Use JavaScript regex to replace numerical HTML entities with their actual characters

I'm trying to use JavaScript & regex to replace numerical HTML entities with their actual Unicode characters, e.g.

foo's bar
→
foo's bar

This is what I got so far:

"foo's b开发者_开发知识库ar".replace(/&#([^\s]*);/g, "$1"); // "foo39s bar"

All that's left to do is to replace the number with String.fromCharCode($1), but I can't seem to get it to work. How can I do this?

---

"foo's bar".replace(/&#(\d+);/g, function(match, match2) {return String.fromCharCode(+match2);})

---

"foo's bar".replace(/&#([^\s]*);/g, function(x, y) { return String.fromCharCode(y) })

First argument (x) is a "'" in current example. y is 39.

---

As well as using a callback function, you may want to consider adding support for hex character references (ሴ).

Also, fromCharCode may not be enough. eg 𐤀 is a valid reference to a Phoenician character, but because it is outside the Basic Multilingual Plane, and JavaScript's String model is based on UTF-16 code units, not complete character code points, fromCharCode(67840) won't work. You'd need a UTF-16 encoder, for example:

String.fromCharCodePoint= function(/* codepoints */) {
    var codeunits= [];
    for (var i= 0; i<arguments.length; i++) {
        var c= arguments[i];
        if (arguments[i]<0x10000) {
            codeunits.push(arguments[i]);
        } else if (arguments[i]<0x110000) {
            c-= 0x10000;
            codeunits.push((c>>10 & 0x3FF) + 0xD800);
            codeunits.push((c&0x3FF) + 0xDC00);
        }
    }
    return String.fromCharCode.apply(String, codeunits);
};

function decodeCharacterReferences(s) {
    return s.replace(/&#(\d+);/g, function(_, n) {;
        return String.fromCharCodePoint(parseInt(n, 10));
    }).replace(/&#x([0-9a-f]+);/gi, function(_, n) {
        return String.fromCharCodePoint(parseInt(n, 16));
    });
};

alert(decodeCharacterReferences('Hello &#x10900; mum &#67840;!'));

---

If you don't want to define all the entities you can let the browser do it for you- this bit creates an empty p element, writes the html and returns the text it produces. The p element is never added to the document.

function translateEntities(string){
    var text, p=document.createElement('p');
    p.innerHTML=string;
    text= p.innerText || p.textContent;
    p.innerHTML='';
    return text;
}
var s= 'foo's bar';
translateEntities(s);

/*  returned value: (String)
foo's bar
*/