Not able to sanitize URL : http://localhost:3000/tv/%3Cscript%3Easd12569%3C/script%3E using bleach

[manankapoor88]

Hi,

I am not able to sanitize encoded URL as see below:

http://localhost:3000/tv/%3Cscript%3Easd12569%3C/script%3E.

we are also to sanitize if url is coming as : http://localhost:3000/tv/<script>asd12569</script>

Can you please help on this how this can be sanitize as from request itself we are getting URL in this manner.

[wusala01]

You need to decode the URI. There are two globals for that in JS:

decodeURI
decodeURIComponent

see in action:

const {sanitize} = require('bleach');
const unsafe_uri = 'http://localhost:3000/tv/%3Cscript%3Easd12569%3C/script%3E';

const sanitizeUri = uri => {
  let decodedUri = decodeURI(uri);
  let sanitized = sanitize(decodedUri);
  let sanitized_and_encoded = encodeURI(sanitized);
  return sanitized_and_encoded;
};

var safe_uri = sanitizeUri(unsafe_uri);

console.log(safe_uri);

or if you can or want to be more precize in what to sanitize:

const {sanitize} = require('bleach'),
  url = require("url");

const unsafe_uri = 'http://localhost:3000/tv/%3Cscript%3Easd12569%3C/script%3E';

const sanitizeUri = (uri, options = {
  component: "pathname", 
  encode: "none" 
}) => {
  let urlObject = url.parse(uri);
  let compenentString = urlObject[options.component];
  compenentString = decodeURIComponent(compenentString);
  compenentString = sanitize(compenentString);
  if(options.encode === "full") compenentString = encodeURI(compenentString);
  else if (options.encode === "component") compenentString = encodeURIComponent(compenentString);
  urlObject[options.component] = compenentString;
  return url.format(urlObject);
};

var safe_uri = sanitizeUri(unsafe_uri, {
  component: "pathname",
  encode: "full"
});

console.log(safe_uri);