/** * A Javascript object to encode and/or decode html characters * @Author R Reid * source: http://www.strictly-software.com/htmlencode * Licence: GPL * * Revision: * 2011-07-14, Jacques-Yves Bleau: * - fixed conversion error with capitalized accentuated characters * + converted arr1 and arr2 to object property to remove redundancy */ Encoder = { // When encoding do we convert characters into html or numerical entities EncodeType : "entity", // entity OR numerical isEmpty : function(val){ if(val){ return ((val===null) || val.length==0 || /^\s+$/.test(val)); }else{ return true; } }, arr1: new Array(' ','¡','¢','£','¤','¥','¦','§','¨','©','ª','«','¬','­','®','¯','°','±','²','³','´','µ','¶','·','¸','¹','º','»','¼','½','¾','¿','À','Á','Â','Ã','Ä','Å','&Aelig;','Ç','È','É','Ê','Ë','Ì','Í','Î','Ï','Ð','Ñ','Ò','Ó','Ô','Õ','Ö','×','Ø','Ù','Ú','Û','Ü','Ý','Þ','ß','à','á','â','ã','ä','å','æ','ç','è','é','ê','ë','ì','í','î','ï','ð','ñ','ò','ó','ô','õ','ö','÷','Ø','ù','ú','û','ü','ý','þ','ÿ','"','&','<','>','œ','œ','š','š','ÿ','ˆ','˜',' ',' ',' ','‌','‍','‎','‏','–','—','‘','’','‚','“','”','„','†','†','‰','‹','›','€','ƒ','α','β','γ','δ','ε','ζ','η','θ','ι','κ','λ','μ','ν','ξ','ο','π','ρ','σ','τ','υ','φ','χ','ψ','ω','α','β','γ','δ','ε','ζ','η','θ','ι','κ','λ','μ','ν','ξ','ο','π','ρ','ς','σ','τ','υ','φ','χ','ψ','ω','ϑ','ϒ','ϖ','•','…','′','′','‾','⁄','℘','ℑ','ℜ','™','ℵ','←','↑','→','↓','↔','↵','←','↑','→','↓','↔','∀','∂','∃','∅','∇','∈','∉','∋','∏','∑','−','∗','√','∝','∞','∠','∧','∨','∩','∪','∫','∴','∼','≅','≈','≠','≡','≤','≥','⊂','⊃','⊄','⊆','⊇','⊕','⊗','⊥','⋅','⌈','⌉','⌊','⌋','⟨','⟩','◊','♠','♣','♥','♦'), arr2: new Array(' ','¡','¢','£','¤','¥','¦','§','¨','©','ª','«','¬','­','®','¯','°','±','²','³','´','µ','¶','·','¸','¹','º','»','¼','½','¾','¿','À','Á','Â','Ã','Ä','Å','Æ','Ç','È','É','Ê','Ë','Ì','Í','Î','Ï','Ð','Ñ','Ò','Ó','Ô','Õ','Ö','×','Ø','Ù','Ú','Û','Ü','Ý','Þ','ß','à','á','â','ã','ä','å','æ','ç','è','é','ê','ë','ì','í','î','ï','ð','ñ','ò','ó','ô','õ','ö','÷','ø','ù','ú','û','ü','ý','þ','ÿ','"','&','<','>','Œ','œ','Š','š','Ÿ','ˆ','˜',' ',' ',' ','‌','‍','‎','‏','–','—','‘','’','‚','“','”','„','†','‡','‰','‹','›','€','ƒ','Α','Β','Γ','Δ','Ε','Ζ','Η','Θ','Ι','Κ','Λ','Μ','Ν','Ξ','Ο','Π','Ρ','Σ','Τ','Υ','Φ','Χ','Ψ','Ω','α','β','γ','δ','ε','ζ','η','θ','ι','κ','λ','μ','ν','ξ','ο','π','ρ','ς','σ','τ','υ','φ','χ','ψ','ω','ϑ','ϒ','ϖ','•','…','′','″','‾','⁄','℘','ℑ','ℜ','™','ℵ','←','↑','→','↓','↔','↵','⇐','⇑','⇒','⇓','⇔','∀','∂','∃','∅','∇','∈','∉','∋','∏','∑','−','∗','√','∝','∞','∠','∧','∨','∩','∪','∫','∴','∼','≅','≈','≠','≡','≤','≥','⊂','⊃','⊄','⊆','⊇','⊕','⊗','⊥','⋅','⌈','⌉','⌊','⌋','〈','〉','◊','♠','♣','♥','♦'), // Convert HTML entities into numerical entities HTML2Numerical : function(s){ return this.swapArrayVals(s,this.arr1,this.arr2); }, // Convert Numerical entities into HTML entities NumericalToHTML : function(s){ return this.swapArrayVals(s,this.arr2,this.arr1); }, // Numerically encodes all unicode characters numEncode : function(s){ if(this.isEmpty(s)) return ""; var e = ""; for (var i = 0; i < s.length; i++) { var c = s.charAt(i); if (c < " " || c > "~") { c = "&#" + c.charCodeAt() + ";"; } e += c; } return e; }, // HTML Decode numerical and HTML entities back to original values htmlDecode : function(s){ var c,m,d = s; if(this.isEmpty(d)) return ""; // convert HTML entites back to numerical entites first d = this.HTML2Numerical(d); // look for numerical entities " arr=d.match(/&#[0-9]{1,5};/g); // if no matches found in string then skip if(arr!=null){ for(var x=0;x= -32768 && c <= 65535){ // decode every single match within string d = d.replace(m, String.fromCharCode(c)); }else{ d = d.replace(m, ""); //invalid so replace with nada } } } return d; }, // encode an input string into either numerical or HTML entities htmlEncode : function(s,dbl){ if(this.isEmpty(s)) return ""; // do we allow double encoding? E.g will & be turned into &amp; dbl = dbl || false; //default to prevent double encoding // if allowing double encoding we do ampersands first if(dbl){ if(this.EncodeType=="numerical"){ s = s.replace(/&/g, "&"); }else{ s = s.replace(/&/g, "&"); } } // convert the xss chars to numerical entities ' " < > s = this.XSSEncode(s,false); if(this.EncodeType=="numerical" || !dbl){ // Now call function that will convert any HTML entities to numerical codes s = this.HTML2Numerical(s); } // Now encode all chars above 127 e.g unicode s = this.numEncode(s); // now we know anything that needs to be encoded has been converted to numerical entities we // can encode any ampersands & that are not part of encoded entities // to handle the fact that I need to do a negative check and handle multiple ampersands &&& // I am going to use a placeholder // if we don't want double encoded entities we ignore the & in existing entities if(!dbl){ s = s.replace(/&#/g,"##AMPHASH##"); if(this.EncodeType=="numerical"){ s = s.replace(/&/g, "&"); }else{ s = s.replace(/&/g, "&"); } s = s.replace(/##AMPHASH##/g,"&#"); } // replace any malformed entities s = s.replace(/&#\d*([^\d;]|$)/g, "$1"); if(!dbl){ // safety check to correct any double encoded & s = this.correctEncoding(s); } // now do we need to convert our numerical encoded string into entities if(this.EncodeType=="entity"){ s = this.NumericalToHTML(s); } return s; }, // Encodes the basic 4 characters used to malform HTML in XSS hacks XSSEncode : function(s,en){ if(!this.isEmpty(s)){ en = en || true; // do we convert to numerical or html entity? if(en){ s = s.replace(/\'/g,"'"); //no HTML equivalent as &apos is not cross browser supported s = s.replace(/\"/g,"""); s = s.replace(//g,">"); }else{ s = s.replace(/\'/g,"'"); //no HTML equivalent as &apos is not cross browser supported s = s.replace(/\"/g,"""); s = s.replace(//g,">"); } return s; }else{ return ""; } }, // returns true if a string contains html or numerical encoded entities hasEncoded : function(s){ if(/&#[0-9]{1,5};/g.test(s)){ return true; }else if(/&[A-Z]{2,6};/gi.test(s)){ return true; }else{ return false; } }, // will remove any unicode characters stripUnicode : function(s){ return s.replace(/[^\x20-\x7E]/g,""); }, // corrects any double encoded & entities e.g &amp; correctEncoding : function(s){ return s.replace(/(&)(amp;)+/,"$1"); }, // Function to loop through an array swaping each item with the value from another array e.g swap HTML entities with Numericals swapArrayVals : function(s,arr1,arr2){ if(this.isEmpty(s)) return ""; var re; if(arr1 && arr2){ //ShowDebug("in swapArrayVals arr1.length = " + arr1.length + " arr2.length = " + arr2.length) // array lengths must match if(arr1.length == arr2.length){ for(var x=0,i=arr1.length;x