Convert special characters to HTML in Javascript

Question

The best way in my opinion is to use the browser's inbuilt HTML escape functionality to handle many of the cases. To do this simply create a element in the DOM tree and set the innerText of the element to your string. Then retrieve the innerHTML of the element. The browser will return an HTML encoded string.

function HtmlEncode(s)
{
  var el = document.createElement("div");
  el.innerText = el.textContent = s;
  s = el.innerHTML;
  return s;
}

Test run:

alert(HtmlEncode('&;\'><"'));

Output:

&;'><"

This method of escaping HTML is also used by the Prototype JS library though differently from the simplistic sample I have given.

Note: You will still need to escape quotes (double and single) yourself. You can use any of the methods outlined by others here.

You need a function that does something like

return mystring.replace(/&/g, "&amp;").replace(/>/g, "&gt;").replace(/</g, "&lt;").replace(/"/g, "&quot;");

But taking into account your desire for different handling of single/double quotes.

This generic function encodes every non alphabetic character to its htmlcode (numeric):

function HTMLEncode(str) {
    var i = str.length,
        aRet = [];

    while (i--) {
        var iC = str[i].charCodeAt();
        if (iC < 65 || iC > 127 || (iC>90 && iC<97)) {
            aRet[i] = '&#'+iC+';';
        } else {
            aRet[i] = str[i];
        }
    }
    return aRet.join('');
}

For those who want to decode an integer char code like &#xxx; inside a string, use this function:

function decodeHtmlCharCodes(str) { 
  return str.replace(/(&#(\d+);)/g, function(match, capture, charCode) {
    return String.fromCharCode(charCode);
  });
}

// Will output "The show that gained int’l reputation’!"
console.log(decodeHtmlCharCodes('The show that gained int’l reputation’!'));

ES6

const decodeHtmlCharCodes = str => 
  str.replace(/(&#(\d+);)/g, (match, capture, charCode) => 
    String.fromCharCode(charCode));

// Will output "The show that gained int’l reputation’!"
console.log(decodeHtmlCharCodes('The show that gained int’l reputation’!'));

From Mozilla ...

Note that charCodeAt will always return a value that is less than 65,536. This is because the higher code points are represented by a pair of (lower valued) "surrogate" pseudo-characters which are used to comprise the real character. Because of this, in order to examine or reproduce the full character for individual characters of value 65,536 and above, for such characters, it is necessary to retrieve not only charCodeAt(i), but also charCodeAt(i+1) (as if examining/reproducing a string with two >letters).

The Best Solution

/**
 * (c) 2012 Steven Levithan <http://slevithan.com/>
 * MIT license
 */
if (!String.prototype.codePointAt) {
    String.prototype.codePointAt = function (pos) {
        pos = isNaN(pos) ? 0 : pos;
        var str = String(this),
            code = str.charCodeAt(pos),
            next = str.charCodeAt(pos + 1);
        // If a surrogate pair
        if (0xD800 <= code && code <= 0xDBFF && 0xDC00 <= next && next <= 0xDFFF) {
            return ((code - 0xD800) * 0x400) + (next - 0xDC00) + 0x10000;
        }
        return code;
    };
}

/**
 * Encodes special html characters
 * @param string
 * @return {*}
 */
function html_encode(string) {
    var ret_val = '';
    for (var i = 0; i < string.length; i++) { 
        if (string.codePointAt(i) > 127) {
            ret_val += '&#' + string.codePointAt(i) + ';';
        } else {
            ret_val += string.charAt(i);
        }
    }
    return ret_val;
}

Usage example:

html_encode("✈");

Create a function that uses string replace

function convert(str)
{
  str = str.replace(/&/g, "&");
  str = str.replace(/>/g, ">");
  str = str.replace(/</g, "&lt;");
  str = str.replace(/"/g, "&quot;");
  str = str.replace(/'/g, "&#039;");
  return str;
}