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
This commit is contained in:
morluto authored and GitHub committed 2026-11-15 19:54:39 +08:00
1 parent abd36dd250
commit cabd56ea71
103 files changed
+322 -251

No files matched your search

+5 -3
View File
@@ -5,6 +5,7 @@ import {
absoluteCallerPath,
appendCallerPath,
} from "../filesystem/callerPath.js";
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
/** An unresolved Hermes profile must not be configured as the default home. */
export class HermesClientPathError extends Error {
@@ -178,9 +179,10 @@ export const resolveHermesClientHome = (
let name: string;
try {
// Python uses utf-8-sig and ignores unreadable / invalid-UTF8 active_profile files.
name = new TextDecoder("utf-8", { fatal: true })
.decode(readFileSync(appendCallerPath(stickyRoot, "active_profile")))
.trim();
name = decodeStrictUtf8(
readFileSync(appendCallerPath(stickyRoot, "active_profile")),
"strip-signature",
).trim();
} catch {
return root;
}
+2 -1
View File
@@ -1,3 +1,4 @@
import { strictUtf8Decoder } from "../domain/strictUtf8.js";
import { constants } from "node:buffer";
import { createHash } from "node:crypto";
import type { Stats } from "node:fs";
@@ -717,7 +718,7 @@ async function* decodedChunks(
observe?: (bytes: Uint8Array) => void,
physicalRead: JsonInputPhysicalReadObservation = {},
): AsyncGenerator<string> {
const decoder = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true });
const decoder = strictUtf8Decoder("preserve");
let leading = true;
const checked = (text: string): string => {
if (leading && text.length > 0) {
+2 -1
View File
@@ -54,6 +54,7 @@ import {
type LinuxPackageFamily,
} from "./HopperReleaseFeed.js";
import { withRegularFile } from "./RegularFileRead.js";
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
/** Metadata/key inspection budget, independent of the compressed package budget. */
const RELEASE_METADATA_BYTES = 1024 * 1024;
@@ -1082,7 +1083,7 @@ export const retryLinuxHopperPublisherCleanup = async (): Promise<void> => {
};
const decodeUtf8 = (bytes: Uint8Array): string =>
new TextDecoder("utf-8", { fatal: true }).decode(bytes);
decodeStrictUtf8(bytes, "strip-signature");
const releaseFailure = (
cause: unknown,
signal: AbortSignal | undefined,
+2 -1
View File
@@ -8,6 +8,7 @@ import {
} from "../domain/analysisErrorCore.js";
import { analysisErrorWithCancellation } from "../domain/analysisErrorCancellation.js";
import { ConfigurationError } from "../domain/configurationErrors.js";
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
import { absoluteCallerPath } from "../filesystem/callerPath.js";
import {
ExecFileOutputCancelledError,
@@ -65,7 +66,7 @@ const gitOutput = async (
throw gitFailure(cause);
}
try {
return new TextDecoder("utf-8", { fatal: true }).decode(observation.stdout);
return decodeStrictUtf8(observation.stdout, "strip-signature");
} catch {
// The failure keeps the exact observation it could not decode.
throw gitFailure(
@@ -26,6 +26,7 @@ import type {
} from "../reference/ReferenceSourceReaderTypes.js";
import { typescriptEmittedSourceCandidates } from "./TypeScriptEmittedSourceCandidates.js";
import { appendAll } from "../domain/appendAll.js";
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
export interface ParsedReferenceSourceEntries {
readonly entries: HistoricalSourceGraphInput["entries"];
@@ -152,7 +153,8 @@ const readPackageMetadata = (
}
try {
const manifest: unknown = JSON.parse(
new TextDecoder("utf-8", { fatal: true }).decode(entry.bytes),
// npm and Node both accept a BOM-signed package.json.
decodeStrictUtf8(entry.bytes, "strip-signature"),
);
if (
typeof manifest !== "object" ||
+2 -3
View File
@@ -1,3 +1,4 @@
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
import type { Stats } from "node:fs";
import type { FileHandle } from "node:fs/promises";
@@ -343,9 +344,7 @@ export const readRegularFileTextSnapshot = (
const decodeFileText = (path: string, bytes: Buffer): string => {
try {
return new TextDecoder("utf-8", { fatal: true, ignoreBOM: true }).decode(
bytes,
);
return decodeStrictUtf8(bytes, "preserve");
} catch (cause: unknown) {
if (!(cause instanceof TypeError)) throw cause;
throw new InvalidUtf8FileError(path, cause);
+2 -1
View File
@@ -1,3 +1,4 @@
import { strictUtf8Decoder } from "../domain/strictUtf8.js";
import { constants } from "node:buffer";
import { AnalysisResourceConstraintError } from "../domain/analysisErrorCore.js";
@@ -45,7 +46,7 @@ export const parseUtf8Json = (
);
let text: string;
try {
const decoder = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true });
const decoder = strictUtf8Decoder("preserve");
if (bytes.byteLength <= constants.MAX_STRING_LENGTH) {
text = decoder.decode(bytes);
} else {
+2 -4
View File
@@ -1,3 +1,4 @@
import { decodeStrictUtf8 } from "../domain/strictUtf8.js";
import { createHash } from "node:crypto";
import { z } from "zod";
@@ -396,10 +397,7 @@ const parseCapture = (
closeFailure?: { readonly cause: unknown },
): Result<ReturnType<typeof selectScriptCapture>, AnalysisError> => {
try {
const text = new TextDecoder("utf-8", {
fatal: true,
ignoreBOM: true,
}).decode(bytes);
const text = decodeStrictUtf8(bytes, "preserve");
const json = safeParseJson(text);
if (!json.ok) throw new TypeError(json.error);
return ok(selectScriptCapture(json.value));
@@ -1,3 +1,4 @@
import { decodeStrictUtf8 } from "../../domain/strictUtf8.js";
import { getHeapStatistics } from "node:v8";
import { version } from "graphql";
import type { ArtifactResourceScope } from "../../artifacts/ArtifactResourceScope.js";
@@ -86,9 +87,7 @@ const decode = (
),
);
try {
return ok(
new TextDecoder("utf-8", { fatal: true, ignoreBOM: true }).decode(bytes),
);
return ok(decodeStrictUtf8(bytes, "preserve"));
} catch (cause) {
if (!(cause instanceof TypeError)) throw cause;
return err(
@@ -1,3 +1,4 @@
import { decodeStrictUtf8 } from "../../domain/strictUtf8.js";
import { createHash, randomUUID } from "node:crypto";
import { constants } from "node:fs";
import {
@@ -737,10 +738,7 @@ const parseJournal = (
const committedBytes = bytes.lastIndexOf(0x0a) + 1;
let committed: string;
try {
committed = new TextDecoder("utf-8", {
fatal: true,
ignoreBOM: true,
}).decode(bytes.subarray(0, committedBytes));
committed = decodeStrictUtf8(bytes.subarray(0, committedBytes), "preserve");
} catch {
return err(incompatibleJournal());
}