My current code converts characters into entities as expected. But if I convert emoji, then it generates something like ļæ½ļæ½ for š¤© which doesn't render as expected.
String.prototype.toHtmlEntities = function() {
return this.replace(/./gm, function(s) {
// return "&#" + s.charCodeAt(0) + ";";
return (s.match(/[a-z0-9\s]+/i)) ? s : "&#" + s.charCodeAt(0) + ";";
});
};
console.log("š¤©".toHtmlEntities())
document.write("š¤©".toHtmlEntities())You're iterating over the code units of your string. Instead, you want to iterate over the code points. Most emojis consist of one code point, which is encoded by two code units called surrogate pairs - one high and one low one. Surrogate pairs when displayed standalone don't represent a valid symbol, which ends up with ļæ½ being rendered. If you use the u (unicode) flag on your regular expression, your . will then match based on the code points, allowing you to iterate over each code point (rather than code unit). You can then access the code point value using codePointAt(0), which you can then encode into a HTML entity:
String.prototype.toHtmlEntities = function() {
return this.replace(/./ugm, s => s.match(/[a-z0-9\s]+/i) ? s : "&#" + s.codePointAt(0) + ";");
};
console.log("a".toHtmlEntities());
document.write("a".toHtmlEntities());
console.log("&".toHtmlEntities());
document.write("&".toHtmlEntities());
console.log("š".toHtmlEntities()); // surrogate pair test
document.write("š".toHtmlEntities());
console.log("šØāš©āš§āš¦".toHtmlEntities()); // ZWJ test
document.write("šØāš©āš§āš¦".toHtmlEntities());
console.log("ā¤ļø".toHtmlEntities()); // variation selector test
document.write("ā¤ļø".toHtmlEntities()); // variation selector test
console.log("nĢ".toHtmlEntities()); // decomposed character test (length of 2)
document.write("nĢ".toHtmlEntities()); // decomposed character test (length of 2)
console.log("Ʊ".toHtmlEntities()); // composed character (length of 1)
document.write("Ʊ".toHtmlEntities()); // composed character (length of 1)