mirror of
https://github.com/morluto/rea.git
synced 2026-11-22 14:35:45 +00:00
* refactor(domain): give strict UTF-8 decoding one owner with an explicit BOM policy * fix(domain): keep the leading-BOM behaviour every migrated UTF-8 decoder had * refactor(domain): read the domain layer's strict UTF-8 through the BOM-policy owner (#10803) Twelve domain decoders built their own fatal TextDecoder with ignoreBOM: true. They now use strictUtf8Decoder("preserve"), which keeps that behaviour: each reads bytes where a leading U+FEFF is content (binary-format names and fields, JSON and XML read byte-for-byte, recorded bodies, registry seeds whose kept bytes are re-emitted). The counted baseline drops from 74 to 62. * refactor(artifacts): read artifact readers' strict UTF-8 through the BOM-policy owner (#10871) Fourteen artifact reader modules (17 sites) built their own fatal TextDecoder. They now take it from strictUtf8Decoder with the policy each had: every one kept a leading BOM (ignoreBOM: true), so they use "preserve"; JavaScriptArtifactFiles keeps it for JavaScript and HTML entries and strips it otherwise, as before. The strict-utf8-decoder baseline drops those 17 sites. * refactor(domain): drop TextDecoder imports left by the strict UTF-8 migration * refactor(application): read MCP registration metadata through the strict UTF-8 owner * refactor(formats): read binary-format readers' strict UTF-8 through the BOM-policy owner (#10903) * refactor(formats): read binary-format readers' strict UTF-8 through the BOM-policy owner * refactor(formats): drop the model readers' unused TextDecoder imports * refactor(browser): read browser capture and fetch strict UTF-8 through the BOM-policy owner (#10935) * refactor(browser): read browser capture and fetch strict UTF-8 through the BOM-policy owner * refactor(native): read LLDB and Mach-O name strict UTF-8 through the BOM-policy owner (#10936) * refactor(native): read LLDB and Mach-O name strict UTF-8 through the BOM-policy owner * refactor(process): read MCP and NDJSON transport frames' strict UTF-8 through the BOM-policy owner (#10937) * refactor(process): read MCP and NDJSON transport frames' strict UTF-8 through the BOM-policy owner * refactor(application): read JSON and file inputs' strict UTF-8 through the BOM-policy owner (#10938) * refactor(application): read JSON and file inputs' strict UTF-8 through the BOM-policy owner * refactor(providers): read IDA, Electron, Ghidra and reference strict UTF-8 through the BOM-policy owner (#10939) * refactor(providers): read IDA, Electron, Ghidra and reference strict UTF-8 through the BOM-policy owner * refactor(evm): read the hex bytecode carrier's strict UTF-8 through the owner and refuse new local decoders (#10940) * refactor(evm): read the hex bytecode carrier's strict UTF-8 through the BOM-policy owner * chore(architecture): match local strict UTF-8 decoders in any option order
26 lines
861 B
TypeScript
26 lines
861 B
TypeScript
import { expect, it } from "vitest";
|
||
|
||
import {
|
||
decodeStrictUtf8,
|
||
isStrictUtf8,
|
||
strictUtf8Decoder,
|
||
} from "./strictUtf8.js";
|
||
|
||
const bomPrefixed = Uint8Array.of(0xef, 0xbb, 0xbf, 0x7b, 0x7d);
|
||
|
||
it("keeps a leading BOM unless the caller states it is a signature", () => {
|
||
expect(decodeStrictUtf8(bomPrefixed, "preserve")).toBe("{}");
|
||
expect(decodeStrictUtf8(bomPrefixed, "strip-signature")).toBe("{}");
|
||
expect(strictUtf8Decoder("preserve").decode(bomPrefixed)).toBe("{}");
|
||
});
|
||
|
||
it("refuses malformed UTF-8 for every policy", () => {
|
||
const malformed = Uint8Array.of(0x61, 0xc3);
|
||
expect(() => decodeStrictUtf8(malformed, "preserve")).toThrow(TypeError);
|
||
expect(() => decodeStrictUtf8(malformed, "strip-signature")).toThrow(
|
||
TypeError,
|
||
);
|
||
expect(isStrictUtf8(malformed)).toBe(false);
|
||
expect(isStrictUtf8(bomPrefixed)).toBe(true);
|
||
});
|