HTML Entity Decode [duplicate]

Question

This question already has an answer here:

• Unescape HTML entities in Javascript? 10 answers

How do I encode and decode HTML entities using JavaScript or JQuery?

var varTitle = "Chris' corner";

I want it to be:

var varTitle = "Chris' corner";

Answer 1

Inspired by Robert K's solution, this version does not strip HTML tags, and is just as secure.

var decode_entities = (function() {
    // Remove HTML Entities
    var element = document.createElement('div');

    function decode_HTML_entities (str) {

        if(str && typeof str === 'string') {

            // Escape HTML before decoding for HTML Entities
            str = escape(str).replace(/%26/g,'&').replace(/%23/g,'#').replace(/%3B/g,';');

            element.innerHTML = str;
            if(element.innerText){
                str = element.innerText;
                element.innerText = '';
            }else{
                // Firefox support
                str = element.textContent;
                element.textContent = '';
            }
        }
        return unescape(str);
    }
    return decode_HTML_entities;
})();

Answer 2

Because @Robert K and @mattcasey both have good code, I thought I'd contribute here with a CoffeeScript version, in case anyone in the future could use it:

    String::unescape = (strict = false) ->
      ###
      # Take escaped text, and return the unescaped version
      #
      # @param string str | String to be used
      # @param bool strict | Stict mode will remove all HTML
      #
      # Test it here:
      # https://jsfiddle.net/tigerhawkvok/t9pn1dn5/
      #
      # Code: https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d
      ###
      # Create a dummy element
      element = document.createElement("div")
      decodeHTMLEntities = (str) ->
        if str? and typeof str is "string"
          unless strict is true
            # escape HTML tags
            str = escape(str).replace(/%26/g,'&').replace(/%23/g,'#').replace(/%3B/g,';')
          else
            str = str.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '')
            str = str.replace(/<\/?\w(?:[^"'>]|"[^"]*"|'[^']*')*>/gmi, '')
          element.innerHTML = str
          if element.innerText
            # Do we support innerText?
            str = element.innerText
            element.innerText = ""
          else
            # Firefox
            str = element.textContent
            element.textContent = ""
        unescape(str)
      # Remove encoded or double-encoded tags
      fixHtmlEncodings = (string) ->
        string = string.replace(/\&amp;#/mg, '&#') # The rest, for double-encodings
        string = string.replace(/\&quot;/mg, '"')
        string = string.replace(/\&quote;/mg, '"')
        string = string.replace(/\&#95;/mg, '_')
        string = string.replace(/\&#39;/mg, "'")
        string = string.replace(/\&#34;/mg, '"')
        string = string.replace(/\&#62;/mg, '>')
        string = string.replace(/\&#60;/mg, '<')
        string
      # Run it
      tmp = fixHtmlEncodings(this)
      decodeHTMLEntities(tmp)

See https://jsfiddle.net/tigerhawkvok/t9pn1dn5/7/ or https://gist.github.com/tigerhawkvok/285b8631ed6ebef4446d (includes compiled JS, and is probably updated compared to this answer)

Answer 3

You could try something like:

var Title = $('<textarea />').html("Chris&apos; corner").text();
console.log(Title);

<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>

JS Fiddle.

A more interactive version:

$('form').submit(function() {
  var theString = $('#string').val();
  var varTitle = $('<textarea />').html(theString).text();
  $('#output').text(varTitle);
  return false;
});

<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<form action="#" method="post">
  <fieldset>
    <label for="string">Enter a html-encoded string to decode</label>
    <input type="text" name="string" id="string" />
  </fieldset>
  <fieldset>
    <input type="submit" value="decode" />
  </fieldset>
</form>

<div id="output"></div>

JS Fiddle.

Answer 4

To add yet another "inspired by Robert K" to the list, here is another safe version which does not strip HTML tags. Instead of running the whole string through the HTML parser, it pulls out only the entities and converts those.

var decodeEntities = (function() {
    // this prevents any overhead from creating the object each time
    var element = document.createElement('div');

    // regular expression matching HTML entities
    var entity = /&(?:#x[a-f0-9]+|#[0-9]+|[a-z0-9]+);?/ig;

    return function decodeHTMLEntities(str) {
        // find and replace all the html entities
        str = str.replace(entity, function(m) {
            element.innerHTML = m;
            return element.textContent;
        });

        // reset the value
        element.textContent = '';

        return str;
    }
})();

Answer 5

here is another version:

function convertHTMLEntity(text){
    const span = document.createElement('span');

    return text
    .replace(/&[#A-Za-z0-9]+;/gi, (entity,position,text)=> {
        span.innerHTML = entity;
        return span.innerText;
    });
}

console.log(convertHTMLEntity('Large < £ 500'));

Answer 6

I think that is the exact opposite of the solution chosen.

var decoded = $("<div/>").text(encodedStr).html();

Try it :)