mirror of
https://github.com/vercel-labs/scriptc.git
synced 2026-11-02 07:43:42 +08:00
Chris Tate
47904df3c2
charCodeAt on a non-ASCII string mapped the UTF-16 index to a byte offset through a string index entry, which the first read claimed and the string's release purged. For a string of one character, such as each character of a for-of loop that codePointAt(0) classifies, the entry cost more than the read. A non-ASCII receiver of up to 16 bytes is now decoded from its start on each read, as scr_str_utf16_len already counts short receivers. Longer receivers keep the index entry and its cursor.
51 lines
1.8 KiB
TypeScript
51 lines
1.8 KiB
TypeScript
// charCodeAt and codePointAt on short non-ASCII strings: characters of each
|
|
// UTF-8 length, astral pairs, lone surrogates, out-of-range and non-integer
|
|
// indexes, strings at the 16-byte boundary, and a long receiver scanned in
|
|
// between.
|
|
|
|
const samples = [
|
|
"é", "ß", "日", "語", "😀", "🚀", "a", "",
|
|
"café", "naïve", "straße", "日本語", "テキスト", "한국어",
|
|
"a😀b", "😀😀", "xéy日z",
|
|
"\ud800", "\udc00", "a\ud800b", "\ud83d", "\ude00x",
|
|
"0123456789abcdé", "0123456789abcdeé", "0123456789abcdefé", "ééééééé", "éééééééé", "ééééééééé",
|
|
];
|
|
|
|
function codes(s: string): string {
|
|
const out: string[] = [];
|
|
for (let i = -1; i <= s.length + 1; i++) out.push(String(s.charCodeAt(i)));
|
|
out.push(String(s.charCodeAt(0.5)), String(s.charCodeAt(NaN)), String(s.charCodeAt(1.9)));
|
|
return out.join(",");
|
|
}
|
|
|
|
function points(s: string): string {
|
|
const out: string[] = [];
|
|
for (let i = -1; i <= s.length + 1; i++) out.push(String(s.codePointAt(i)));
|
|
return out.join(",");
|
|
}
|
|
|
|
for (const s of samples) {
|
|
console.log(JSON.stringify(s), s.length, codes(s));
|
|
console.log(" points", points(s));
|
|
}
|
|
|
|
// A long receiver scanned while short ones are read.
|
|
let long = "";
|
|
for (let i = 0; i < 200; i++) long += i % 3 === 0 ? "é" : i % 3 === 1 ? "日" : "x";
|
|
let sum = 0;
|
|
for (let i = 0; i < long.length; i++) {
|
|
sum += long.charCodeAt(i);
|
|
sum += samples[i % samples.length]!.charCodeAt(0) || 0;
|
|
}
|
|
console.log("long", long.length, sum);
|
|
|
|
// Characters of a for-of loop classified by their code points.
|
|
let letters = 0;
|
|
let others = 0;
|
|
for (const c of "the café, 日本 😀 naïve!") {
|
|
const code = c.codePointAt(0)!;
|
|
if ((code >= 0x61 && code <= 0x7a) || code >= 0xc0) letters++;
|
|
else others++;
|
|
}
|
|
console.log("letters", letters, "others", others);
|