mirror of
https://github.com/nodejs/node.git
synced 2026-10-29 10:45:11 +08:00
Matteo Collina
22ab7d77f1
Add `Buffer.stringLength(input[, encoding])`, the counterpart of `Buffer.byteLength()`: it returns the number of UTF-16 code units that `buf.toString(encoding)` would produce, without decoding. For UTF-8 the count is computed with simdutf. Invalid input is counted with the same maximal-subpart replacement that the decoder applies, so the result always matches `toString().length`. The other encodings are computed from `byteLength` alone. This lets code that accumulates streamed input check the result against `buffer.constants.MAX_STRING_LENGTH` and size its memory budget before decoding. Refs: https://github.com/nodejs/node/issues/66062 Signed-off-by: Matteo Collina <hello@matteocollina.com> PR-URL: https://github.com/nodejs/node/pull/66064 Reviewed-By: Paolo Insogna <paolo@cowtech.it> Reviewed-By: Gürgün Dayıoğlu <hey@gurgun.day>
29 lines
769 B
JavaScript
29 lines
769 B
JavaScript
'use strict';
|
|
|
|
const common = require('../common.js');
|
|
const { Buffer } = require('node:buffer');
|
|
const assert = require('node:assert');
|
|
|
|
const bench = common.createBenchmark(main, {
|
|
n: [1e6],
|
|
encoding: ['utf8', 'latin1', 'base64'],
|
|
len: [32, 4096, 1048576],
|
|
input: ['ascii', 'multibyte', 'invalid'],
|
|
});
|
|
|
|
function main({ n, encoding, len, input }) {
|
|
let buf;
|
|
if (input === 'ascii') {
|
|
buf = Buffer.alloc(len, 'a');
|
|
} else {
|
|
buf = Buffer.alloc(len - (len % 3), '€');
|
|
if (input === 'invalid') buf = Buffer.concat([buf, Buffer.from([0xE2, 0x82])]);
|
|
}
|
|
const expected = buf.toString(encoding).length;
|
|
bench.start();
|
|
for (let i = 0; i < n; ++i) {
|
|
assert.strictEqual(Buffer.stringLength(buf, encoding), expected);
|
|
}
|
|
bench.end(n);
|
|
}
|