Files
reverse-engineering-anything/src/application/Utf8JsonInput.ts
T
morluto cabd56ea71 refactor(domain): give strict UTF-8 decoding one owner with an explicit BOM policy (#10728)
* 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
2026-11-15 19:54:39 +08:00

108 lines
4.0 KiB
TypeScript

import { strictUtf8Decoder } from "../domain/strictUtf8.js";
import { constants } from "node:buffer";
import { AnalysisResourceConstraintError } from "../domain/analysisErrorCore.js";
import { safeParseJson, type SafeJsonParseResult } from "../domain/safeJson.js";
/** Recovery that preserves complete, authenticated Evidence workflow inputs. */
export const JSON_INPUT_RESOURCE_REMEDIATION =
"Provide a smaller valid JSON value. For Evidence workflows, re-analyze a smaller selection of the original target and use its complete Evidence; splitting JSON text or trimming Evidence fields does not produce valid workflow input.";
/**
* Strict JSON input keeps rejecting a leading byte-order mark, but names it:
* the parser's own message quotes the invisible U+FEFF as the bad token.
*/
export const JSON_BYTE_ORDER_MARK_MESSAGE =
"JSON input begins with a UTF-8 byte-order mark (EF BB BF), which strict JSON input does not accept. Save the file as UTF-8 without a byte-order mark.";
/** Decode JSON bytes without confusing a runtime string limit with malformed input. */
export const parseUtf8Json = (
bytes: Uint8Array,
operation: string,
path: string,
boundary = "json-input",
): SafeJsonParseResult & { readonly userMessage?: string } => {
const stringLimitFailure = (
cause?: unknown,
decodedUnits?: number,
): AnalysisResourceConstraintError =>
new AnalysisResourceConstraintError(
operation,
"memory",
"JSON input exceeds the runtime's maximum decoded string length",
{
boundary,
input_path: path,
input_bytes: bytes.byteLength,
max_string_code_units: constants.MAX_STRING_LENGTH,
...(decodedUnits === undefined
? {}
: { decoded_string_code_units_at_least: decodedUnits }),
},
{
...(cause === undefined ? {} : { cause }),
remediationAction: JSON_INPUT_RESOURCE_REMEDIATION,
},
);
let text: string;
try {
const decoder = strictUtf8Decoder("preserve");
if (bytes.byteLength <= constants.MAX_STRING_LENGTH) {
text = decoder.decode(bytes);
} else {
// Node 22's UTF-8 fast path bounds encoded bytes before decoding. Decode
// large inputs in chunks so valid multibyte text is bounded by its actual
// UTF-16 length. Streaming also preserves characters spanning chunks.
const parts: string[] = [];
let decodedUnits = 0;
const append = (part: string): void => {
decodedUnits += part.length;
if (decodedUnits > constants.MAX_STRING_LENGTH)
throw stringLimitFailure(undefined, decodedUnits);
parts.push(part);
};
const chunkBytes = 1024 * 1024;
for (let offset = 0; offset < bytes.byteLength; offset += chunkBytes)
append(
decoder.decode(bytes.subarray(offset, offset + chunkBytes), {
stream: true,
}),
);
append(decoder.decode());
text = parts.join("");
}
} catch (cause: unknown) {
if (cause instanceof AnalysisResourceConstraintError) throw cause;
const code =
typeof cause === "object" && cause !== null && "code" in cause
? cause.code
: undefined;
if (code === "ERR_STRING_TOO_LONG") throw stringLimitFailure(cause);
if (code !== "ERR_ENCODING_INVALID_ENCODED_DATA") throw cause;
return {
ok: false,
error: "JSON input is not valid UTF-8",
userMessage: "JSON input is not valid UTF-8",
cause,
};
}
if (text.startsWith("\uFEFF"))
return {
ok: false,
error: JSON_BYTE_ORDER_MARK_MESSAGE,
cause: undefined,
userMessage: JSON_BYTE_ORDER_MARK_MESSAGE,
};
const parsed = safeParseJson(text);
// Native syntax errors can quote source snippets containing transport
// credentials. Keep the original exception internal, never in public text.
return parsed.ok
? parsed
: {
ok: false,
error:
"JSON input is not valid JSON. Check syntax in the selected file.",
cause: parsed.cause,
};
};