I have some Javascript code that communicates with an XML-RPC backend. The XML-RPC returns strings of the form:
a javascript solution that catches the common ones:
var map = {amp: '&', lt: '<', gt: '>', quot: '"', '#039': "'"}
str = str.replace(/&([^;]+);/g, (m, c) => map[c])
this is the reverse of https://stackoverflow.com/a/4835406/2738039
Closures can avoid creating unnecessary objects.
const decodingHandler = (() => {
const element = document.createElement('div');
return text => {
element.innerHTML = text;
return element.textContent;
};
})();
A more concise way
const decodingHandler = (() => {
const element = document.createElement('div');
return text => ((element.innerHTML = text), element.textContent);
})();
The trick is to use the power of the browser to decode the special HTML characters, but not allow the browser to execute the results as if it was actual html... This function uses a regex to identify and replace encoded HTML characters, one character at a time.
function unescapeHtml(html) {
var el = document.createElement('div');
return html.replace(/\&[#0-9a-z]+;/gi, function (enc) {
el.innerHTML = enc;
return el.innerText
});
}
var htmlEnDeCode = (function() {
var charToEntityRegex,
entityToCharRegex,
charToEntity,
entityToChar;
function resetCharacterEntities() {
charToEntity = {};
entityToChar = {};
// add the default set
addCharacterEntities({
'&' : '&',
'>' : '>',
'<' : '<',
'"' : '"',
''' : "'"
});
}
function addCharacterEntities(newEntities) {
var charKeys = [],
entityKeys = [],
key, echar;
for (key in newEntities) {
echar = newEntities[key];
entityToChar[key] = echar;
charToEntity[echar] = key;
charKeys.push(echar);
entityKeys.push(key);
}
charToEntityRegex = new RegExp('(' + charKeys.join('|') + ')', 'g');
entityToCharRegex = new RegExp('(' + entityKeys.join('|') + '|&#[0-9]{1,5};' + ')', 'g');
}
function htmlEncode(value){
var htmlEncodeReplaceFn = function(match, capture) {
return charToEntity[capture];
};
return (!value) ? value : String(value).replace(charToEntityRegex, htmlEncodeReplaceFn);
}
function htmlDecode(value) {
var htmlDecodeReplaceFn = function(match, capture) {
return (capture in entityToChar) ? entityToChar[capture] : String.fromCharCode(parseInt(capture.substr(2), 10));
};
return (!value) ? value : String(value).replace(entityToCharRegex, htmlDecodeReplaceFn);
}
resetCharacterEntities();
return {
htmlEncode: htmlEncode,
htmlDecode: htmlDecode
};
})();
This is from ExtJS source code.
All of the other answers here have problems.
The document.createElement('div') methods (including those using jQuery) execute any javascript passed into it (a security issue) and the DOMParser.parseFromString() method trims whitespace. Here is a pure javascript solution that has neither problem:
function htmlDecode(html) {
var textarea = document.createElement("textarea");
html= html.replace(/\r/g, String.fromCharCode(0xe000)); // Replace "\r" with reserved unicode character.
textarea.innerHTML = html;
var result = textarea.value;
return result.replace(new RegExp(String.fromCharCode(0xe000), 'g'), '\r');
}
TextArea is used specifically to avoid executig js code. It passes these:
htmlDecode('<& >'); // returns "<& >" with non-breaking space.
htmlDecode(' '); // returns " "
htmlDecode('<img src="dummy" onerror="alert(\'xss\')">'); // Does not execute alert()
htmlDecode('\r\n') // returns "\r\n", doesn't lose the \r like other solutions.
I was crazy enough to go through and make this function that should be pretty, if not completely, exhaustive:
function removeEncoding(string) {
return string.replace(/À/g, "À").replace(/Á/g, "Á").replace(/Â/g, "Â").replace(/Ã/g, "Ã").replace(/Ä/g, "Ä").replace(/Å/g, "Å").replace(/à/g, "à").replace(/â/g, "â").replace(/ã/g, "ã").replace(/ä/g, "ä").replace(/å/g, "å").replace(/Æ/g, "Æ").replace(/æ/g, "æ").replace(/ß/g, "ß").replace(/Ç/g, "Ç").replace(/ç/g, "ç").replace(/È/g, "È").replace(/É/g, "É").replace(/Ê/g, "Ê").replace(/Ë/g, "Ë").replace(/è/g, "è").replace(/é/g, "é").replace(/ê/g, "ê").replace(/ë/g, "ë").replace(/ƒ/g, "ƒ").replace(/Ì/g, "Ì").replace(/Í/g, "Í").replace(/Î/g, "Î").replace(/Ï/g, "Ï").replace(/ì/g, "ì").replace(/í/g, "í").replace(/î/g, "î").replace(/ï/g, "ï").replace(/Ñ/g, "Ñ").replace(/ñ/g, "ñ").replace(/Ò/g, "Ò").replace(/Ó/g, "Ó").replace(/Ô/g, "Ô").replace(/Õ/g, "Õ").replace(/Ö/g, "Ö").replace(/ò/g, "ò").replace(/ó/g, "ó").replace(/ô/g, "ô").replace(/õ/g, "õ").replace(/ö/g, "ö").replace(/Ø/g, "Ø").replace(/ø/g, "ø").replace(/Œ/g, "Œ").replace(/œ/g, "œ").replace(/Š/g, "Š").replace(/š/g, "š").replace(/Ù/g, "Ù").replace(/Ú/g, "Ú").replace(/Û/g, "Û").replace(/Ü/g, "Ü").replace(/ù/g, "ù").replace(/ú/g, "ú").replace(/û/g, "û").replace(/ü/g, "ü").replace(/µ/g, "µ").replace(/×/g, "×").replace(/Ý/g, "Ý").replace(/Ÿ/g, "Ÿ").replace(/ý/g, "ý").replace(/ÿ/g, "ÿ").replace(/°/g, "°").replace(/†/g, "†").replace(/‡/g, "‡").replace(/</g, "<").replace(/>/g, ">").replace(/±/g, "±").replace(/«/g, "«").replace(/»/g, "»").replace(/¿/g, "¿").replace(/¡/g, "¡").replace(/·/g, "·").replace(/•/g, "•").replace(/™/g, "™").replace(/©/g, "©").replace(/®/g, "®").replace(/§/g, "§").replace(/¶/g, "¶").replace(/Α/g, "Α").replace(/Β/g, "Β").replace(/Γ/g, "Γ").replace(/Δ/g, "Δ").replace(/Ε/g, "Ε").replace(/Ζ/g, "Ζ").replace(/Η/g, "Η").replace(/Θ/g, "Θ").replace(/Ι/g, "Ι").replace(/Κ/g, "Κ").replace(/Λ/g, "Λ").replace(/Μ/g, "Μ").replace(/Ν/g, "Ν").replace(/Ξ/g, "Ξ").replace(/Ο/g, "Ο").replace(/Π/g, "Π").replace(/Ρ/g, "Ρ").replace(/Σ/g, "Σ").replace(/Τ/g, "Τ").replace(/Υ/g, "Υ").replace(/Φ/g, "Φ").replace(/Χ/g, "Χ").replace(/Ψ/g, "Ψ").replace(/Ω/g, "Ω").replace(/α/g, "α").replace(/β/g, "β").replace(/γ/g, "γ").replace(/δ/g, "δ").replace(/ε/g, "ε").replace(/ζ/g, "ζ").replace(/η/g, "η").replace(/θ/g, "θ").replace(/ι/g, "ι").replace(/κ/g, "κ").replace(/λ/g, "λ").replace(/μ/g, "μ").replace(/ν/g, "ν").replace(/ξ/g, "ξ").replace(/ο/g, "ο").replace(/&piρ;/g, "ρ").replace(/ρ/g, "ς").replace(/ς/g, "ς").replace(/σ/g, "σ").replace(/τ/g, "τ").replace(/φ/g, "φ").replace(/χ/g, "χ").replace(/ψ/g, "ψ").replace(/ω/g, "ω").replace(/•/g, "•").replace(/…/g, "…").replace(/′/g, "′").replace(/″/g, "″").replace(/‾/g, "‾").replace(/⁄/g, "⁄").replace(/℘/g, "℘").replace(/ℑ/g, "ℑ").replace(/ℜ/g, "ℜ").replace(/™/g, "™").replace(/ℵ/g, "ℵ").replace(/←/g, "←").replace(/↑/g, "↑").replace(/→/g, "→").replace(/↓/g, "↓").replace(/&barr;/g, "↔").replace(/↵/g, "↵").replace(/⇐/g, "⇐").replace(/⇑/g, "⇑").replace(/⇒/g, "⇒").replace(/⇓/g, "⇓").replace(/⇔/g, "⇔").replace(/∀/g, "∀").replace(/∂/g, "∂").replace(/∃/g, "∃").replace(/∅/g, "∅").replace(/∇/g, "∇").replace(/∈/g, "∈").replace(/∉/g, "∉").replace(/∋/g, "∋").replace(/∏/g, "∏").replace(/∑/g, "∑").replace(/−/g, "−").replace(/∗/g, "∗").replace(/√/g, "√").replace(/∝/g, "∝").replace(/∞/g, "∞").replace(/&OEig;/g, "Œ").replace(/œ/g, "œ").replace(/Ÿ/g, "Ÿ").replace(/♠/g, "♠").replace(/♣/g, "♣").replace(/♥/g, "♥").replace(/♦/g, "♦").replace(/ϑ/g, "ϑ").replace(/ϒ/g, "ϒ").replace(/ϖ/g, "ϖ").replace(/Š/g, "Š").replace(/š/g, "š").replace(/∠/g, "∠").replace(/∧/g, "∧").replace(/∨/g, "∨").replace(/∩/g, "∩").replace(/∪/g, "∪").replace(/∫/g, "∫").replace(/∴/g, "∴").replace(/∼/g, "∼").replace(/≅/g, "≅").replace(/≈/g, "≈").replace(/≠/g, "≠").replace(/≡/g, "≡").replace(/≤/g, "≤").replace(/≥/g, "≥").replace(/⊂/g, "⊂").replace(/⊃/g, "⊃").replace(/⊄/g, "⊄").replace(/⊆/g, "⊆").replace(/⊇/g, "⊇").replace(/⊕/g, "⊕").replace(/⊗/g, "⊗").replace(/⊥/g, "⊥").replace(/⋅/g, "⋅").replace(/&lcell;/g, "⌈").replace(/&rcell;/g, "⌉").replace(/⌊/g, "⌊").replace(/⌋/g, "⌋").replace(/⟨/g, "⟨").replace(/⟩/g, "⟩").replace(/◊/g, "◊").replace(/'/g, "'").replace(/&/g, "&").replace(/"/g, "\"");
}
Used like so:
let decodedText = removeEncoding("Ich heiße David");
console.log(decodedText);
Prints: Ich Heiße David
P.S. this took like an hour and a half to make.