davidsatz wrote:
> I need an easy way to transform the html entities into
the real chars instead
here's the dirty work. you'll need to find the entities via
regex, strip out the
"&" and ";" bits, take what's left & look up in the
entityMap & finally
replace w/the unicode code point that's returned.
<cfscript>
function createEntityMap() {
/*
author paul hastings
date 22-aug-2006
note maps HTML entities to unicode code points
HTML entity data derived from Roedy Green's entities.java
found at
http://mindprod.com/products1.html#ENTITIES
*/
var entities=structNew();
entities["le"]=8804;
entities["Yacute"]=253;
entities["cup"]=8746;
entities["sim"]=8764;
entities["real"]=8476;
entities["sub"]=8834;
entities["gt"]=62;
entities["lfloor"]=8970;
entities["ordf"]=170;
entities["sup"]=8835;
entities["otimes"]=8855;
entities["Ouml"]=246;
entities["sube"]=8838;
entities["Sigma"]=963;
entities["reg"]=174;
entities["Beta"]=946;
entities["oplus"]=8853;
entities["Pi"]=960;
entities["ETH"]=240;
entities["rfloor"]=8971;
entities["shy"]=173;
entities["Oslash"]=248;
entities["Otilde"]=245;
entities["ang"]=8736;
entities["trade"]=8482;
entities["fnof"]=402;
entities["Chi"]=967;
entities["upsih"]=978;
entities["frac12"]=189;
entities["rlm"]=8207;
entities["Eacute"]=233;
entities["permil"]=8240;
entities["hearts"]=9829;
entities["Icirc"]=238;
entities["cent"]=162;
entities["AElig"]=230;
entities["Psi"]=968;
entities["sum"]=8721;
entities["divide"]=247;
entities["iquest"]=191;
entities["Ecirc"]=234;
entities["ensp"]=8194;
entities["empty"]=8709;
entities["forall"]=8704;
entities["emsp"]=8195;
entities["Gamma"]=947;
entities["lceil"]=8968;
entities["dagger"]=8225;
entities["not"]=172;
entities["equiv"]=8801;
entities["Acirc"]=226;
entities["Agrave"]=224;
entities["Eta"]=951;
entities["alefsym"]=8501;
entities["ordm"]=186;
entities["piv"]=982;
entities["bdquo"]=8222;
entities["Delta"]=948;
entities["or"]=8744;
entities["acute"]=180;
entities["deg"]=176;
entities["cong"]=8773;
entities["Ntilde"]=241;
entities["lsaquo"]=8249;
entities["clubs"]=9827;
entities["hellip"]=8230;
entities["Ograve"]=242;
entities["Iuml"]=239;
entities["diams"]=9830;
entities["cedil"]=184;
entities["amp"]=38;
entities["Alpha"]=945;
entities["Egrave"]=232;
entities["darr"]=8659;
entities["and"]=8743;
entities["nsub"]=8836;
entities["ne"]=8800;
entities["Epsilon"]=949;
entities["isin"]=8712;
entities["Ccedil"]=231;
entities["lsquo"]=8216;
entities["copy"]=169;
entities["Aacute"]=225;
entities["Theta"]=952;
entities["mdash"]=8212;
entities["Euml"]=235;
entities["Kappa"]=954;
entities["notin"]=8713;
entities["iexcl"]=161;
entities["ge"]=8805;
entities["Igrave"]=236;
entities["harr"]=8660;
entities["lowast"]=8727;
entities["Ocirc"]=244;
entities["infin"]=8734;
entities["brvbar"]=166;
entities["int"]=8747;
entities["macr"]=175;
entities["frac34"]=190;
entities["curren"]=164;
entities["asymp"]=8776;
entities["Lambda"]=955;
entities["frasl"]=8260;
entities["circ"]=710;
entities["crarr"]=8629;
entities["OElig"]=339;
entities["image"]=8465;
entities["there4"]=8756;
entities["lt"]=60;
entities["minus"]=8722;
entities["Atilde"]=227;
entities["ldquo"]=8220;
entities["nabla"]=8711;
entities["exist"]=8707;
entities["Auml"]=228;
entities["Mu"]=956;
entities["frac14"]=188;
entities["nbsp"]=160;
entities["Oacute"]=243;
entities["bull"]=8226;
entities["larr"]=8656;
entities["laquo"]=171;
entities["oline"]=8254;
entities["ndash"]=8211;
entities["euro"]=8364;
entities["micro"]=181;
entities["Nu"]=957;
entities["cap"]=8745;
entities["Aring"]=229;
entities["Omicron"]=959;
entities["Iacute"]=237;
entities["perp"]=8869;
entities["para"]=182;
entities["rarr"]=8658;
entities["raquo"]=187;
entities["Ucirc"]=251;
entities["Iota"]=953;
entities["sbquo"]=8218;
entities["loz"]=9674;
entities["thetasym"]=977;
entities["ni"]=8715;
entities["part"]=8706;
entities["rdquo"]=8221;
entities["weierp"]=8472;
entities["sup1"]=185;
entities["sup2"]=178;
entities["Uacute"]=250;
entities["sdot"]=8901;
entities["Scaron"]=353;
entities["yen"]=165;
entities["Xi"]=958;
entities["plusmn"]=177;
entities["yuml"]=376;
entities["THORN"]=254;
entities["rang"]=9002;
entities["Ugrave"]=249;
entities["radic"]=8730;
entities["zwj"]=8205;
entities["tilde"]=732;
entities["uarr"]=8657;
entities["times"]=215;
entities["thinsp"]=8201;
entities["sect"]=167;
entities["rceil"]=8969;
entities["szlig"]=223;
entities["supe"]=8839;
entities["Uuml"]=252;
entities["rsquo"]=8217;
entities["Zeta"]=950;
entities["Rho"]=961;
entities["lrm"]=8206;
entities["Phi"]=966;
entities["zwnj"]=8204;
entities["lang"]=9001;
entities["pound"]=163;
entities["sigmaf"]=962;
entities["uml"]=168;
entities["prop"]=8733;
entities["Upsilon"]=965;
entities["Omega"]=969;
entities["middot"]=183;
entities["Tau"]=964;
entities["sup3"]=179;
entities["rsaquo"]=8250;
entities["prod"]=8719;
entities["quot"]=34;
entities["prime"]=8243;
entities["spades"]=9824;
return entities;
}
entityMap=createEntityMap();
cent=structFind(entityMap,"cent");
writeoutput("#cent# #chr(cent)#");
</cfscript>