Skip to content

Instantly share code, notes, and snippets.

@AaronHarris

AaronHarris/remove-invalid-xml-characters.js

Forked from john-doherty/remove-invalid-xml-characters.js
Last active January 11, 2021 18:49
Show Gist options
  • Save AaronHarris/1c4d48b6058ed9af7935534474b0f59c to your computer and use it in GitHub Desktop.
Save AaronHarris/1c4d48b6058ed9af7935534474b0f59c to your computer and use it in GitHub Desktop.
Download ZIP
JavaScript function that removes invalid XML characters from a string according to the spec
Raw
remove-invalid-xml-characters.js
// remove everything forbidden by XML 1.0 specifications, plus the unicode replacement character U+FFFD
const INVALID_XML_REGEX = /((?:[\0-\x08\x0B\f\x0E-\x1F\uFFFD\uFFFE\uFFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?:[^\uD800-\uDBFF]|^)[\uDC00-\uDFFF]))/g;
// remove everything discouraged by XML 1.0 specifications
const DISCOURAGED_XML_REGEX = new RegExp(
'([\\x7F-\\x84]|[\\x86-\\x9F]|[\\uFDD0-\\uFDEF]|(?:\\uD83F[\\uDFFE\\uDFFF])|(?:\\uD87F[\\uDF' +
'FE\\uDFFF])|(?:\\uD8BF[\\uDFFE\\uDFFF])|(?:\\uD8FF[\\uDFFE\\uDFFF])|(?:\\uD93F[\\uDFFE\\uD' +
'FFF])|(?:\\uD97F[\\uDFFE\\uDFFF])|(?:\\uD9BF[\\uDFFE\\uDFFF])|(?:\\uD9FF[\\uDFFE\\uDFFF])' +
'|(?:\\uDA3F[\\uDFFE\\uDFFF])|(?:\\uDA7F[\\uDFFE\\uDFFF])|(?:\\uDABF[\\uDFFE\\uDFFF])|(?:\\' +
'uDAFF[\\uDFFE\\uDFFF])|(?:\\uDB3F[\\uDFFE\\uDFFF])|(?:\\uDB7F[\\uDFFE\\uDFFF])|(?:\\uDBBF' +
'[\\uDFFE\\uDFFF])|(?:\\uDBFF[\\uDFFE\\uDFFF])(?:[\\0-\\t\\x0B\\f\\x0E-\\u2027\\u202A-\\uD7FF\\' +
'uE000-\\uFFFF]|[\\uD800-\\uDBFF][\\uDC00-\\uDFFF]|[\\uD800-\\uDBFF](?![\\uDC00-\\uDFFF])|' +
'(?:[^\\uD800-\\uDBFF]|^)[\\uDC00-\\uDFFF]))', 'g');
/**
* Removes invalid XML characters from a string
* @param {string} str - a string containing potentially invalid XML characters (non-UTF8 characters, STX, EOX etc)
* @param {boolean} removeDiscouragedChars - should it remove discouraged but valid XML characters
* @return {string} a sanitized string stripped of invalid XML characters
*/
function escapeXMLInvalidChars(str, removeDiscouragedChars) {
// ensure we have a string
str = String(str || '').replace(INVALID_XML_REGEX, c => '\\u' + ('000' + c.charCodeAt().toString(16)).slice(-4));
if (removeDiscouragedChars) {
str = str.replace(DISCOURAGED_XML_REGEX, c => '\\u' + ('000' + c.charCodeAt().toString(16)).slice(-4));
}
return str;
}
@AaronHarris
Copy link
Author

Inspiration:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment