mirror of
https://github.com/morluto/rea.git
synced 2026-11-22 14:35:45 +00:00
* perf(json): count long unescaped ASCII strings without a JS loop * perf(json): count unescaped UTF-8 prefixes without rescanning --------- Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
47 lines
1.5 KiB
TypeScript
47 lines
1.5 KiB
TypeScript
/** UTF-8 JSON string bytes without serialization; above budget only establishes overflow. */
|
|
export const jsonStringByteLength = (
|
|
value: string,
|
|
budget = Number.POSITIVE_INFINITY,
|
|
): number => {
|
|
// Unescaped text has its native UTF-8 length. Stop before surrogate code
|
|
// units so the bounded loop continues to distinguish pairs from lone units.
|
|
let index = 0;
|
|
let bytes = 2;
|
|
if (value.length >= 1024 && value.length + 2 <= budget) {
|
|
const prefixEnd =
|
|
/["\\\u0000-\u001f\ud800-\udfff]/.exec(value)?.index ?? value.length;
|
|
const prefixBytes = Buffer.byteLength(
|
|
prefixEnd === value.length ? value : value.slice(0, prefixEnd),
|
|
"utf8",
|
|
);
|
|
if (prefixBytes + 2 <= budget) {
|
|
index = prefixEnd;
|
|
bytes = prefixBytes + 2;
|
|
}
|
|
}
|
|
for (; index < value.length && bytes <= budget; index++) {
|
|
const unit = value.charCodeAt(index);
|
|
if (unit === 0x22 || unit === 0x5c) bytes += 2;
|
|
else if (unit < 0x20)
|
|
bytes +=
|
|
unit === 0x08 ||
|
|
unit === 0x09 ||
|
|
unit === 0x0a ||
|
|
unit === 0x0c ||
|
|
unit === 0x0d
|
|
? 2
|
|
: 6;
|
|
else if (unit < 0x80) bytes += 1;
|
|
else if (unit < 0x800) bytes += 2;
|
|
else if (unit >= 0xd800 && unit <= 0xdbff) {
|
|
const next = value.charCodeAt(index + 1);
|
|
if (next >= 0xdc00 && next <= 0xdfff) {
|
|
bytes += 4;
|
|
index++;
|
|
} else bytes += 6;
|
|
} else if (unit >= 0xdc00 && unit <= 0xdfff) bytes += 6;
|
|
else bytes += 3;
|
|
}
|
|
return bytes;
|
|
};
|