A9 ISOgrk3

        unicodeMappings.put ("α",    "\u03b1"); // greek small letter alpha, U+03B1 ISOgrk3

        unicodeMappings.put ("β",     "\u03b2"); // greek small letter beta, U+03B2 ISOgrk3

        unicodeMappings.put ("γ",    "\u03b3"); // greek small letter gamma, U+03B3 ISOgrk3

        unicodeMappings.put ("δ",    "\u03b4"); // greek small letter delta, U+03B4 ISOgrk3

        unicodeMappings.put ("ε",  "\u03b5"); // greek small letter epsilon, U+03B5 ISOgrk3

        unicodeMappings.put ("ζ",     "\u03b6"); // greek small letter zeta, U+03B6 ISOgrk3

        unicodeMappings.put ("η",      "\u03b7"); // greek small letter eta, U+03B7 ISOgrk3

        unicodeMappings.put ("θ",    "\u03b8"); // greek small letter theta, U+03B8 ISOgrk3

        unicodeMappings.put ("ι",     "\u03b9"); // greek small letter iota, U+03B9 ISOgrk3

        unicodeMappings.put ("κ",    "\u03ba"); // greek small letter kappa, U+03BA ISOgrk3

        unicodeMappings.put ("λ",   "\u03bb"); // greek small letter lambda, U+03BB ISOgrk3

        unicodeMappings.put ("μ",       "\u03bc"); // greek small letter mu, U+03BC ISOgrk3

        unicodeMappings.put ("ν",       "\u03bd"); // greek small letter nu, U+03BD ISOgrk3

        unicodeMappings.put ("ξ",       "\u03be"); // greek small letter xi, U+03BE ISOgrk3

        unicodeMappings.put ("ο",  "\u03bf"); // greek small letter omicron, U+03BF NEW

        unicodeMappings.put ("π",       "\u03c0"); // greek small letter pi, U+03C0 ISOgrk3

        unicodeMappings.put ("ρ",      "\u03c1"); // greek small letter rho, U+03C1 ISOgrk3

        unicodeMappings.put ("ς",   "\u03c2"); // greek small letter final sigma, U+03C2 ISOgrk3

        unicodeMappings.put ("σ",    "\u03c3"); // greek small letter sigma, U+03C3 ISOgrk3

        unicodeMappings.put ("τ",      "\u03c4"); // greek small letter tau, U+03C4 ISOgrk3

        unicodeMappings.put ("υ",  "\u03c5"); // greek small letter upsilon, U+03C5 ISOgrk3

        unicodeMappings.put ("φ",      "\u03c6"); // greek small letter phi, U+03C6 ISOgrk3

        unicodeMappings.put ("χ",      "\u03c7"); // greek small letter chi, U+03C7 ISOgrk3

        unicodeMappings.put ("ψ",      "\u03c8"); // greek small letter psi, U+03C8 ISOgrk3

        unicodeMappings.put ("ω",    "\u03c9"); // greek small letter omega, U+03C9 ISOgrk3

        unicodeMappings.put ("ϑ", "\u03d1"); // greek small letter theta symbol, U+03D1 NEW

        unicodeMappings.put ("ϒ",    "\u03d2"); // greek upsilon with hook symbol, U+03D2 NEW

        unicodeMappings.put ("ϖ",      "\u03d6"); // greek pi symbol, U+03D6 ISOgrk3

        // General Punctuation

        unicodeMappings.put ("•",     "\u2022"); // bullet = black small circle, U+2022 ISOpub

        // bullet is NOT the same as bullet operator, U+2219

        unicodeMappings.put ("…",   "\u2026"); // horizontal ellipsis = three dot leader, U+2026 ISOpub

        unicodeMappings.put ("′",    "\u2032"); // prime = minutes = feet, U+2032 ISOtech

        unicodeMappings.put ("″",    "\u2033"); // double prime = seconds = inches, U+2033 ISOtech

        unicodeMappings.put ("‾",    "\u203e"); // overline = spacing overscore, U+203E NEW

        unicodeMappings.put ("⁄",    "\u2044"); // fraction slash, U+2044 NEW

        // Letterlike Symbols

        unicodeMappings.put ("℘",   "\u2118"); // script capital P = power set = Weierstrass p, U+2118 ISOamso

        unicodeMappings.put ("ℑ",    "\u2111"); // blackletter capital I = imaginary part, U+2111 ISOamso

        unicodeMappings.put ("ℜ",     "\u211c"); // blackletter capital R = real part symbol, U+211C ISOamso

        unicodeMappings.put ("™",    "\u2122"); // trade mark sign, U+2122 ISOnum

        unicodeMappings.put ("ℵ",  "\u2135"); // alef symbol = first transfinite cardinal, U+2135 NEW

        // alef symbol is NOT the same as hebrew letter alef,

        // U+05D0 although the same glyph could be used to depict both characters

        // Arrows

        unicodeMappings.put ("←",     "\u2190"); // leftwards arrow, U+2190 ISOnum

        unicodeMappings.put ("↑",     "\u2191"); // upwards arrow, U+2191 ISOnum

        unicodeMappings.put ("→",     "\u2192"); // rightwards arrow, U+2192 ISOnum

        unicodeMappings.put ("↓",     "\u2193"); // downwards arrow, U+2193 ISOnum

        unicodeMappings.put ("↔",     "\u2194"); // left right arrow, U+2194 ISOamsa

        unicodeMappings.put ("↵",    "\u21b5"); // downwards arrow with corner leftwards = carriage return, U+21B5 NEW

        unicodeMappings.put ("⇐",     "\u21d0"); // leftwards double arrow, U+21D0 ISOtech

        // 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

        unicodeMappings.put ("⇑",     "\u21d1"); // upwards double arrow, U+21D1 ISOamsa

        unicodeMappings.put ("⇒",     "\u21d2"); // rightwards double arrow, U+21D2 ISOtech

        // 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

        unicodeMappings.put ("⇓",     "\u21d3"); // downwards double arrow, U+21D3 ISOamsa

        unicodeMappings.put ("⇔",     "\u21d4"); // left right double arrow, U+21D4 ISOamsa

        // Mathematical Operators

        unicodeMappings.put ("∀",   "\u2200"); // for all, U+2200 ISOtech

        unicodeMappings.put ("∂",     "\u2202"); // partial differential, U+2202 ISOtech

        unicodeMappings.put ("∃",    "\u2203"); // there exists, U+2203 ISOtech

        unicodeMappings.put ("∅",    "\u2205"); // empty set = null set = diameter, U+2205 ISOamso

        unicodeMappings.put ("∇",    "\u2207"); // nabla = backward difference, U+2207 ISOtech

        unicodeMappings.put ("∈",     "\u2208"); // element of, U+2208 ISOtech

        unicodeMappings.put ("∉",    "\u2209"); // not an element of, U+2209 ISOtech

        unicodeMappings.put ("∋",       "\u220b"); // contains as member, U+220B ISOtech

        // should there be a more memorable name than 'ni'?

        unicodeMappings.put ("∏",     "\u220f"); // n-ary product = product sign, U+220F ISOamsb

        // prod is NOT the same character as U+03A0 'greek capital letter pi' though

        // the same glyph might be used for both

        unicodeMappings.put ("∑",      "\u2211"); // n-ary sumation, U+2211 ISOamsb

        // sum is NOT the same character as U+03A3 'greek capital letter sigma'

        // though the same glyph might be used for both

        unicodeMappings.put ("−",    "\u2212"); // minus sign, U+2212 ISOtech

        unicodeMappings.put ("∗",   "\u2217"); // asterisk operator, U+2217 ISOtech

        unicodeMappings.put ("√",    "\u221a"); // square root = radical sign, U+221A ISOtech

        unicodeMappings.put ("∝",     "\u221d"); // proportional to, U+221D ISOtech

        unicodeMappings.put ("∞",    "\u221e"); // infinity, U+221E ISOtech

        unicodeMappings.put ("∠",      "\u2220"); // angle, U+2220 ISOamso

        unicodeMappings.put ("∧",      "\u2227"); // logical and = wedge, U+2227 ISOtech

        unicodeMappings.put ("∨",       "\u2228"); // logical or = vee, U+2228 ISOtech

        unicodeMappings.put ("∩",      "\u2229"); // intersection = cap, U+2229 ISOtech

        unicodeMappings.put ("∪",      "\u222a"); // union = cup, U+222A ISOtech

        unicodeMappings.put ("∫",      "\u222b"); // integral, U+222B ISOtech

        unicodeMappings.put ("∴",   "\u2234"); // therefore, U+2234 ISOtech

        unicodeMappings.put ("∼",      "\u223c"); // tilde operator = varies with = similar to, U+223C ISOtech

        // tilde operator is NOT the same character as the tilde, U+007E,

        // although the same glyph might be used to represent both

        unicodeMappings.put ("≅",     "\u2245"); // approximately equal to, U+2245 ISOtech

        unicodeMappings.put ("≈",    "\u2248"); // almost equal to = asymptotic to, U+2248 ISOamsr

        unicodeMappings.put ("≠",       "\u2260"); // not equal to, U+2260 ISOtech

        unicodeMappings.put ("≡",    "\u2261"); // identical to, U+2261 ISOtech

        unicodeMappings.put ("≤",       "\u2264"); // less-than or equal to, U+2264 ISOtech

        unicodeMappings.put ("≥",       "\u2265"); // greater-than or equal to, U+2265 ISOtech

        unicodeMappings.put ("⊂",      "\u2282"); // subset of, U+2282 ISOtech

        unicodeMappings.put ("⊃",      "\u2283"); // superset of, U+2283 ISOtech

        // 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

        unicodeMappings.put ("⊄",     "\u2284"); // not a subset of, U+2284 ISOamsn

        unicodeMappings.put ("⊆",     "\u2286"); // subset of or equal to, U+2286 ISOtech

        unicodeMappings.put ("⊇",     "\u2287"); // superset of or equal to, U+2287 ISOtech

        unicodeMappings.put ("⊕",    "\u2295"); // circled plus = direct sum, U+2295 ISOamsb

        unicodeMappings.put ("⊗",   "\u2297"); // circled times = vector product, U+2297 ISOamsb

        unicodeMappings.put ("⊥",     "\u22a5"); // up tack = orthogonal to = perpendicular, U+22A5 ISOtech

        unicodeMappings.put ("⋅",     "\u22c5"); // dot operator, U+22C5 ISOamsb

        // dot operator is NOT the same character as U+00B7 middle dot

        // Miscellaneous Technical

        unicodeMappings.put ("⌈",    "\u2308"); // left ceiling = apl upstile, U+2308 ISOamsc

        unicodeMappings.put ("⌉",    "\u2309"); // right ceiling, U+2309 ISOamsc

        unicodeMappings.put ("⌊",   "\u230a"); // left floor = apl downstile, U+230A ISOamsc

        unicodeMappings.put ("⌋",   "\u230b"); // right floor, U+230B ISOamsc

        unicodeMappings.put ("⟨",     "\u2329"); // left-pointing angle bracket = bra, U+2329 ISOtech

        // lang is NOT the same character as U+003C 'less than'

        // or U+2039 'single left-pointing angle quotation mark'

        unicodeMappings.put ("⟩",     "\u232a"); // right-pointing angle bracket = ket, U+232A ISOtech

        // rang is NOT the same character as U+003E 'greater than'

        // or U+203A 'single right-pointing angle quotation mark'

        // Geometric Shapes

        unicodeMappings.put ("◊",      "\u25ca"); // lozenge, U+25CA ISOpub

        // Miscellaneous Symbols

        unicodeMappings.put ("♠",   "\u2660"); // black spade suit, U+2660 ISOpub

        // black here seems to mean filled as opposed to hollow

        unicodeMappings.put ("♣",    "\u2663"); // black club suit = shamrock, U+2663 ISOpub

        unicodeMappings.put ("♥",   "\u2665"); // black heart suit = valentine, U+2665 ISOpub

        unicodeMappings.put ("♦",    "\u2666"); // black diamond suit, U+2666 ISOpub

        // Special characters for HTML

        // Character entity set. Typical invocation:

        // <!ENTITY % HTMLspecial PUBLIC

        // "-//W3C//ENTITIES Special//EN//HTML">

        // %HTMLspecial;

        // Portions © International Organization for Standardization 1986:

        // Permission to copy in any form is granted for use with

        // conforming SGML systems and applications as defined in

        // ISO 8879, provided this notice is included in all copies.

        // Relevant ISO entity set is given unless names are newly introduced.

        // New names (i.e., not in ISO 8879 list) do not clash with any

        // existing ISO 8879 entity names. ISO 10646 character numbers

        // are given for each character, in hex. CDATA values are decimal

        // conversions of the ISO 10646 values and refer to the document

        // character set. Names are ISO 10646 names.

        // C0 Controls and Basic Latin

		// epugh  This is a werid one..  If I list it as \u0022, then it doesn't complile, because I think it is a double quote!

        unicodeMappings.put (""",     "\""); // quotation mark = APL quote, U+0022 ISOnum

        unicodeMappings.put ("&",      "\u0026"); // ampersand, U+0026 ISOnum

        unicodeMappings.put ("<",       "\u003c"); // less-than sign, U+003C ISOnum

        unicodeMappings.put (">",       "\u003e"); // greater-than sign, U+003E ISOnum

        // Latin Extended-A

        unicodeMappings.put ("Œ",    "\u0152"); // latin capital ligature OE, U+0152 ISOlat2

        unicodeMappings.put ("œ",    "\u0153"); // latin small ligature oe, U+0153 ISOlat2

        // ligature is a misnomer, this is a separate character in some languages

        unicodeMappings.put ("Š",   "\u0160"); // latin capital letter S with caron, U+0160 ISOlat2

        unicodeMappings.put ("š",   "\u0161"); // latin small letter s with caron, U+0161 ISOlat2

        unicodeMappings.put ("Ÿ",     "\u0178"); // latin capital letter Y with diaeresis, U+0178 ISOlat2

        // Spacing Modifier Letters

        unicodeMappings.put ("ˆ",     "\u02c6"); // modifier letter circumflex accent, U+02C6 ISOpub

        unicodeMappings.put ("˜",    "\u02dc"); // small tilde, U+02DC ISOdia

        // General Punctuation

        unicodeMappings.put (" ",     "\u2002"); // en space, U+2002 ISOpub

        unicodeMappings.put (" ",     "\u2003"); // em space, U+2003 ISOpub

        unicodeMappings.put (" ",   "\u2009"); // thin space, U+2009 ISOpub

        unicodeMappings.put ("‌",     "\u200c"); // zero width non-joiner, U+200C NEW RFC 2070

        unicodeMappings.put ("‍",      "\u200d"); // zero width joiner, U+200D NEW RFC 2070

        unicodeMappings.put ("‎",      "\u200e"); // left-to-right mark, U+200E NEW RFC 2070

        unicodeMappings.put ("‏",      "\u200f"); // right-to-left mark, U+200F NEW RFC 2070

        unicodeMappings.put ("–",    "\u2013"); // en dash, U+2013 ISOpub

        unicodeMappings.put ("—",    "\u2014"); // em dash, U+2014 ISOpub

        unicodeMappings.put ("‘",    "\u2018"); // left single quotation mark, U+2018 ISOnum

        unicodeMappings.put ("’",    "\u2019"); // right single quotation mark, U+2019 ISOnum

        unicodeMappings.put ("‚",    "\u201a"); // single low-9 quotation mark, U+201A NEW

        unicodeMappings.put ("“",    "\u201c"); // left double quotation mark, U+201C ISOnum

        unicodeMappings.put ("”",    "\u201d"); // right double quotation mark, U+201D ISOnum

        unicodeMappings.put ("„",    "\u201e"); // double low-9 quotation mark, U+201E NEW

        unicodeMappings.put ("†",   "\u2020"); // dagger, U+2020 ISOpub

        unicodeMappings.put ("‡",   "\u2021"); // double dagger, U+2021 ISOpub

        unicodeMappings.put ("‰",   "\u2030"); // per mille sign, U+2030 ISOtech

        unicodeMappings.put ("‹",   "\u2039"); // single left-pointing angle quotation mark, U+2039 ISO proposed

        // lsaquo is proposed but not yet ISO standardized

        unicodeMappings.put ("›",   "\u203a"); // single right-pointing angle quotation mark, U+203A ISO proposed

        // rsaquo is proposed but not yet ISO standardized

        unicodeMappings.put ("€",     "\u20ac"); // euro sign, U+20AC NEW