I need to sort an array of strings, where elements are compared lexicographically as sequences of code point values, so that, for example, "Z" < "a" < "\udabc" < "�" < "💩".
"�" < "💩" should still hold)? Is there a more efficient procedure for this special case?Note: there are many answers on StackOverflow explaining how to sort strings, but they either use the localeCompare order or the order defined by JavaScript comparison operators (which compare strings as sequences of UTF-16 code units). I am not interested in either of those.
How to sort strings in JavaScript by code point values?
It appears to be a surprisingly difficult problem. Here's a Proof Of Concept (POC) implementation:
'use strict';
function compareCodePoints(s1, s2) {
const len = Math.min(s1.length, s2.length);
let i = 0;
for (const c1 of s1) {
if (i >= len) {
break;
}
const cp1 = s1.codePointAt(i);
const cp2 = s2.codePointAt(i);
const order = cp1 - cp2;
if (order !== 0) {
return order;
}
i++;
if (cp1 > 0xFFFF) {
i++;
}
}
return s1.length - s2.length;
}
let s =[];
let s1 = "abc𞸁z";
let s2 = "abc𞸂z";
s = [s1, s2];
console.log(s);
s.sort(compareCodePoints);
console.log(s);
console.log()
s = [s2, s1];
console.log(s);
s.sort(compareCodePoints);
console.log(s);
console.log()
s1 = "a";
s2 = "";
console.log([s1, s2]);
console.log(compareCodePoints(s1, s2));
console.log([s2, s1]);
console.log(compareCodePoints(s2, s1));
$ node codepoint.poc.js
[ 'abc𞸁z', 'abc𞸂z' ]
[ 'abc𞸁z', 'abc𞸂z' ]
[ 'abc𞸂z', 'abc𞸁z' ]
[ 'abc𞸁z', 'abc𞸂z' ]
[ 'a', '' ]
1
[ '', 'a' ]
-1
$