morluto
49b4edfe77
Share padded decoding across CDP response shapes and cache fingerprints, and count binary WebSocket bytes without allocating a decoded buffer. Preserve HAR canonical pad bits and validate before allocation. Replace repeated alphabet quartets in canonical schemas with separate alphabet, padding and fixed-width length assertions. Cover near-32MiB encodings under ordinary, Unicode and Unicode-set modes, plus complete 4MiB CLI and MCP retained-evidence export workflows. Fixes #5253
99 lines
2.9 KiB
TypeScript
99 lines
2.9 KiB
TypeScript
import { expect, it } from "vitest";
|
|
|
|
import {
|
|
CANONICAL_BASE64_PATTERN,
|
|
IDENTIFIER_PATTERN,
|
|
PADDED_BASE64_PATTERN,
|
|
STABLE_IDENTIFIER_PATTERN,
|
|
} from "./stringPatterns.js";
|
|
|
|
it("preserves identifier grammars under Unicode and Unicode-set compilation", () => {
|
|
const variants = [
|
|
{ pattern: IDENTIFIER_PATTERN, previous: /^[A-Za-z][A-Za-z0-9._-]*$/u },
|
|
{
|
|
pattern: STABLE_IDENTIFIER_PATTERN,
|
|
previous: /^[A-Za-z][A-Za-z0-9._:/-]*$/u,
|
|
},
|
|
];
|
|
const samples = [
|
|
"",
|
|
"a",
|
|
"A",
|
|
"_id",
|
|
"1id",
|
|
"é",
|
|
"aé",
|
|
"a/b:c",
|
|
"a-b.c_1",
|
|
"a\n",
|
|
"a\\b",
|
|
];
|
|
for (let code = 0; code < 128; code += 1) {
|
|
const character = String.fromCharCode(code);
|
|
samples.push(character, `A${character}`, `A${character}B`);
|
|
}
|
|
for (const { pattern, previous } of variants) {
|
|
for (const flag of ["u", "v"]) {
|
|
const projected = new RegExp(pattern.source, flag);
|
|
for (const sample of samples)
|
|
expect(projected.test(sample), JSON.stringify({ flag, sample })).toBe(
|
|
previous.test(sample),
|
|
);
|
|
}
|
|
}
|
|
});
|
|
|
|
it("preserves canonical base64 padding and pad-bit validation", () => {
|
|
const previous =
|
|
/^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/][AQgw]==|[A-Za-z0-9+/]{2}[AEIMQUYcgkosw048]=)?$/;
|
|
const samples = [
|
|
"",
|
|
"AA==",
|
|
"AB==",
|
|
"AAA=",
|
|
"AAB=",
|
|
"////",
|
|
"A",
|
|
"AA",
|
|
"AAA",
|
|
"====",
|
|
"AA==\n",
|
|
"AA==\r\n",
|
|
"AA==\u2028",
|
|
"AA==\u2029",
|
|
"AA\nAA",
|
|
"AA=\n=",
|
|
"AA-_",
|
|
"a b c",
|
|
];
|
|
const alphabet =
|
|
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
|
|
for (const first of alphabet)
|
|
for (const second of alphabet)
|
|
samples.push(`${first}${second}==`, `A${first}${second}=`);
|
|
for (const flag of ["u", "v"]) {
|
|
const projected = new RegExp(CANONICAL_BASE64_PATTERN.source, flag);
|
|
for (const sample of samples)
|
|
expect(projected.test(sample), JSON.stringify({ flag, sample })).toBe(
|
|
previous.test(sample),
|
|
);
|
|
}
|
|
});
|
|
|
|
it("validates large canonical base64 under JSON Schema Unicode modes", () => {
|
|
// Near the 32 MiB capture input budget: a quartet expansion alone still
|
|
// overflows at this size, especially in Unicode-set client validators.
|
|
const body = Buffer.alloc(24 * 1024 * 1024 - 3, 0x81);
|
|
const encoded = body.toString("base64");
|
|
for (const flag of ["", "u", "v"]) {
|
|
const pattern = new RegExp(CANONICAL_BASE64_PATTERN.source, flag);
|
|
expect(pattern.test(encoded), flag).toBe(true);
|
|
expect(pattern.test(`${encoded.slice(0, -1)}!`), flag).toBe(false);
|
|
expect(pattern.test(`${encoded.slice(0, -3)}R==`), flag).toBe(false);
|
|
expect(pattern.test(`${encoded}A`), flag).toBe(false);
|
|
const padded = new RegExp(PADDED_BASE64_PATTERN.source, flag);
|
|
expect(padded.test(encoded), flag).toBe(true);
|
|
expect(padded.test(`${encoded.slice(0, -1)}!`), flag).toBe(false);
|
|
}
|
|
});
|