Escaping HTML strings with jQuery

There is also the solution from mustache.js

var entityMap = {
  '&': '&',
  '<': '&lt;',
  '>': '&gt;',
  '"': '&quot;',
  "'": '&#39;',
  '/': '&#x2F;',
  '`': '&#x60;',
  '=': '&#x3D;'
};

function escapeHtml (string) {
  return String(string).replace(/[&<>"'`=\/]/g, function (s) {
    return entityMap[s];
  });
}

---

Since you're using jQuery, you can just set the element's text property:

// before:
// <div class="someClass">text</div>
var someHtmlString = "<script>alert('hi!');</script>";

// set a DIV's text:
$("div.someClass").text(someHtmlString);
// after: 
// <div class="someClass">&lt;script&gt;alert('hi!');&lt;/script&gt;</div>

// get the text in a string:
var escaped = $("<div>").text(someHtmlString).html();
// value: 
// &lt;script&gt;alert('hi!');&lt;/script&gt;

---

$('<div/>').text('This is fun & stuff').html(); // "This is fun &amp; stuff"

Source: http://debuggable.com/posts/encode-html-entities-with-jquery:480f4dd6-13cc-4ce9-8071-4710cbdd56cb

---

If you're escaping for HTML, there are only three that I can think of that would be really necessary:

html.replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;");

Depending on your use case, you might also need to do things like " to ". If the list got big enough, I'd just use an array:

var escaped = html;
var findReplace = [[/&/g, "&amp;"], [/</g, "&lt;"], [/>/g, "&gt;"], [/"/g, "&quot;"]]
for(var item in findReplace)
    escaped = escaped.replace(findReplace[item][0], findReplace[item][1]);

encodeURIComponent() will only escape it for URLs, not for HTML.

---

Easy enough to use underscore:

_.escape(string) 

Underscore is a utility library that provides a lot of features that native js doesn't provide. There's also lodash which is the same API as underscore but was rewritten to be more performant.

---

I wrote a tiny little function which does this. It only escapes ", &, < and > (but usually that's all you need anyway). It is slightly more elegant then the earlier proposed solutions in that it only uses one .replace() to do all the conversion. (EDIT 2: Reduced code complexity making the function even smaller and neater, if you're curious about the original code see end of this answer.)

function escapeHtml(text) {
    'use strict';
    return text.replace(/[\"&<>]/g, function (a) {
        return { '"': '&quot;', '&': '&amp;', '<': '&lt;', '>': '&gt;' }[a];
    });
}

This is plain Javascript, no jQuery used.

Escaping / and ' too

Edit in response to mklement's comment.

The above function can easily be expanded to include any character. To specify more characters to escape, simply insert them both in the character class in the regular expression (i.e. inside the /[...]/g) and as an entry in the chr object. (EDIT 2: Shortened this function too, in the same way.)

function escapeHtml(text) {
    'use strict';
    return text.replace(/[\"&'\/<>]/g, function (a) {
        return {
            '"': '&quot;', '&': '&amp;', "'": '&#39;',
            '/': '&#47;',  '<': '&lt;',  '>': '&gt;'
        }[a];
    });
}

Note the above use of ' for apostrophe (the symbolic entity ' might have been used instead – it is defined in XML, but was originally not included in the HTML spec and might therefore not be supported by all browsers. See: Wikipedia article on HTML character encodings). I also recall reading somewhere that using decimal entities is more widely supported than using hexadecimal, but I can't seem to find the source for that now though. (And there cannot be many browsers out there which does not support the hexadecimal entities.)

Note: Adding / and ' to the list of escaped characters isn't all that useful, since they do not have any special meaning in HTML and do not need to be escaped.

Original escapeHtml Function

EDIT 2: The original function used a variable (chr) to store the object needed for the .replace() callback. This variable also needed an extra anonymous function to scope it, making the function (needlessly) a little bit bigger and more complex.

var escapeHtml = (function () {
    'use strict';
    var chr = { '"': '&quot;', '&': '&amp;', '<': '&lt;', '>': '&gt;' };
    return function (text) {
        return text.replace(/[\"&<>]/g, function (a) { return chr[a]; });
    };
}());

I haven't tested which of the two versions are faster. If you do, feel free to add info and links about it here.

---

I realize how late I am to this party, but I have a very easy solution that does not require jQuery.

escaped = new Option(unescaped).innerHTML;

Edit: This does not escape quotes. The only case where quotes would need to be escaped is if the content is going to be pasted inline to an attribute within an HTML string. It is hard for me to imagine a case where doing this would be good design.

Edit 3: For the fastest solution, check the answer above from Saram. This one is the shortest.

---

Here is a clean, clear JavaScript function. It will escape text such as "a few < many" into "a few < many".

function escapeHtmlEntities (str) {
  if (typeof jQuery !== 'undefined') {
    // Create an empty div to use as a container,
    // then put the raw text in and get the HTML
    // equivalent out.
    return jQuery('<div/>').text(str).html();
  }

  // No jQuery, so use string replace.
  return str
    .replace(/&/g, '&amp;')
    .replace(/>/g, '&gt;')
    .replace(/</g, '&lt;')
    .replace(/"/g, '&quot;')
    .replace(/'/g, '&apos;');
}

---

After last tests I can recommend fastest and completely cross browser compatible native javaScript (DOM) solution:

function HTMLescape(html){
    return document.createElement('div')
        .appendChild(document.createTextNode(html))
        .parentNode
        .innerHTML
}

If you repeat it many times you can do it with once prepared variables:

//prepare variables
var DOMtext = document.createTextNode("test");
var DOMnative = document.createElement("span");
DOMnative.appendChild(DOMtext);

//main work for each case
function HTMLescape(html){
  DOMtext.nodeValue = html;
  return DOMnative.innerHTML
}

Look at my final performance comparison (stack question).

---

Try Underscore.string lib, it works with jQuery.

_.str.escapeHTML('<div>Blah blah blah</div>')

output:

'<div>Blah blah blah</div>'

---

escape() and unescape() are intended to encode / decode strings for URLs, not HTML.

Actually, I use the following snippet to do the trick that doesn't require any framework:

var escapedHtml = html.replace(/&/g, '&')
                      .replace(/>/g, '>')
                      .replace(/</g, '&lt;')
                      .replace(/"/g, '&quot;')
                      .replace(/'/g, '&apos;');

---

I've enhanced the mustache.js example adding the escapeHTML() method to the string object.

var __entityMap = {
    "&": "&",
    "<": "&lt;",
    ">": "&gt;",
    '"': '&quot;',
    "'": '&#39;',
    "/": '&#x2F;'
};

String.prototype.escapeHTML = function() {
    return String(this).replace(/[&<>"'\/]/g, function (s) {
        return __entityMap[s];
    });
}

That way it is quite easy to use "Some <text>, more Text&Text".escapeHTML()

---

If you have underscore.js, use _.escape (more efficient than the jQuery method posted above):

_.escape('Curly, Larry & Moe'); // returns: Curly, Larry & Moe

---

If your're going the regex route, there's an error in tghw's example above.

<!-- WON'T WORK -  item[0] is an index, not an item -->

var escaped = html; 
var findReplace = [[/&/g, "&amp;"], [/</g, "&lt;"], [/>/g,"&gt;"], [/"/g,
"&quot;"]]

for(var item in findReplace) {
     escaped = escaped.replace(item[0], item[1]);   
}


<!-- WORKS - findReplace[item[]] correctly references contents -->

var escaped = html;
var findReplace = [[/&/g, "&amp;"], [/</g, "&lt;"], [/>/g, "&gt;"], [/"/g, "&quot;"]]

for(var item in findReplace) {
     escaped = escaped.replace(findReplace[item[0]], findReplace[item[1]]);
}

---

This is a nice safe example...

function escapeHtml(str) {
    if (typeof(str) == "string"){
        try{
            var newStr = "";
            var nextCode = 0;
            for (var i = 0;i < str.length;i++){
                nextCode = str.charCodeAt(i);
                if (nextCode > 0 && nextCode < 128){
                    newStr += "&#"+nextCode+";";
                }
                else{
                    newStr += "?";
                }
             }
             return newStr;
        }
        catch(err){
        }
    }
    else{
        return str;
    }
}

---

You can easily do it with vanilla js.

Simply add a text node the document. It will be escaped by the browser.

var escaped = document.createTextNode("<HTML TO/ESCAPE/>")
document.getElementById("[PARENT_NODE]").appendChild(escaped)

---

2 simple methods that require NO JQUERY...

You can encode all characters in your string like this:

function encode(e){return e.replace(/[^]/g,function(e){return"&#"+e.charCodeAt(0)+";"})}

Or just target the main characters to worry about &, line breaks, <, >, " and ' like:

function encode(r){ return r.replace(/[\x26\x0A\<>'"]/g,function(r){return"&#"+r.charCodeAt(0)+";"}) } var myString='Encode HTML entities!\n"Safe" escape