mirror of
https://github.com/morluto/rea.git
synced 2026-11-10 17:30:32 -10:00
Compare commits
37
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ac072ba228 | ||
|
|
2885347cde | ||
|
|
a6a2527ade | ||
|
|
f8fc572e4a | ||
|
|
ab9e5fa204 | ||
|
|
8d45cb45c4 | ||
|
|
7712e3185e | ||
|
|
466149169e | ||
|
|
1c2626edbd | ||
|
|
b16d18f198 | ||
|
|
14030e2f11 | ||
|
|
9505c73824 | ||
|
|
1a446cdade | ||
|
|
1ef7f02cae | ||
|
|
7b86474be7 | ||
|
|
5d10337709 | ||
|
|
8eadb872f2 | ||
|
|
f170175ec8 | ||
|
|
fbe09f84df | ||
|
|
ebb480ba22 | ||
|
|
da1f029c2f | ||
|
|
4db9c166ef | ||
|
|
29fd6a7d03 | ||
|
|
d7338876d6 | ||
|
|
9df3f7174f | ||
|
|
79e476204f | ||
|
|
9c95218374 | ||
|
|
d9d2641981 | ||
|
|
e2585aa7ce | ||
|
|
1d1c7f98ff | ||
|
|
b1f1b3eff3 | ||
|
|
c1d0f2bb45 | ||
|
|
04de5f3200 | ||
|
|
12d2cacb0d | ||
|
|
d9344ffe17 | ||
|
|
fff18cc77f | ||
|
|
794260aef0 |
No files matched your search
@@ -25,7 +25,7 @@ jobs:
|
||||
node-version-file: .nvmrc
|
||||
- name: Validate the SDK pin against the provider's verified release
|
||||
run: node scripts/verify-ghidra-bridge-sources.mjs --check-sdk-pin >> "$GITHUB_ENV"
|
||||
# The bridge probe imports only source-owned ARM/Thumb bytes and never
|
||||
# The bridge probe imports only source-owned ARM, Thumb and MIPS bytes and never
|
||||
# executes target code. All SDK/project state stays in runner storage.
|
||||
- name: Acquire checksum-verified Ghidra SDK in isolated runner storage
|
||||
shell: bash
|
||||
@@ -46,7 +46,7 @@ jobs:
|
||||
java_home_variable="JAVA_HOME_${GHIDRA_JAVA_MAJOR}_X64"
|
||||
test -n "${!java_home_variable}"
|
||||
JAVA_HOME="${!java_home_variable}" npm run verify:ghidra:bridge-sources -- --verified-sdk
|
||||
- name: Inspect real ARM and Thumb instruction context through the bridge
|
||||
- name: Inspect real ARM, Thumb and MIPS instruction context through the bridge
|
||||
shell: bash
|
||||
run: |
|
||||
java_home_variable="JAVA_HOME_${GHIDRA_JAVA_MAJOR}_X64"
|
||||
@@ -58,10 +58,21 @@ jobs:
|
||||
-import "${probe_root}/arm-thumb.bin" -loader BinaryLoader -processor ARM:LE:32:v7 \
|
||||
-noanalysis -readOnly -deleteProject \
|
||||
-scriptPath "${GITHUB_WORKSPACE}/tests/conformance/ghidra;${GITHUB_WORKSPACE}/bridge/ghidra" \
|
||||
-postScript ReaArmContextProbe.java "${GITHUB_WORKSPACE}/bridge/ghidra" \
|
||||
-postScript ReaInstructionContextProbe.java "${GITHUB_WORKSPACE}/bridge/ghidra" \
|
||||
> "${probe_root}/output.log" 2>&1 || { cat "${probe_root}/output.log"; exit 1; }
|
||||
cat "${probe_root}/output.log"
|
||||
grep -F 'REA_ARM_CONTEXT_OK arm=0 thumb=1 unavailable=null (injected provider value)' "${probe_root}/output.log"
|
||||
mkdir -p "${probe_root}/mips-project"
|
||||
# MIPS32 addiu v0,a0,3; MIPS16 li v0,90. These bytes are never executed.
|
||||
printf '\003\000\202\044\132\152\000\000' > "${probe_root}/mips.bin"
|
||||
timeout 180s "${GHIDRA_INSTALL_DIR}/support/analyzeHeadless" "${probe_root}/mips-project" MipsContext \
|
||||
-import "${probe_root}/mips.bin" -loader BinaryLoader -processor MIPS:LE:32:default \
|
||||
-noanalysis -readOnly -deleteProject \
|
||||
-scriptPath "${GITHUB_WORKSPACE}/tests/conformance/ghidra;${GITHUB_WORKSPACE}/bridge/ghidra" \
|
||||
-postScript ReaInstructionContextProbe.java "${GITHUB_WORKSPACE}/bridge/ghidra" mips \
|
||||
> "${probe_root}/mips-output.log" 2>&1 || { cat "${probe_root}/mips-output.log"; exit 1; }
|
||||
cat "${probe_root}/mips-output.log"
|
||||
grep -F 'REA_MIPS_CONTEXT_OK standard=0 mips16=1' "${probe_root}/mips-output.log"
|
||||
# Each probe imports source-owned bytes at 0x1000, away from the Cortex-M
|
||||
# vector symbols that ARMCortex.pspec defines at 0, and decodes them from
|
||||
# the language's default context, so M-profile Thumb state must hold at
|
||||
|
||||
@@ -1031,6 +1031,11 @@ complete observation.
|
||||
arm64e formats;
|
||||
- legacy `LC_DYLD_INFO` rebase and bind opcodes.
|
||||
|
||||
Text relocation records retain their import identity without claiming a
|
||||
pointer value. Bind types are explicit: a non-lazy binding with no declared
|
||||
type is invalid. Reads that overlap only part of an encoded chained-fixup word remain
|
||||
unresolved rather than treating those stored bytes as an ordinary pointer.
|
||||
|
||||
[dyld symbol names are byte strings](https://github.com/apple-oss-distributions/dyld/blob/dyld-1330/mach_o/BindOpcodes.cpp#L203-L208),
|
||||
compared with [`strcmp`](https://github.com/apple-oss-distributions/dyld/blob/dyld-1330/mach_o/BindOpcodes.cpp#L42-L56).
|
||||
Dependent library install names likewise originate as
|
||||
|
||||
@@ -26,6 +26,7 @@ for new work, roadmap granularity and producer-owned contracts.
|
||||
- [Native call source coordinates](native/call-source-locations/spec.md) ([plan](native/call-source-locations/plan.md), [tasks](native/call-source-locations/tasks.md), [verification](native/call-source-locations/verification.md))
|
||||
- [Go static string-header literal recovery](native/go-string-literals/spec.md) ([plan](native/go-string-literals/plan.md), [tasks](native/go-string-literals/tasks.md))
|
||||
- [Windows Shell Link shortcut inspection](native/windows-shortcut/spec.md) ([plan](native/windows-shortcut/plan.md), [tasks](native/windows-shortcut/tasks.md))
|
||||
- [NTFS $MFT and USN Journal inspection](native/ntfs-mft/spec.md) ([plan](native/ntfs-mft/plan.md), [tasks](native/ntfs-mft/tasks.md))
|
||||
- [Solidity terminal metadata inspection](solidity/cbor-metadata/spec.md) ([plan](solidity/cbor-metadata/plan.md), [tasks](solidity/cbor-metadata/tasks.md), [verification](solidity/cbor-metadata/verification.md))
|
||||
- [Inspect a V8 code cache container](v8/code-cache-inspection/spec.md) ([plan](v8/code-cache-inspection/plan.md), [tasks](v8/code-cache-inspection/tasks.md))
|
||||
- [Deno compile executable inventory and extraction](artifacts/deno-standalone/spec.md) ([plan](artifacts/deno-standalone/plan.md), [tasks](artifacts/deno-standalone/tasks.md))
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
# Implementation plan
|
||||
|
||||
## Boundary and contract
|
||||
|
||||
Follow the existing artifact readers. `src/domain/windows/ntfsMft.ts` owns FILE
|
||||
record bytes and coverage; `src/domain/artifactFormatMetadata.ts` owns the
|
||||
`ntfs-mft` result schema. `NtfsMftArtifactReader` reads the admitted file
|
||||
through `ArtifactFileSource` and exposes its facts through `formatMetadata()`.
|
||||
A record stream is its own content, so the root occurrence carries every fact
|
||||
and no members are enumerated.
|
||||
|
||||
Recognition lives in `hasMftFileRecordSignature` and is applied in
|
||||
`classifyArtifactBytes`, next to the other unambiguous magic probes.
|
||||
|
||||
## Incremental work and validation
|
||||
|
||||
1. Define the first-step contract, limits and observations; add parser fixtures.
|
||||
2. Implement the FILE record header and update-sequence fixup parse with
|
||||
explicit limitations.
|
||||
3. Add the reader, format descriptor and byte classification.
|
||||
4. Decode attribute records, then `$FILE_NAME` attributes so a record's parent
|
||||
reference, names and timestamps become explicit; keep hard links separate.
|
||||
5. Parse `$UsnJrnl:$J` records and correlate them to records by full file
|
||||
reference, including sequence numbers, reporting unresolved references.
|
||||
6. Document the workflow in a native Windows artifact guide.
|
||||
|
||||
## Effects and compatibility
|
||||
|
||||
The workflow reads one caller-selected local file. It adds no target execution,
|
||||
injection, mutation, protection recovery, network access, volume mount or live
|
||||
filesystem access, so no maintainer scope decision is required.
|
||||
`inspect_artifact` routing for every existing format is unchanged, and the new
|
||||
format id appears only for bytes whose first record carries the `FILE`
|
||||
signature.
|
||||
|
||||
## References
|
||||
|
||||
- https://learn.microsoft.com/en-us/windows/win32/fileio/master-file-table
|
||||
- https://github.com/libyal/libfsntfs/blob/main/documentation/New%20Technologies%20File%20System%20(NTFS).asciidoc
|
||||
@@ -0,0 +1,51 @@
|
||||
# NTFS $MFT and USN Journal inspection
|
||||
|
||||
This specification records an implementation increment and its original problem
|
||||
statement. For current behavior and limitations, see the artifact inventory
|
||||
guide.
|
||||
|
||||
## Problem and outcome
|
||||
|
||||
REA has no reader for acquired NTFS metadata artifacts. An analyst holding a
|
||||
captured `$MFT` stream cannot ask which FILE records it contains, whether their
|
||||
update-sequence fixups survived acquisition, or which records are directories,
|
||||
extensions of another record, or no longer in use. Add offline, read-only
|
||||
inventory of a selected `$MFT` file, delivered in steps so each one merges on
|
||||
its own.
|
||||
|
||||
## Requirements
|
||||
|
||||
- Recognize a `$MFT` stream by a plausible first `FILE` record header under
|
||||
any file name. CLI and MCP target admission route it to the artifact reader.
|
||||
- Validate each FILE record header: the `FILE` signature, sequence number, flags,
|
||||
used and total byte counts, base record reference, and the update-sequence
|
||||
array's offset, count and array bounds.
|
||||
- Verify the update-sequence fixups: every sector trailer the array covers must
|
||||
hold the array's sequence number. A mismatch keeps the record's header facts
|
||||
and is reported per record and in the metadata count.
|
||||
- Report a missing, misplaced or short update-sequence array as unverified
|
||||
rather than as a clean record, and a trailing partial record as a byte count.
|
||||
- Report the first invalid record signature and the number of invalid slots.
|
||||
Continue at the next slot when the stream declared a supported record size.
|
||||
With a fallback record size, stop at the first invalid signature.
|
||||
- Bound the whole file at a fixed 512 MiB ceiling and report the ceiling as a
|
||||
`limit` failure with its boundary.
|
||||
- Return the first 32 decoded record headers with their source offsets and the
|
||||
number of omitted headers. Aggregate counts cover the full parsed stream.
|
||||
- Parse only the records' headers and fixups. Attributes, filenames, data
|
||||
streams and the `$UsnJrnl:$J` journal are not decoded in this step, so no path,
|
||||
file size, file reference correlation or change history is claimed.
|
||||
|
||||
## Acceptance
|
||||
|
||||
Synthesized fixtures cover a clean record, a failed fixup, a missing update
|
||||
sequence array, an array shorter than the record's sector count, extension and
|
||||
directory records, a record whose signature is wrong mid-stream, a trailing
|
||||
partial record, an undeclared record size, a 4 KiB record, a stream shorter than
|
||||
one header, bytes without the `FILE` signature, and the file-size ceiling.
|
||||
Inventory tests cover the root occurrence's metadata and the coverage status
|
||||
when a fixup fails, and classification tests cover several file names for the
|
||||
same bytes.
|
||||
|
||||
Not covered in this step: real `$MFT` files written by a Windows host, USN
|
||||
journal records, attribute decoding, and any correlation between the two.
|
||||
@@ -0,0 +1,11 @@
|
||||
# Tasks
|
||||
|
||||
- [x] Define the first-step scope, contract and limits.
|
||||
- [x] Parse FILE record headers and update-sequence fixups with synthesized
|
||||
fixtures and explicit limitations.
|
||||
- [x] Add the reader, format descriptor and byte classification.
|
||||
- [ ] Decode attribute records, then `$FILE_NAME` attributes with parent
|
||||
references, names, hard links and timestamps.
|
||||
- [ ] Parse `$UsnJrnl:$J` records and correlate them to records by full file
|
||||
reference.
|
||||
- [ ] Verify against real `$MFT` and journal captures from a Windows host.
|
||||
@@ -636,7 +636,7 @@ const PATH_SCOPES = {
|
||||
"src/ghidra/GhidraJavaProperties.ts",
|
||||
"src/ghidra/GhidraReleasePolicy.ts",
|
||||
"scripts/verify-ghidra-bridge-sources.mjs",
|
||||
"tests/conformance/ghidra/ReaArmContextProbe.java",
|
||||
"tests/conformance/ghidra/ReaInstructionContextProbe.java",
|
||||
"tests/conformance/ghidra/ReaComputedCallCoverageProbe.java",
|
||||
"tests/conformance/ghidra/ReaDecodeProbe.java",
|
||||
".github/workflows/ghidra-bridge-sources.yml",
|
||||
|
||||
@@ -50,7 +50,7 @@ transport.stderr?.on("data", (bytes) => {
|
||||
const ajv = new Ajv2020({ strict: false, validateFormats: false });
|
||||
const measurements = [];
|
||||
const contract = toolContract("inspect_web_network_capture");
|
||||
await withVerifierCleanup(async () => {
|
||||
const report = await withVerifierCleanup(async () => {
|
||||
try {
|
||||
await client.connect(transport);
|
||||
} catch (cause) {
|
||||
@@ -196,7 +196,7 @@ await withVerifierCleanup(async () => {
|
||||
});
|
||||
}
|
||||
await client.ping();
|
||||
const report = {
|
||||
return {
|
||||
status: "passed",
|
||||
profile: "aioquic-1.5.0-json-0.3",
|
||||
measurements,
|
||||
@@ -206,17 +206,6 @@ await withVerifierCleanup(async () => {
|
||||
"No PCAP or keylog is read by this verifier; repeated STREAM coverage is not proof of retransmission or network loss.",
|
||||
],
|
||||
};
|
||||
await writeFile(reportPath, JSON.stringify(report, null, 2) + "\n", {
|
||||
flag: "wx",
|
||||
mode: 0o600,
|
||||
});
|
||||
console.log(
|
||||
JSON.stringify({
|
||||
status: report.status,
|
||||
cases: measurements.length,
|
||||
report: reportPath,
|
||||
}),
|
||||
);
|
||||
}, [
|
||||
async () => {
|
||||
await closeVerifierResources([
|
||||
@@ -225,3 +214,15 @@ await withVerifierCleanup(async () => {
|
||||
]);
|
||||
},
|
||||
]);
|
||||
|
||||
await writeFile(reportPath, JSON.stringify(report, null, 2) + "\n", {
|
||||
flag: "wx",
|
||||
mode: 0o600,
|
||||
});
|
||||
console.log(
|
||||
JSON.stringify({
|
||||
status: report.status,
|
||||
cases: measurements.length,
|
||||
report: reportPath,
|
||||
}),
|
||||
);
|
||||
@@ -97,6 +97,7 @@ import {
|
||||
isDfuSeFile,
|
||||
} from "../domain/firmware/dfuse.js";
|
||||
import { hasFitImagesNode } from "../domain/firmware/fitImage.js";
|
||||
import { hasMftFileRecordHeader } from "../domain/windows/ntfsMft.js";
|
||||
import {
|
||||
locateEspFlashLayout,
|
||||
type EspFlashSelection,
|
||||
@@ -816,6 +817,7 @@ const detectArtifactFormat = async (
|
||||
});
|
||||
if (esp === "esp-image") return "esp-image";
|
||||
if (hasFitImagesNode(magic)) return "fit";
|
||||
if (hasMftFileRecordHeader(magic)) return "ntfs-mft";
|
||||
// Binary plists, including keyed archives, often use other extensions.
|
||||
if (hasBinaryPlistSignature(magic)) return "plist";
|
||||
const named = namedArtifactFormat(lower);
|
||||
@@ -899,6 +901,7 @@ const isArchiveFormat = (
|
||||
"dfuse",
|
||||
"esp-flash-image",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
].includes(format);
|
||||
|
||||
/** Whether the leading bytes begin any executable header family, valid or not. */
|
||||
|
||||
@@ -135,6 +135,7 @@ const TARGETS: TargetFixtures = {
|
||||
espFlash: { selected: true, flashOffset: null, partitionTableOffset: null },
|
||||
},
|
||||
fit: { ...archive, format: "fit" },
|
||||
"ntfs-mft": { ...archive, format: "ntfs-mft" },
|
||||
plist: { ...artifact, format: "plist" },
|
||||
javascript: { ...artifact, format: "javascript" },
|
||||
"source-map": { ...artifact, format: "source-map" },
|
||||
|
||||
@@ -215,6 +215,7 @@ export interface ArtifactReader {
|
||||
| "dfuse"
|
||||
| "esp-flash-image"
|
||||
| "fit"
|
||||
| "ntfs-mft"
|
||||
| "file";
|
||||
entries(
|
||||
signal?: AbortSignal,
|
||||
|
||||
@@ -18,7 +18,10 @@ import {
|
||||
type ArtifactTraversalOptions,
|
||||
} from "./ArtifactReader.js";
|
||||
import { ArtifactResourceScope } from "./ArtifactResourceScope.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { readFileHandleChunks } from "../filesystem/readFileHandleChunks.js";
|
||||
import type { StableRegularFileDescriptor } from "../filesystem/RegularFile.js";
|
||||
@@ -64,12 +67,14 @@ export const regionFileName = (start: number, end: number): string =>
|
||||
*/
|
||||
export class DecodedRegionArtifactReader<Image> implements ArtifactReader {
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
readonly #entries = new Map<string, ArtifactEntry>();
|
||||
readonly #regions = new Map<string, Uint8Array>();
|
||||
#entries = new Map<string, ArtifactEntry>();
|
||||
#regions = new Map<string, Uint8Array>();
|
||||
readonly #streams = new Set<Readable>();
|
||||
readonly #source: ArtifactFileSource;
|
||||
readonly #decoding: RegionDecoding<Image>;
|
||||
#prepared: Promise<void> | undefined;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
/** Whole-file facts only; the region map is the sole owner of region bytes. */
|
||||
#described: Omit<DecodedRegions, "regions"> | undefined;
|
||||
#closing = false;
|
||||
@@ -110,8 +115,27 @@ export class DecodedRegionArtifactReader<Image> implements ArtifactReader {
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
this.#prepared ??= this.#prepare(signal);
|
||||
await this.#prepared;
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
const coverage = this.#described?.coverage;
|
||||
@@ -230,6 +254,8 @@ export class DecodedRegionArtifactReader<Image> implements ArtifactReader {
|
||||
|
||||
async #prepare(signal?: AbortSignal): Promise<void> {
|
||||
const described = this.#decoding.describe(await this.#decode(signal));
|
||||
const entries = new Map<string, ArtifactEntry>();
|
||||
const regions = new Map<string, Uint8Array>();
|
||||
let index = 0;
|
||||
for (const region of described.regions) {
|
||||
if (index % 256 === 0) await setImmediate();
|
||||
@@ -248,13 +274,16 @@ export class DecodedRegionArtifactReader<Image> implements ArtifactReader {
|
||||
adapterKey: `${this.#decoding.keyPrefix}:${String(index)}`,
|
||||
formatMetadata: region.formatMetadata,
|
||||
} satisfies ArtifactEntry;
|
||||
this.#entries.set(entry.adapterKey, entry);
|
||||
this.#regions.set(entry.adapterKey, region.bytes);
|
||||
entries.set(entry.adapterKey, entry);
|
||||
regions.set(entry.adapterKey, region.bytes);
|
||||
index += 1;
|
||||
}
|
||||
const { regions: _regions, ...facts } = described;
|
||||
this.#described = facts;
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#entries = entries;
|
||||
this.#regions = regions;
|
||||
this.#described = facts;
|
||||
}
|
||||
|
||||
async #decode(signal?: AbortSignal): Promise<Image> {
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { artifactPreparationRecoveryCases } from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import { getEventListeners, once } from "node:events";
|
||||
import { readFile, truncate, writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
@@ -404,6 +405,38 @@ it("keeps the cancellation reason before admission", async () => {
|
||||
}
|
||||
});
|
||||
|
||||
it("does not publish FIT entries when final source verification fails", async () => {
|
||||
const path = await writeFit("partial-publication.itb", FIT_EMBEDDED);
|
||||
const control = new FitArtifactReader(path);
|
||||
const reader = new FitArtifactReader(path);
|
||||
const expected = await firstEntry(control);
|
||||
const nativeRead = ArtifactFileSource.prototype.read;
|
||||
const physical = Object.assign(
|
||||
new Error("final source verification failed"),
|
||||
{ code: "EIO" },
|
||||
);
|
||||
let calls = 0;
|
||||
const read = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementation(function (this: ArtifactFileSource, ...args) {
|
||||
calls += 1;
|
||||
if (calls === 4) return Promise.reject(physical);
|
||||
return nativeRead.apply(this, args);
|
||||
});
|
||||
try {
|
||||
await expect(firstEntry(reader)).rejects.toBe(physical);
|
||||
await expect(reader.open(expected)).rejects.toMatchObject({
|
||||
reason: "integrity",
|
||||
});
|
||||
read.mockRestore();
|
||||
expect((await firstEntry(reader)).path).toBe(expected.path);
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await control.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("keeps the cancellation reason during hash verification", async () => {
|
||||
const reader = new FitArtifactReader(
|
||||
await writeFit("hashing.itb", LARGE_FIT),
|
||||
@@ -430,6 +463,8 @@ it("keeps the cancellation reason during hash verification", async () => {
|
||||
reader.entries(controller.signal)[Symbol.asyncIterator]().next(),
|
||||
).rejects.toMatchObject({ reason: "cancelled", cause: reason });
|
||||
expect(observer).toHaveBeenCalledWith("sha256");
|
||||
observer.mockRestore();
|
||||
expect((await firstEntry(reader)).kind).toBe("file");
|
||||
} finally {
|
||||
observer.mockRestore();
|
||||
await reader.close();
|
||||
@@ -569,3 +604,8 @@ it("preserves a final validation failure when cancellation overlaps it", async (
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
|
||||
artifactPreparationRecoveryCases({
|
||||
image: () => FIT_EMBEDDED,
|
||||
createReader: (path, admitted) => new FitArtifactReader(path, admitted),
|
||||
});
|
||||
@@ -13,7 +13,10 @@ import {
|
||||
type ArtifactTraversalOptions,
|
||||
} from "./ArtifactReader.js";
|
||||
import { ArtifactResourceScope } from "./ArtifactResourceScope.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import {
|
||||
createFitDigest,
|
||||
@@ -30,11 +33,13 @@ const FDT_HEADER_BYTES = 40;
|
||||
export class FitArtifactReader implements ArtifactReader {
|
||||
readonly format = "fit" as const;
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
readonly #entries = new Map<string, ArtifactEntry>();
|
||||
#entries = new Map<string, ArtifactEntry>();
|
||||
readonly #streams = new Set<Readable>();
|
||||
readonly #path: string;
|
||||
readonly #source: ArtifactFileSource;
|
||||
#prepared: Promise<void> | undefined;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
#metadata: FitMetadata | undefined;
|
||||
#coverage: ArtifactReaderTraversal | undefined;
|
||||
#closing = false;
|
||||
@@ -66,8 +71,27 @@ export class FitArtifactReader implements ArtifactReader {
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
this.#prepared ??= this.#prepare(signal);
|
||||
await this.#prepared;
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
if (this.#coverage !== undefined)
|
||||
@@ -207,6 +231,7 @@ export class FitArtifactReader implements ArtifactReader {
|
||||
this.#path,
|
||||
initial.size,
|
||||
);
|
||||
const entries = new Map<string, ArtifactEntry>();
|
||||
let index = 0;
|
||||
for (const image of structure.images) {
|
||||
if (index % 256 === 0) await setImmediate();
|
||||
@@ -228,15 +253,17 @@ export class FitArtifactReader implements ArtifactReader {
|
||||
adapterKey: `fit:${String(image.index)}`,
|
||||
formatMetadata: image.metadata,
|
||||
} satisfies ArtifactEntry;
|
||||
this.#entries.set(entry.adapterKey, entry);
|
||||
entries.set(entry.adapterKey, entry);
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#entries = entries;
|
||||
this.#metadata = structure.metadata;
|
||||
if (structure.limitations.length > 0)
|
||||
this.#coverage = {
|
||||
status: "complete",
|
||||
limitations: structure.limitations,
|
||||
};
|
||||
await this.#source.read(signal);
|
||||
}
|
||||
|
||||
/** One streamed pass per image feeds every supported digest. */
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
import { artifactPreparationRecoveryCases } from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { openRegularFile } from "../filesystem/RegularFile.js";
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
@@ -159,6 +162,72 @@ it("settles an active region stream when closed", async () => {
|
||||
}
|
||||
});
|
||||
|
||||
it("retries decoded-region preparation cancelled while reading", async () => {
|
||||
const path = await writeImage("retry.hex", INTEL_HEX_I32_GAP);
|
||||
const admitted = await openRegularFile(path, { symlinks: "reject" });
|
||||
const reader = new HexRecordArtifactReader(path, "intel-hex", admitted);
|
||||
const controller = new AbortController();
|
||||
const reason = { stage: "decoded region read" };
|
||||
const nativeRead = admitted.handle.read.bind(admitted.handle);
|
||||
const read = vi.spyOn(admitted.handle, "read").mockImplementation((async (
|
||||
...args: unknown[]
|
||||
) => {
|
||||
const result = await Reflect.apply(nativeRead, admitted.handle, args);
|
||||
controller.abort(reason);
|
||||
return result;
|
||||
}) as typeof admitted.handle.read);
|
||||
try {
|
||||
await expect(
|
||||
reader.entries(controller.signal)[Symbol.asyncIterator]().next(),
|
||||
).rejects.toMatchObject({ reason: "cancelled", cause: reason });
|
||||
read.mockRestore();
|
||||
expect(
|
||||
(await reader.entries()[Symbol.asyncIterator]().next()).value,
|
||||
).toMatchObject({ kind: "file" });
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await admitted.handle.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("does not publish decoded regions when final source verification fails", async () => {
|
||||
const path = await writeImage("partial.hex", INTEL_HEX_I32_GAP);
|
||||
const control = new HexRecordArtifactReader(path, "intel-hex");
|
||||
const reader = new HexRecordArtifactReader(path, "intel-hex");
|
||||
const expected = (await control.entries()[Symbol.asyncIterator]().next())
|
||||
.value!;
|
||||
const nativeRead = ArtifactFileSource.prototype.read;
|
||||
const physical = Object.assign(
|
||||
new Error("final source verification failed"),
|
||||
{ code: "EIO" },
|
||||
);
|
||||
let calls = 0;
|
||||
const read = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementation(function (this: ArtifactFileSource, ...args) {
|
||||
calls += 1;
|
||||
if (calls === 2) return Promise.reject(physical);
|
||||
return nativeRead.apply(this, args);
|
||||
});
|
||||
try {
|
||||
await expect(reader.entries()[Symbol.asyncIterator]().next()).rejects.toBe(
|
||||
physical,
|
||||
);
|
||||
await expect(reader.open(expected)).rejects.toMatchObject({
|
||||
reason: "integrity",
|
||||
});
|
||||
read.mockRestore();
|
||||
expect(
|
||||
(await reader.entries()[Symbol.asyncIterator]().next()).value,
|
||||
).toMatchObject({ path: expected.path });
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await control.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("honors cancellation before admitting a file with the exact reason", async () => {
|
||||
const reader = new HexRecordArtifactReader(
|
||||
await writeImage("cancel.hex", INTEL_HEX_I32_GAP),
|
||||
@@ -337,3 +406,9 @@ it("bounds copied region chunks and isolates cached bytes across opens", async (
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
|
||||
artifactPreparationRecoveryCases({
|
||||
image: () => Buffer.from(INTEL_HEX_I32_GAP),
|
||||
createReader: (path, admitted) =>
|
||||
new HexRecordArtifactReader(path, "intel-hex", admitted),
|
||||
});
|
||||
@@ -0,0 +1,211 @@
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { expect, it, vi } from "vitest";
|
||||
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import { NtfsMftArtifactReader } from "./NtfsMftArtifactReader.js";
|
||||
|
||||
import { MFT_DEFAULT_RECORD_BYTES } from "../domain/windows/ntfsMft.js";
|
||||
import { createTestTempDirectory } from "../../tests/fixtures/temporaryDirectory.js";
|
||||
import { scanCanonicalArtifactInventory } from "../../tests/fixtures/artifactInventory.js";
|
||||
|
||||
/** A 1 KiB FILE record whose update sequence array covers both sectors. */
|
||||
const recordBytes = (options: {
|
||||
readonly sequenceNumber?: number;
|
||||
readonly flags?: number;
|
||||
readonly index?: number;
|
||||
}): Buffer => {
|
||||
const record = Buffer.alloc(MFT_DEFAULT_RECORD_BYTES);
|
||||
record.write("FILE", 0, "latin1");
|
||||
const sequenceNumber = options.sequenceNumber ?? 1;
|
||||
record.writeUInt16LE(48, 4);
|
||||
record.writeUInt16LE(3, 6);
|
||||
record.writeUInt16LE(sequenceNumber, 48);
|
||||
record.writeUInt16LE(0xa5a5, 50);
|
||||
record.writeUInt16LE(0xa5a5, 52);
|
||||
record.writeUInt16LE(sequenceNumber, 16);
|
||||
record.writeUInt16LE(1, 18);
|
||||
record.writeUInt32LE(options.index ?? 0, 44);
|
||||
record.writeUInt16LE(56, 20);
|
||||
record.writeUInt16LE(options.flags ?? 0x0001, 22);
|
||||
record.writeUInt32LE(64, 24);
|
||||
record.writeUInt32LE(0xffff_ffff, 56);
|
||||
record.writeUInt32LE(MFT_DEFAULT_RECORD_BYTES, 28);
|
||||
record.writeUInt16LE(sequenceNumber, 510);
|
||||
record.writeUInt16LE(sequenceNumber, 1022);
|
||||
return record;
|
||||
};
|
||||
|
||||
const writeMft = async (name: string, bytes: Buffer): Promise<string> => {
|
||||
const directory = await createTestTempDirectory("rea-ntfs-mft-");
|
||||
const path = join(directory, name);
|
||||
await writeFile(path, bytes);
|
||||
return path;
|
||||
};
|
||||
|
||||
it("reports a $MFT stream's record headers as the root occurrence", async () => {
|
||||
const inventory = await scanCanonicalArtifactInventory(
|
||||
await writeMft(
|
||||
"$MFT",
|
||||
Buffer.concat([
|
||||
recordBytes({}),
|
||||
recordBytes({ flags: 0x0003, index: 1 }),
|
||||
]),
|
||||
),
|
||||
);
|
||||
expect(inventory.manifest.root_format).toBe("ntfs-mft");
|
||||
expect(inventory.coverage.status).toBe("complete");
|
||||
// A record stream declares no members, so the root is its whole inventory.
|
||||
expect(inventory.occurrences.map((row) => row.logical_path)).toEqual(["."]);
|
||||
expect(inventory.occurrences[0]).toMatchObject({
|
||||
artifact_format: "ntfs-mft",
|
||||
format_metadata: {
|
||||
kind: "ntfs-mft",
|
||||
record_bytes: MFT_DEFAULT_RECORD_BYTES,
|
||||
record_count: 2,
|
||||
in_use_record_count: 2,
|
||||
directory_record_count: 1,
|
||||
extension_record_count: 0,
|
||||
fixup_mismatch_count: 0,
|
||||
fixup_unverified_record_count: 0,
|
||||
truncated_tail_bytes: 0,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("names a failed fixup in the coverage limitations", async () => {
|
||||
const record = recordBytes({ sequenceNumber: 4 });
|
||||
// A trailer that is not the sequence number marks the sector as not cleanly written.
|
||||
record.writeUInt16LE(0x1234, 510);
|
||||
const inventory = await scanCanonicalArtifactInventory(
|
||||
await writeMft("$MFT", record),
|
||||
);
|
||||
expect(inventory.manifest.root_format).toBe("ntfs-mft");
|
||||
expect(inventory.coverage.status).toBe("unknown");
|
||||
expect(inventory.limitations).toContainEqual(
|
||||
expect.stringMatching(/sector trailer that is not the update sequence/u),
|
||||
);
|
||||
});
|
||||
|
||||
it("reports an unaligned used-byte count as incomplete coverage", async () => {
|
||||
const record = recordBytes({});
|
||||
record.writeUInt32LE(57, 24);
|
||||
const inventory = await scanCanonicalArtifactInventory(
|
||||
await writeMft("$MFT", record),
|
||||
);
|
||||
expect(inventory.coverage.status).toBe("unknown");
|
||||
expect(inventory.occurrences[0]?.format_metadata).toMatchObject({
|
||||
record_headers: [{ usedBytes: 57, extentValid: false }],
|
||||
});
|
||||
});
|
||||
|
||||
it("reports incomplete coverage when FILE extents contradict the record slots", async () => {
|
||||
const usedTooLarge = recordBytes({});
|
||||
usedTooLarge.writeUInt32LE(4096, 24);
|
||||
const totalTooSmall = recordBytes({});
|
||||
totalTooSmall.writeUInt32LE(512, 28);
|
||||
|
||||
const inventory = await scanCanonicalArtifactInventory(
|
||||
await writeMft("$MFT", Buffer.concat([usedTooLarge, totalTooSmall])),
|
||||
);
|
||||
expect(inventory.coverage.status).toBe("unknown");
|
||||
expect(inventory.limitations).toContainEqual(
|
||||
"2 FILE record(s) declare inconsistent record extents, beginning at offset 0",
|
||||
);
|
||||
expect(inventory.occurrences[0]?.format_metadata).toMatchObject({
|
||||
record_count: 2,
|
||||
fixup_mismatch_count: 0,
|
||||
fixup_unverified_record_count: 0,
|
||||
});
|
||||
});
|
||||
|
||||
it("retries after final source verification fails without publishing its metadata", async () => {
|
||||
const reader = new NtfsMftArtifactReader(
|
||||
await writeMft("$MFT", recordBytes({})),
|
||||
);
|
||||
const read = ArtifactFileSource.prototype.read;
|
||||
const spy = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementationOnce(function (this: ArtifactFileSource, signal) {
|
||||
return read.call(this, signal);
|
||||
})
|
||||
.mockRejectedValueOnce(new Error("final source verification failed"));
|
||||
try {
|
||||
await expect(
|
||||
reader.entries()[Symbol.asyncIterator]().next(),
|
||||
).rejects.toThrow("final source verification failed");
|
||||
expect(reader.formatMetadata()).toBeUndefined();
|
||||
await expect(
|
||||
reader.entries()[Symbol.asyncIterator]().next(),
|
||||
).resolves.toMatchObject({
|
||||
done: true,
|
||||
});
|
||||
expect(reader.formatMetadata()).toMatchObject({
|
||||
kind: "ntfs-mft",
|
||||
record_count: 1,
|
||||
});
|
||||
} finally {
|
||||
spy.mockRestore();
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("retries a shared preparation cancelled by another traversal", async () => {
|
||||
const reader = new NtfsMftArtifactReader(
|
||||
await writeMft("$MFT", recordBytes({})),
|
||||
);
|
||||
const controller = new AbortController();
|
||||
let entered: () => void = () => {};
|
||||
const started = new Promise<void>((resolve) => {
|
||||
entered = resolve;
|
||||
});
|
||||
const read = ArtifactFileSource.prototype.read;
|
||||
const spy = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementationOnce(async function (this: ArtifactFileSource, signal) {
|
||||
entered();
|
||||
await new Promise<void>((resolve) => {
|
||||
signal?.addEventListener("abort", () => resolve(), { once: true });
|
||||
});
|
||||
assertArtifactReadActive(signal);
|
||||
return read.call(this, signal);
|
||||
});
|
||||
try {
|
||||
const cancelled = reader
|
||||
.entries(controller.signal)
|
||||
[Symbol.asyncIterator]()
|
||||
.next();
|
||||
const cancelledResult = expect(cancelled).rejects.toMatchObject({
|
||||
reason: "cancelled",
|
||||
});
|
||||
await started;
|
||||
const other = reader.entries()[Symbol.asyncIterator]().next();
|
||||
controller.abort("cancelled first traversal");
|
||||
await cancelledResult;
|
||||
await expect(other).resolves.toMatchObject({ done: true });
|
||||
expect(reader.formatMetadata()).toMatchObject({ record_count: 1 });
|
||||
} finally {
|
||||
controller.abort();
|
||||
spy.mockRestore();
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("revalidates the source before reusing a completed header inventory", async () => {
|
||||
const path = await writeMft("$MFT", recordBytes({}));
|
||||
const reader = new NtfsMftArtifactReader(path);
|
||||
try {
|
||||
await reader.entries()[Symbol.asyncIterator]().next();
|
||||
await writeFile(
|
||||
path,
|
||||
Buffer.concat([recordBytes({}), recordBytes({ index: 1 })]),
|
||||
);
|
||||
await expect(
|
||||
reader.entries()[Symbol.asyncIterator]().next(),
|
||||
).rejects.toMatchObject({ reason: "integrity" });
|
||||
} finally {
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
@@ -0,0 +1,174 @@
|
||||
import type { Readable } from "node:stream";
|
||||
|
||||
import {
|
||||
ntfsMftMetadataSchema,
|
||||
type ArtifactFormatMetadata,
|
||||
} from "../domain/artifactFormatMetadata.js";
|
||||
import type { RegionDecodeFailure } from "../domain/firmware/regionDecoder.js";
|
||||
import {
|
||||
createMftDecoder,
|
||||
type MftInventory,
|
||||
} from "../domain/windows/ntfsMft.js";
|
||||
import {
|
||||
ArtifactReaderFailure,
|
||||
type ArtifactEntry,
|
||||
type ArtifactReader,
|
||||
type ArtifactReaderTraversal,
|
||||
type ArtifactTraversalOptions,
|
||||
} from "./ArtifactReader.js";
|
||||
import { ArtifactResourceScope } from "./ArtifactResourceScope.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { readFileHandleChunks } from "../filesystem/readFileHandleChunks.js";
|
||||
import type { StableRegularFileDescriptor } from "../filesystem/RegularFile.js";
|
||||
|
||||
/**
|
||||
* An MFT stream is its own content: the FILE records describe the source
|
||||
* volume, not members inside the stream, so header facts are attached to
|
||||
* the root occurrence.
|
||||
*/
|
||||
export class NtfsMftArtifactReader implements ArtifactReader {
|
||||
readonly format = "ntfs-mft" as const;
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
readonly #source: ArtifactFileSource;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
#metadata: ArtifactFormatMetadata | undefined;
|
||||
#limitations: readonly string[] = [];
|
||||
#closing = false;
|
||||
|
||||
constructor(path: string, admitted?: StableRegularFileDescriptor) {
|
||||
this.#source = new ArtifactFileSource(path, "$MFT stream", admitted);
|
||||
}
|
||||
|
||||
formatMetadata(): ArtifactFormatMetadata | undefined {
|
||||
return this.#metadata === undefined
|
||||
? undefined
|
||||
: structuredClone(this.#metadata);
|
||||
}
|
||||
|
||||
async prepareContainer(
|
||||
expectedSha256: string,
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
await this.#source.bindSha256(expectedSha256, signal);
|
||||
});
|
||||
}
|
||||
|
||||
async *entries(
|
||||
signal?: AbortSignal,
|
||||
options?: ArtifactTraversalOptions,
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
this.#assertOpen(signal);
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
// An MFT declares no members, so the root occurrence is the whole
|
||||
// inventory; the coverage callback reports what its parse did not establish.
|
||||
options?.onCoverage?.(coverageOf(this.#limitations));
|
||||
}
|
||||
|
||||
async open(entry: ArtifactEntry, _signal?: AbortSignal): Promise<Readable> {
|
||||
return this.#scope.run(async () => {
|
||||
throw new ArtifactReaderFailure(
|
||||
"unavailable",
|
||||
`$MFT stream declares no member to open for ${entry.path}`,
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
async close(): Promise<void> {
|
||||
this.#closing = true;
|
||||
await this.#scope.close();
|
||||
await this.#source.close();
|
||||
this.#metadata = undefined;
|
||||
}
|
||||
|
||||
provenance(): readonly [] {
|
||||
return [];
|
||||
}
|
||||
|
||||
#assertOpen(signal?: AbortSignal): void {
|
||||
assertArtifactReadActive(signal);
|
||||
if (this.#closing)
|
||||
throw new ArtifactReaderFailure(
|
||||
"unavailable",
|
||||
"$MFT stream reader is closed",
|
||||
);
|
||||
}
|
||||
|
||||
async #prepare(signal?: AbortSignal): Promise<void> {
|
||||
const image = await this.#decode(signal);
|
||||
await this.#source.read(signal);
|
||||
this.#metadata = ntfsMftMetadataSchema.parse(image.metadata);
|
||||
this.#limitations = image.limitations;
|
||||
}
|
||||
|
||||
async #decode(signal?: AbortSignal): Promise<MftInventory> {
|
||||
const { handle, initial } = await this.#source.read(signal);
|
||||
const decoder = createMftDecoder(initial.size);
|
||||
if (!decoder.ok) throw this.#failure(decoder.error);
|
||||
if (initial.size > 0)
|
||||
for await (const chunk of readFileHandleChunks(handle, {
|
||||
end: initial.size - 1,
|
||||
signal,
|
||||
cancellationFailure: (reason) =>
|
||||
new ArtifactReaderFailure("cancelled", "$MFT stream read cancelled", {
|
||||
cause: reason,
|
||||
}),
|
||||
}) as AsyncIterable<Buffer>) {
|
||||
this.#assertOpen(signal);
|
||||
const written = decoder.value.write(chunk);
|
||||
if (!written.ok) throw this.#failure(written.error);
|
||||
}
|
||||
const image = decoder.value.finish();
|
||||
if (!image.ok) throw this.#failure(image.error);
|
||||
return image.value;
|
||||
}
|
||||
|
||||
#failure(failure: RegionDecodeFailure): ArtifactReaderFailure {
|
||||
return failure.kind === "format"
|
||||
? new ArtifactReaderFailure(
|
||||
"format",
|
||||
`$MFT stream is malformed: ${failure.message}`,
|
||||
)
|
||||
: new ArtifactReaderFailure(
|
||||
"limit",
|
||||
`$MFT stream exceeds a fixed limit: ${failure.message}`,
|
||||
failure.boundary === undefined ? {} : { boundary: failure.boundary },
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const coverageOf = (limitations: readonly string[]): ArtifactReaderTraversal =>
|
||||
limitations.length === 0
|
||||
? { status: "complete", limitations: [] }
|
||||
: { status: "unknown", limitations };
|
||||
@@ -1,4 +1,7 @@
|
||||
import { artifactReaderLifecycleCases } from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import {
|
||||
artifactPreparationRecoveryCases,
|
||||
artifactReaderLifecycleCases,
|
||||
} from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { buffer } from "node:stream/consumers";
|
||||
@@ -91,6 +94,14 @@ it("preserves cancellation during payload CRC admission", async () => {
|
||||
}
|
||||
})(),
|
||||
).rejects.toMatchObject({ reason: "cancelled", cause: reason });
|
||||
reads.mockRestore();
|
||||
const recovered = await entries(reader);
|
||||
expect(recovered).toHaveLength(1);
|
||||
expect(
|
||||
(await buffer(await reader.open(recovered[0]!))).equals(
|
||||
Buffer.alloc(128 * 1024, 0x61),
|
||||
),
|
||||
).toBe(true);
|
||||
} finally {
|
||||
await reader.close();
|
||||
reads.mockRestore();
|
||||
@@ -205,3 +216,8 @@ it("reports impossible over-cap component extents as malformed", async () => {
|
||||
await reader.close();
|
||||
}
|
||||
});
|
||||
|
||||
artifactPreparationRecoveryCases({
|
||||
image: () => buildUImage({ payload: Buffer.from("payload") }),
|
||||
createReader: (path, admitted) => new UImageArtifactReader(path, admitted),
|
||||
});
|
||||
@@ -8,7 +8,10 @@ import type {
|
||||
UImageMetadata,
|
||||
} from "../domain/artifactFormatMetadata.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
ArtifactReaderFailure,
|
||||
copyArtifactEntry,
|
||||
@@ -47,7 +50,9 @@ export class UImageArtifactReader implements ArtifactReader {
|
||||
readonly #entries = new Map<string, UImageEntry>();
|
||||
readonly #streams = new Set<Readable>();
|
||||
readonly #source: ArtifactFileSource;
|
||||
#prepared: Promise<void> | undefined;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
#header: UImageMetadata | undefined;
|
||||
#closing = false;
|
||||
|
||||
@@ -75,8 +80,27 @@ export class UImageArtifactReader implements ArtifactReader {
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
this.#prepared ??= this.#prepare(signal);
|
||||
await this.#prepared;
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
this.#assertOpen(signal);
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
import { artifactPreparationRecoveryCases } from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { truncate, writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { buffer, text } from "node:stream/consumers";
|
||||
@@ -43,6 +45,68 @@ const repeatedBlock = (data: Buffer): Buffer => {
|
||||
]);
|
||||
};
|
||||
|
||||
it("retries UnityFs preparation cancelled during file reading", async () => {
|
||||
const path = await fixture(buildUnityFs([{ path: "a", data: "x" }]));
|
||||
const admitted = await openRegularFile(path, { symlinks: "reject" });
|
||||
const reader = new UnityFsArtifactReader(path, admitted);
|
||||
const controller = new AbortController();
|
||||
const reason = { stage: "header read" };
|
||||
const nativeRead = admitted.handle.read.bind(admitted.handle);
|
||||
const read = vi.spyOn(admitted.handle, "read").mockImplementation((async (
|
||||
...args: unknown[]
|
||||
) => {
|
||||
const result = await Reflect.apply(nativeRead, admitted.handle, args);
|
||||
controller.abort(reason);
|
||||
return result;
|
||||
}) as typeof admitted.handle.read);
|
||||
try {
|
||||
await expect(
|
||||
(async () => {
|
||||
for await (const _ of reader.entries(controller.signal)) {
|
||||
}
|
||||
})(),
|
||||
).rejects.toMatchObject({ reason: "cancelled", cause: reason });
|
||||
read.mockRestore();
|
||||
expect((await entries(reader)).map((entry) => entry.path)).toEqual(["a"]);
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await admitted.handle.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("does not publish UnityFs entries when final source verification fails", async () => {
|
||||
const path = await fixture(buildUnityFs([{ path: "a", data: "x" }]));
|
||||
const control = new UnityFsArtifactReader(path);
|
||||
const reader = new UnityFsArtifactReader(path);
|
||||
const expected = (await entries(control))[0]!;
|
||||
const nativeRead = ArtifactFileSource.prototype.read;
|
||||
const physical = Object.assign(
|
||||
new Error("final source verification failed"),
|
||||
{ code: "EIO" },
|
||||
);
|
||||
let calls = 0;
|
||||
const read = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementation(function (this: ArtifactFileSource, ...args) {
|
||||
calls += 1;
|
||||
if (calls === 2) return Promise.reject(physical);
|
||||
return nativeRead.apply(this, args);
|
||||
});
|
||||
try {
|
||||
await expect(entries(reader)).rejects.toBe(physical);
|
||||
await expect(reader.open(expected)).rejects.toMatchObject({
|
||||
reason: "integrity",
|
||||
});
|
||||
read.mockRestore();
|
||||
expect((await entries(reader)).map((entry) => entry.path)).toEqual(["a"]);
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await control.close();
|
||||
}
|
||||
});
|
||||
|
||||
describe("UnityFS allocation and malformed-input boundaries", () => {
|
||||
it("rejects an oversized directory extending past the physical file", async () => {
|
||||
const bytes = buildUnityFs([{ path: "data", data: "x" }]);
|
||||
@@ -431,3 +495,8 @@ describe("UnityFS stream capacity and cache ownership", () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
artifactPreparationRecoveryCases({
|
||||
image: () => buildUnityFs([{ path: "a", data: "x" }]),
|
||||
createReader: (path, admitted) => new UnityFsArtifactReader(path, admitted),
|
||||
});
|
||||
@@ -12,7 +12,10 @@ import {
|
||||
type ArtifactTraversalOptions,
|
||||
} from "./ArtifactReader.js";
|
||||
import { ArtifactResourceScope } from "./ArtifactResourceScope.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import { readArtifactFileBytes } from "./ArtifactFileRange.js";
|
||||
import type {
|
||||
ArtifactFormatMetadata,
|
||||
@@ -52,10 +55,12 @@ interface UnityFsEntryState {
|
||||
export class UnityFsArtifactReader implements ArtifactReader {
|
||||
readonly format = "unityfs" as const;
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
readonly #entries = new Map<string, UnityFsEntryState>();
|
||||
#entries = new Map<string, UnityFsEntryState>();
|
||||
readonly #streams = new Map<Readable, AbortController>();
|
||||
readonly #source: ArtifactFileSource;
|
||||
#prepared: Promise<void> | undefined;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
#header: UnityFsMetadata | undefined;
|
||||
#blocks: readonly UnityFsBlock[] = [];
|
||||
#dataStart = 0;
|
||||
@@ -88,8 +93,27 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
this.#prepared ??= this.#prepare(signal);
|
||||
await this.#prepared;
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
this.#assertOpen(signal);
|
||||
@@ -229,7 +253,7 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
if (header === undefined)
|
||||
throw unityFsFormatFailure("no complete UnityFS header");
|
||||
const status = header.layout.status;
|
||||
this.#header = {
|
||||
const metadata: UnityFsMetadata = {
|
||||
kind: "unityfs",
|
||||
signature: "UnityFS",
|
||||
format_version: header.formatVersion,
|
||||
@@ -245,7 +269,12 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
data_hash: null,
|
||||
directory_status: status,
|
||||
};
|
||||
if (status !== "available") return;
|
||||
if (status !== "available") {
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#header = metadata;
|
||||
return;
|
||||
}
|
||||
const { dataHash, blocks, nodes, dataStart } = await readUnityFsBlocksInfo(
|
||||
handle,
|
||||
header,
|
||||
@@ -259,44 +288,55 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
if (streamBytes > BigInt(budget))
|
||||
throw expansionLimit("declared virtual stream", streamBytes, budget);
|
||||
}
|
||||
this.#header = {
|
||||
...this.#header,
|
||||
const preparedMetadata: UnityFsMetadata = {
|
||||
...metadata,
|
||||
data_hash: dataHash,
|
||||
block_count: blocks.length,
|
||||
data_start: dataStart,
|
||||
};
|
||||
this.#dataStart = dataStart;
|
||||
// Keep the source block count above, but do not revisit zero-output rows
|
||||
// for every member. Parsed stream/compressed offsets remain authoritative.
|
||||
this.#blocks = blocks.filter((block) => block.uncompressedSize > 0);
|
||||
this.#remainingDecodeBytes = budget;
|
||||
await this.#registerNodes(nodes, budget, signal);
|
||||
const readableBlocks = blocks.filter((block) => block.uncompressedSize > 0);
|
||||
const registered = await this.#registerNodes(
|
||||
nodes,
|
||||
readableBlocks,
|
||||
budget,
|
||||
signal,
|
||||
);
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#header = preparedMetadata;
|
||||
this.#dataStart = dataStart;
|
||||
this.#blocks = readableBlocks;
|
||||
this.#remainingDecodeBytes = budget;
|
||||
this.#entries = registered.entries;
|
||||
this.#remainingReadOperations = registered.remainingReadOperations;
|
||||
}
|
||||
|
||||
async #registerNodes(
|
||||
nodes: readonly UnityFsNode[],
|
||||
blocks: readonly UnityFsBlock[],
|
||||
budget: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
): Promise<{
|
||||
entries: Map<string, UnityFsEntryState>;
|
||||
remainingReadOperations: number;
|
||||
}> {
|
||||
const entries = new Map<string, UnityFsEntryState>();
|
||||
let readableBytes = 0n;
|
||||
for (let index = 0; index < nodes.length; index++) {
|
||||
if (index % 256 === 0) await setImmediate();
|
||||
this.#assertOpen(signal);
|
||||
const node = nodes[index]!;
|
||||
const firstBlock =
|
||||
node.size === 0 ? -1 : blockEndingAfter(this.#blocks, node.offset);
|
||||
node.size === 0 ? -1 : blockEndingAfter(blocks, node.offset);
|
||||
const lastBlock =
|
||||
node.size === 0
|
||||
? -1
|
||||
: blockEndingAfter(this.#blocks, node.offset + node.size - 1);
|
||||
: blockEndingAfter(blocks, node.offset + node.size - 1);
|
||||
if (node.size !== 0 && (firstBlock < 0 || lastBlock < firstBlock))
|
||||
throw unityFsFormatFailure("member has no block range");
|
||||
const unavailable = firstUnavailableBlock(
|
||||
this.#blocks,
|
||||
firstBlock,
|
||||
lastBlock,
|
||||
);
|
||||
const unavailable = firstUnavailableBlock(blocks, firstBlock, lastBlock);
|
||||
const kind =
|
||||
(node.flags & 1) !== 0 ? ("directory" as const) : ("file" as const);
|
||||
if (kind === "file" && unavailable === undefined) {
|
||||
@@ -331,7 +371,7 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
flags: node.flags,
|
||||
},
|
||||
} satisfies UnityFsEntry;
|
||||
this.#entries.set(adapterKey, {
|
||||
entries.set(adapterKey, {
|
||||
entry,
|
||||
firstBlock,
|
||||
lastBlock,
|
||||
@@ -340,14 +380,15 @@ export class UnityFsArtifactReader implements ArtifactReader {
|
||||
}
|
||||
// Four ordinary passes over admitted blocks, nodes and plaintext chunks,
|
||||
// with a small-reader floor. Byte quotas alone cannot bound tiny-block I/O.
|
||||
this.#remainingReadOperations =
|
||||
const remainingReadOperations =
|
||||
4 *
|
||||
Math.max(
|
||||
1024,
|
||||
this.#blocks.length +
|
||||
blocks.length +
|
||||
nodes.length +
|
||||
Math.ceil(Number(readableBytes) / CHUNK_BYTES),
|
||||
);
|
||||
return { entries, remainingReadOperations };
|
||||
}
|
||||
|
||||
async *#memberChunks(
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
import { artifactPreparationRecoveryCases } from "../../tests/fixtures/artifactReaderLifecycle.js";
|
||||
import { ArtifactFileSource } from "./ArtifactFileSource.js";
|
||||
import { once } from "node:events";
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
@@ -26,6 +28,68 @@ const entries = async (reader: WxapkgArtifactReader) => {
|
||||
return result;
|
||||
};
|
||||
|
||||
it("retries Wxapkg preparation cancelled during file reading", async () => {
|
||||
const path = await fixture(buildWxapkg([{ path: "a", data: "x" }]));
|
||||
const admitted = await openRegularFile(path, { symlinks: "reject" });
|
||||
const reader = new WxapkgArtifactReader(path, admitted);
|
||||
const controller = new AbortController();
|
||||
const reason = { stage: "header read" };
|
||||
const nativeRead = admitted.handle.read.bind(admitted.handle);
|
||||
const read = vi.spyOn(admitted.handle, "read").mockImplementation((async (
|
||||
...args: unknown[]
|
||||
) => {
|
||||
const result = await Reflect.apply(nativeRead, admitted.handle, args);
|
||||
controller.abort(reason);
|
||||
return result;
|
||||
}) as typeof admitted.handle.read);
|
||||
try {
|
||||
await expect(
|
||||
(async () => {
|
||||
for await (const _ of reader.entries(controller.signal)) {
|
||||
}
|
||||
})(),
|
||||
).rejects.toMatchObject({ reason: "cancelled", cause: reason });
|
||||
read.mockRestore();
|
||||
expect((await entries(reader)).map((entry) => entry.path)).toEqual(["a"]);
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await admitted.handle.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("does not publish Wxapkg entries when final source verification fails", async () => {
|
||||
const path = await fixture(buildWxapkg([{ path: "a", data: "x" }]));
|
||||
const control = new WxapkgArtifactReader(path);
|
||||
const reader = new WxapkgArtifactReader(path);
|
||||
const expected = (await entries(control))[0]!;
|
||||
const nativeRead = ArtifactFileSource.prototype.read;
|
||||
const physical = Object.assign(
|
||||
new Error("final source verification failed"),
|
||||
{ code: "EIO" },
|
||||
);
|
||||
let calls = 0;
|
||||
const read = vi
|
||||
.spyOn(ArtifactFileSource.prototype, "read")
|
||||
.mockImplementation(function (this: ArtifactFileSource, ...args) {
|
||||
calls += 1;
|
||||
if (calls === 2) return Promise.reject(physical);
|
||||
return nativeRead.apply(this, args);
|
||||
});
|
||||
try {
|
||||
await expect(entries(reader)).rejects.toBe(physical);
|
||||
await expect(reader.open(expected)).rejects.toMatchObject({
|
||||
reason: "integrity",
|
||||
});
|
||||
read.mockRestore();
|
||||
expect((await entries(reader)).map((entry) => entry.path)).toEqual(["a"]);
|
||||
} finally {
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await control.close();
|
||||
}
|
||||
});
|
||||
|
||||
describe("wxapkg allocation and malformed-input boundaries", () => {
|
||||
it("admits the encoded table budget before reading it", async () => {
|
||||
const bytes = buildWxapkg([{ path: "a", data: "x" }]);
|
||||
@@ -308,3 +372,8 @@ describe("wxapkg stream capacity and freshness", () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
artifactPreparationRecoveryCases({
|
||||
image: () => buildWxapkg([{ path: "a", data: "x" }]),
|
||||
createReader: (path, admitted) => new WxapkgArtifactReader(path, admitted),
|
||||
});
|
||||
@@ -12,7 +12,10 @@ import {
|
||||
type ArtifactTraversalOptions,
|
||||
} from "./ArtifactReader.js";
|
||||
import { ArtifactResourceScope } from "./ArtifactResourceScope.js";
|
||||
import { assertArtifactReadActive } from "./ArtifactFileOperation.js";
|
||||
import {
|
||||
artifactReadCancelledBy,
|
||||
assertArtifactReadActive,
|
||||
} from "./ArtifactFileOperation.js";
|
||||
import { readArtifactFileBytes } from "./ArtifactFileRange.js";
|
||||
import type {
|
||||
ArtifactFormatMetadata,
|
||||
@@ -48,10 +51,12 @@ interface WxapkgEntryState {
|
||||
export class WxapkgArtifactReader implements ArtifactReader {
|
||||
readonly format = "wxapkg" as const;
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
readonly #entries = new Map<string, WxapkgEntryState>();
|
||||
#entries = new Map<string, WxapkgEntryState>();
|
||||
readonly #streams = new Map<Readable, AbortController>();
|
||||
readonly #source: ArtifactFileSource;
|
||||
#prepared: Promise<void> | undefined;
|
||||
#prepared:
|
||||
| { signal: AbortSignal | undefined; promise: Promise<void> }
|
||||
| undefined;
|
||||
#header: WxapkgMetadata | undefined;
|
||||
#remainingReadOperations = 0;
|
||||
#admittedReadOperations = 0;
|
||||
@@ -81,8 +86,27 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
): AsyncIterable<ArtifactEntry> {
|
||||
await this.#scope.run(async () => {
|
||||
this.#assertOpen(signal);
|
||||
this.#prepared ??= this.#prepare(signal);
|
||||
await this.#prepared;
|
||||
for (;;) {
|
||||
const pending = (this.#prepared ??= {
|
||||
signal,
|
||||
promise: this.#prepare(signal),
|
||||
});
|
||||
try {
|
||||
await pending.promise;
|
||||
break;
|
||||
} catch (cause: unknown) {
|
||||
if (this.#prepared === pending) this.#prepared = undefined;
|
||||
if (
|
||||
pending.signal !== signal &&
|
||||
signal?.aborted !== true &&
|
||||
artifactReadCancelledBy(cause, pending.signal)
|
||||
) {
|
||||
this.#assertOpen(signal);
|
||||
continue;
|
||||
}
|
||||
throw cause;
|
||||
}
|
||||
}
|
||||
await this.#source.read(signal);
|
||||
});
|
||||
this.#assertOpen(signal);
|
||||
@@ -201,7 +225,7 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
const header = await readWxapkgHeader(handle, initial.size, signal);
|
||||
if (header === undefined)
|
||||
throw wxapkgFormatFailure("no complete wxapkg header");
|
||||
this.#header = {
|
||||
const metadata: WxapkgMetadata = {
|
||||
kind: "wxapkg",
|
||||
info: header.layout.status === "available" ? header.info : null,
|
||||
index_length:
|
||||
@@ -212,7 +236,12 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
header.layout.status === "available" ? header.fileCount : null,
|
||||
directory_status: header.layout.status,
|
||||
};
|
||||
if (header.layout.status !== "available") return;
|
||||
if (header.layout.status !== "available") {
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#header = metadata;
|
||||
return;
|
||||
}
|
||||
const { members } = await readWxapkgFileTable(
|
||||
handle,
|
||||
header,
|
||||
@@ -220,6 +249,7 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
signal,
|
||||
);
|
||||
const budget = artifactExpansionBudgetBytes(initial.size);
|
||||
const entries = new Map<string, WxapkgEntryState>();
|
||||
let declaredBytes = 0n;
|
||||
for (let index = 0; index < members.length; index++) {
|
||||
if (index % 256 === 0) await setImmediate();
|
||||
@@ -234,7 +264,7 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
{ boundary: "memory" },
|
||||
);
|
||||
const adapterKey = `wxapkg-entry:${String(index)}`;
|
||||
this.#entries.set(adapterKey, {
|
||||
entries.set(adapterKey, {
|
||||
entry: {
|
||||
path: member.path,
|
||||
sourcePath: member.declaredPath,
|
||||
@@ -260,14 +290,18 @@ export class WxapkgArtifactReader implements ArtifactReader {
|
||||
});
|
||||
}
|
||||
// Header, table and per-chunk member reads; a small-reader floor applies.
|
||||
this.#admittedReadOperations =
|
||||
const admittedReadOperations =
|
||||
4 *
|
||||
Math.max(
|
||||
1024,
|
||||
members.length + Math.ceil(Number(declaredBytes) / CHUNK_BYTES),
|
||||
);
|
||||
this.#remainingReadOperations = this.#admittedReadOperations;
|
||||
await this.#source.read(signal);
|
||||
this.#assertOpen(signal);
|
||||
this.#header = metadata;
|
||||
this.#entries = entries;
|
||||
this.#admittedReadOperations = admittedReadOperations;
|
||||
this.#remainingReadOperations = admittedReadOperations;
|
||||
}
|
||||
|
||||
async *#memberChunks(
|
||||
|
||||
@@ -132,6 +132,7 @@ describe("Mach-O encryption reader: thin images", () => {
|
||||
container_file_offset: 0,
|
||||
size: expect.any(Number),
|
||||
status: "absent",
|
||||
malformed_kind: null,
|
||||
reason: null,
|
||||
commands: [],
|
||||
range: null,
|
||||
@@ -479,6 +480,27 @@ describe("Mach-O encryption reader: segment VM extent", () => {
|
||||
});
|
||||
|
||||
describe("Mach-O encryption reader: defects are never absent", () => {
|
||||
it.each([0, 1, 2])(
|
||||
"keeps a structural encryption defect at index %i ahead of duplicate ambiguity",
|
||||
async (index) => {
|
||||
const commands = Array.from({ length: 3 }, () =>
|
||||
encryption({ cryptoff: 0, cryptsize: 0, cryptid: 1 }),
|
||||
);
|
||||
commands[index] = encryption(
|
||||
{ cryptoff: 0, cryptsize: 0, cryptid: 1 },
|
||||
true,
|
||||
8,
|
||||
);
|
||||
const slice = await onlySlice(machoImage({ commands }));
|
||||
expect(slice).toMatchObject({
|
||||
status: "malformed",
|
||||
malformed_kind: "structure",
|
||||
reason: `slice has 3 encryption load commands; load command ${index} LC_ENCRYPTION_INFO_64 has cmdsize 8, expected 24`,
|
||||
range: null,
|
||||
});
|
||||
expect(slice.commands.map(({ index }) => index)).toEqual([0, 1]);
|
||||
},
|
||||
);
|
||||
it.each([
|
||||
{
|
||||
name: "a 64-bit command in a 32-bit image",
|
||||
@@ -544,6 +566,7 @@ describe("Mach-O encryption reader: defects are never absent", () => {
|
||||
expect(slice).toMatchObject({
|
||||
status: "malformed",
|
||||
reason: "slice has 1000 encryption load commands",
|
||||
malformed_kind: "duplicate-commands",
|
||||
range: null,
|
||||
});
|
||||
expect(slice.commands.map(({ index }) => index)).toEqual([0, 1]);
|
||||
|
||||
@@ -117,6 +117,7 @@ const unread = (
|
||||
container_file_offset: declaration.offset,
|
||||
size: declaration.size,
|
||||
status,
|
||||
malformed_kind: status === "malformed" ? "structure" : null,
|
||||
reason,
|
||||
commands: [],
|
||||
range: null,
|
||||
@@ -143,6 +144,10 @@ const readSlice = async (
|
||||
// and dropped so a large table of small commands stays one buffer.
|
||||
const commands: MachoEncryptionCommand[] = [];
|
||||
let encryptionCommands = 0;
|
||||
const encryption: {
|
||||
first: ValidEncryptionCommand | null;
|
||||
failure: string | null;
|
||||
} = { first: null, failure: null };
|
||||
// Null once this slice's segments need more records than the shared
|
||||
// mapping budget has left; none are retained past that point.
|
||||
let segments: MachoLoadCommand[] | null = [];
|
||||
@@ -155,6 +160,7 @@ const readSlice = async (
|
||||
}: MachoReadIssue): MachoSliceEncryption => ({
|
||||
...base,
|
||||
status: status === "unsupported" ? "unknown" : "malformed",
|
||||
malformed_kind: status === "unsupported" ? null : "structure",
|
||||
reason,
|
||||
commands,
|
||||
range: null,
|
||||
@@ -164,8 +170,12 @@ const readSlice = async (
|
||||
const framed = frameLoadCommands(table, (command) => {
|
||||
if (isEncryptionCommand(command.command)) {
|
||||
encryptionCommands += 1;
|
||||
const decoded = decodeEncryptionCommand(command);
|
||||
if (commands.length < RETAINED_ENCRYPTION_COMMANDS)
|
||||
commands.push(decodeEncryptionCommand(command));
|
||||
commands.push(decoded);
|
||||
const checked = classifyCommand(decoded, header, slice.size);
|
||||
if (checked.status === "malformed") encryption.failure ??= checked.reason;
|
||||
else encryption.first ??= checked.command;
|
||||
} else if (
|
||||
segments !== null &&
|
||||
(command.command === LC_SEGMENT || command.command === LC_SEGMENT_64)
|
||||
@@ -187,15 +197,44 @@ const readSlice = async (
|
||||
return {
|
||||
...base,
|
||||
status: "malformed",
|
||||
malformed_kind: "structure",
|
||||
reason: identityIssue,
|
||||
commands,
|
||||
range: null,
|
||||
};
|
||||
const outcome = classify(commands, encryptionCommands, header, slice.size);
|
||||
if (outcome.status !== "valid")
|
||||
return { ...base, ...outcome, commands, range: null };
|
||||
if (encryption.failure !== null)
|
||||
return {
|
||||
...base,
|
||||
status: "malformed",
|
||||
malformed_kind: "structure",
|
||||
reason:
|
||||
encryptionCommands > 1
|
||||
? `slice has ${encryptionCommands} encryption load commands; ${encryption.failure}`
|
||||
: encryption.failure,
|
||||
commands,
|
||||
range: null,
|
||||
};
|
||||
if (encryptionCommands > 1)
|
||||
return {
|
||||
...base,
|
||||
status: "malformed",
|
||||
malformed_kind: "duplicate-commands",
|
||||
reason: `slice has ${encryptionCommands} encryption load commands`,
|
||||
commands,
|
||||
range: null,
|
||||
};
|
||||
const command = encryption.first;
|
||||
if (command === null)
|
||||
return {
|
||||
...base,
|
||||
status: "absent",
|
||||
malformed_kind: null,
|
||||
reason: null,
|
||||
commands,
|
||||
range: null,
|
||||
};
|
||||
const range = encryptedRange(
|
||||
outcome.command,
|
||||
command,
|
||||
header,
|
||||
segments,
|
||||
slice.offset,
|
||||
@@ -206,7 +245,8 @@ const readSlice = async (
|
||||
if (range.mapping.status === "mapped") budget.remaining -= segmentRecords;
|
||||
return {
|
||||
...base,
|
||||
status: outcome.command.cryptid === 0 ? "not-encrypted" : "encrypted",
|
||||
status: command.cryptid === 0 ? "not-encrypted" : "encrypted",
|
||||
malformed_kind: null,
|
||||
reason: null,
|
||||
commands,
|
||||
range,
|
||||
@@ -236,31 +276,23 @@ const decodeEncryptionCommand = ({
|
||||
};
|
||||
};
|
||||
|
||||
type ValidEncryptionCommand = MachoEncryptionCommand & {
|
||||
readonly cryptoff: number;
|
||||
readonly cryptsize: number;
|
||||
readonly cryptid: number;
|
||||
};
|
||||
type Classification =
|
||||
| {
|
||||
readonly status: "valid";
|
||||
readonly command: MachoEncryptionCommand & {
|
||||
readonly cryptoff: number;
|
||||
readonly cryptsize: number;
|
||||
readonly cryptid: number;
|
||||
};
|
||||
readonly command: ValidEncryptionCommand;
|
||||
}
|
||||
| { readonly status: "absent"; readonly reason: null }
|
||||
| { readonly status: "malformed"; readonly reason: string };
|
||||
|
||||
const classify = (
|
||||
commands: readonly MachoEncryptionCommand[],
|
||||
count: number,
|
||||
const classifyCommand = (
|
||||
command: MachoEncryptionCommand,
|
||||
header: MachoSliceHeader,
|
||||
sliceSize: number,
|
||||
): Classification => {
|
||||
if (count === 0) return { status: "absent", reason: null };
|
||||
const [command] = commands;
|
||||
if (command === undefined || count > 1)
|
||||
return {
|
||||
status: "malformed",
|
||||
reason: `slice has ${count} encryption load commands`,
|
||||
};
|
||||
const width = header.wide ? 64 : 32;
|
||||
const expectedKind = header.wide
|
||||
? "LC_ENCRYPTION_INFO_64"
|
||||
|
||||
@@ -43,7 +43,8 @@ type FormatsWithReaders =
|
||||
| "uf2"
|
||||
| "dfuse"
|
||||
| "esp-flash-image"
|
||||
| "fit";
|
||||
| "fit"
|
||||
| "ntfs-mft";
|
||||
|
||||
const readerFormatsMatch: Equal<ArtifactReaderFormat, FormatsWithReaders> =
|
||||
true;
|
||||
|
||||
@@ -40,6 +40,7 @@ import { NodeSeaArtifactReader } from "./NodeSeaArtifactReader.js";
|
||||
import type { PyInstallerAdmission } from "./pyinstaller/PyInstallerAdmission.js";
|
||||
import { PyInstallerArtifactReader } from "./PyInstallerArtifactReader.js";
|
||||
import { Uf2ArtifactReader } from "./Uf2ArtifactReader.js";
|
||||
import { NtfsMftArtifactReader } from "./NtfsMftArtifactReader.js";
|
||||
import { UImageArtifactReader } from "./UImageArtifactReader.js";
|
||||
import { UnityFsArtifactReader } from "./UnityFsArtifactReader.js";
|
||||
import { WxapkgArtifactReader } from "./WxapkgArtifactReader.js";
|
||||
@@ -465,6 +466,14 @@ const NON_ZIP_FORMATS = {
|
||||
createReader: (path, options) =>
|
||||
new FitArtifactReader(path, sourceOf(options)),
|
||||
}),
|
||||
"ntfs-mft": described("ntfs-mft", {
|
||||
...plain,
|
||||
retainClassifiedSource: true,
|
||||
readerLimitation:
|
||||
"MFT inventory reports whole-stream counts and a bounded sample of the first 32 decoded FILE record headers, with the omitted-header count. Attributes, filenames, data streams and the $UsnJrnl:$J journal are not decoded, so no path, file size or change history is established.",
|
||||
createReader: (path, options) =>
|
||||
new NtfsMftArtifactReader(path, sourceOf(options)),
|
||||
}),
|
||||
unknown: described("unknown", plain),
|
||||
} satisfies Record<
|
||||
Exclude<ArtifactFormatId, ZipPackageFormat>,
|
||||
|
||||
@@ -576,6 +576,28 @@ it("classifies nested UF2 by block magics and DfuSe by prefix and suffix", () =>
|
||||
).toMatchObject({ format: "file" });
|
||||
});
|
||||
|
||||
it("classifies a $MFT stream by its FILE record header, under any name", () => {
|
||||
const mft = Buffer.alloc(2_048);
|
||||
mft.write("FILE", 0, "latin1");
|
||||
mft.writeUInt32LE(1024, 28);
|
||||
for (const path of ["evidence/$MFT", "evidence/mft.raw", "evidence/records"])
|
||||
expect(classifyArtifactBytesAtPath(path, mft)).toEqual({
|
||||
kind: "executable",
|
||||
format: "ntfs-mft",
|
||||
});
|
||||
});
|
||||
|
||||
it("leaves plain content beginning with FILE unclassified as MFT", () => {
|
||||
const text = Buffer.from(
|
||||
"FILE is a plain text prefix, not an NTFS record header",
|
||||
);
|
||||
expect(
|
||||
classifyArtifactBytesAtPath("evidence/readme.txt", text),
|
||||
).toMatchObject({
|
||||
format: "file",
|
||||
});
|
||||
});
|
||||
|
||||
it("classifies a FIT by a /images node within the first 4 KiB", () => {
|
||||
const images = [{ name: "kernel", data: Buffer.from("kernel") }];
|
||||
const late = devicetreeFixture({
|
||||
|
||||
@@ -11,6 +11,7 @@ import { recognizeEspImage } from "../../domain/firmware/espImage.js";
|
||||
import { hasUf2Block } from "../../domain/firmware/uf2.js";
|
||||
import { isDfuSeFile } from "../../domain/firmware/dfuse.js";
|
||||
import { hasFitImagesNode } from "../../domain/firmware/fitImage.js";
|
||||
import { hasMftFileRecordHeader } from "../../domain/windows/ntfsMft.js";
|
||||
import type { ArtifactClassificationEvidence } from "../ArtifactClassificationProbe.js";
|
||||
import { asarHeaderAdmissionFailure } from "../AsarHeader.js";
|
||||
import { hasDestinationPath } from "../ArtifactPaths.js";
|
||||
@@ -622,6 +623,7 @@ export const classifyArtifactBytes = (
|
||||
return "dfuse";
|
||||
if (recognizeEspImage(prefix, fileSize) === "esp-image") return "esp-image";
|
||||
if (hasFitImagesNode(prefix)) return "fit";
|
||||
if (hasMftFileRecordHeader(prefix)) return "ntfs-mft";
|
||||
if (hasBinaryPlistSignature(prefix)) return "plist";
|
||||
if (hasXmlPlistSignature(prefix)) return "plist";
|
||||
const fatFormat = classifyFatArtifact(evidence, fileSize);
|
||||
|
||||
@@ -86,6 +86,7 @@ const formatSchema = z.enum([
|
||||
"dfuse",
|
||||
"esp-flash-image",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
"plist",
|
||||
"javascript",
|
||||
"source-map",
|
||||
|
||||
@@ -68,6 +68,42 @@ it("keeps historical symbol defaults scoped to their selected Mach-O facet", ()
|
||||
).toBe(false);
|
||||
});
|
||||
|
||||
it.each(["not-encrypted", "malformed"] as const)(
|
||||
"projects historical encryption rows with %s status",
|
||||
(status) => {
|
||||
const current = inspectMachoSchema.parse(report);
|
||||
const { malformed_kind: _unrecorded, ...recorded } =
|
||||
current.encryption.items[0]!;
|
||||
const historical = {
|
||||
...recorded,
|
||||
status,
|
||||
...(status === "malformed"
|
||||
? { reason: "slice has 3 encryption load commands", range: null }
|
||||
: {}),
|
||||
};
|
||||
const source = { ...current, encryption: coverage([historical]) };
|
||||
expect(inspectMachoSchema.safeParse(source).success).toBe(false);
|
||||
const projected = projectAnalysisView(parent(source), {
|
||||
kind: "macho",
|
||||
facet: "encryption",
|
||||
offset: 0,
|
||||
limit: 10,
|
||||
});
|
||||
if (!projected.ok || projected.value.kind !== "macho")
|
||||
throw new Error("Expected a historical Mach-O encryption page");
|
||||
expect(projected.value.item).toEqual([
|
||||
{
|
||||
...historical,
|
||||
malformed_kind: status === "malformed" ? "unrecorded" : null,
|
||||
},
|
||||
]);
|
||||
expect(analysisViewResultSchema.safeParse(projected.value).success).toBe(
|
||||
true,
|
||||
);
|
||||
expect(historical).not.toHaveProperty("malformed_kind");
|
||||
},
|
||||
);
|
||||
|
||||
const symbol = (name: string) => ({
|
||||
name,
|
||||
runtime_name: name.slice(1),
|
||||
@@ -148,6 +184,7 @@ const report = {
|
||||
container_file_offset: 0,
|
||||
size: 4096,
|
||||
status: "not-encrypted",
|
||||
malformed_kind: null,
|
||||
reason: null,
|
||||
commands: [
|
||||
{
|
||||
|
||||
@@ -3,6 +3,7 @@ import { z } from "zod";
|
||||
import type { AnalysisError } from "../analysisErrorBase.js";
|
||||
import { uniqueSorted } from "../canonicalOrdering.js";
|
||||
import { isMachOFormat } from "../binaryTargetTypes.js";
|
||||
import { machoSliceEncryptionViewSchema } from "../apple/machoEncryption.js";
|
||||
import {
|
||||
inspectMachoSchema,
|
||||
retainedInspectMachoSchema,
|
||||
@@ -56,7 +57,7 @@ export const machoViewRows = {
|
||||
imports: exactRows(shape.imports.shape.items),
|
||||
exports: exactRows(shape.exports.shape.items),
|
||||
segments: exactRows(shape.segments.shape.items),
|
||||
encryption: exactRows(shape.encryption.shape.items),
|
||||
encryption: z.array(machoSliceEncryptionViewSchema),
|
||||
provenance: exactRows(shape.provenance),
|
||||
};
|
||||
|
||||
@@ -90,7 +91,7 @@ export const machoSummarySchema = z.strictObject({
|
||||
limitation_count: z.int().nonnegative(),
|
||||
});
|
||||
|
||||
type MachoReport = z.output<typeof inspectMachoSchema>;
|
||||
type MachoReport = z.output<typeof retainedInspectMachoSchema>;
|
||||
|
||||
/** Admit a well-formed report whose recorded subject, if any, is a Mach-O. */
|
||||
const parseMachoReport = (
|
||||
|
||||
@@ -77,7 +77,10 @@ export const directoryOf = (path: string): string => {
|
||||
export const joinPath = (directory: string, rest: string): string =>
|
||||
directory === "" ? rest : rest === "" ? directory : `${directory}/${rest}`;
|
||||
|
||||
export type Expansion =
|
||||
export type Expansion = {
|
||||
/** Recognized dyld token, owned by the same parse that expands the path. */
|
||||
readonly prefix?: "loader_path" | "executable_path";
|
||||
} & (
|
||||
| {
|
||||
readonly scope: "target";
|
||||
/** Source-facing expansion retained in candidate Evidence. */
|
||||
@@ -86,7 +89,8 @@ export type Expansion =
|
||||
readonly lookupPath?: string;
|
||||
}
|
||||
| { readonly scope: "outside"; readonly path: string }
|
||||
| { readonly scope: "undetermined"; readonly path: string };
|
||||
| { readonly scope: "undetermined"; readonly path: string }
|
||||
);
|
||||
|
||||
/** Expand one dyld path prefix relative to its owning image. */
|
||||
export const expandPrefix = (
|
||||
@@ -102,12 +106,17 @@ export const expandPrefix = (
|
||||
if (variable !== null) {
|
||||
const rest = variable[2] ?? "";
|
||||
if (variable[1] === "loader_path")
|
||||
return { scope: "target", path: joinPath(context.ownerDirectory, rest) };
|
||||
return {
|
||||
scope: "target",
|
||||
path: joinPath(context.ownerDirectory, rest),
|
||||
prefix: "loader_path",
|
||||
};
|
||||
return context.executable === null
|
||||
? { scope: "undetermined", path: raw }
|
||||
? { scope: "undetermined", path: raw, prefix: "executable_path" }
|
||||
: {
|
||||
scope: "target",
|
||||
path: joinPath(directoryOf(context.executable), rest),
|
||||
prefix: "executable_path",
|
||||
};
|
||||
}
|
||||
if (raw.startsWith("/")) {
|
||||
|
||||
@@ -222,9 +222,9 @@ it.each(["@loader_path_suffix", "@executable_path_suffix", "@loader_path\n"])(
|
||||
}),
|
||||
{ roots: [MAIN] },
|
||||
);
|
||||
expect(edgeFor(trace, MAIN, name).resolution).toEqual({
|
||||
status: "undetermined",
|
||||
image: null,
|
||||
expect(edgeFor(trace, MAIN, name)).toMatchObject({
|
||||
candidates: [{ source: "literal", path: name }],
|
||||
resolution: { status: "undetermined", image: null },
|
||||
});
|
||||
},
|
||||
);
|
||||
@@ -1020,6 +1020,12 @@ describe("dyld slice compatibility and coverage", () => {
|
||||
],
|
||||
resolution: { status: "undetermined", image: null },
|
||||
});
|
||||
expect(trace.coverage.status).toBe("partial");
|
||||
expect(trace.limitations).toContainEqual(
|
||||
expect.stringContaining(
|
||||
"Contents/MacOS/libarm.dylib have unknown architecture compatibility",
|
||||
),
|
||||
);
|
||||
});
|
||||
|
||||
it("lets an x86_64h process load generic x86_64 but not arm64e load arm64", async () => {
|
||||
|
||||
@@ -268,6 +268,7 @@ interface ProcessContext {
|
||||
>;
|
||||
readonly searchOverrides: readonly DyldSearchOverride[];
|
||||
readonly environmentRoots: Set<string>;
|
||||
readonly unknownArchitectureCandidates: Set<string>;
|
||||
readonly unknownPlatformCandidates: Set<string>;
|
||||
readonly undecodableSymlinkTargets: Map<string, string>;
|
||||
readonly implicitMacOSPlatformCandidates: Set<string>;
|
||||
@@ -310,15 +311,11 @@ const candidateTemplates = (
|
||||
): CandidateTemplate[] => {
|
||||
const name = dependency.install_name;
|
||||
if (!name.startsWith("@rpath/")) {
|
||||
const source = name.startsWith("@executable_path")
|
||||
? "executable_path"
|
||||
: name.startsWith("@loader_path")
|
||||
? "loader_path"
|
||||
: "literal";
|
||||
const expansion = expandCandidatePath(name, directoryOf(loader), context);
|
||||
return [
|
||||
{
|
||||
expansion: expandCandidatePath(name, directoryOf(loader), context),
|
||||
source,
|
||||
expansion,
|
||||
source: expansion.prefix ?? "literal",
|
||||
rpath: null,
|
||||
rpathOwner: null,
|
||||
},
|
||||
@@ -379,8 +376,10 @@ const evaluateCandidate = async (
|
||||
machoImageSlices(facts),
|
||||
context.processIdentity,
|
||||
);
|
||||
if (selection.kind === "unknown") outcome = "undetermined";
|
||||
else if (selection.kind === "missing") outcome = "architecture-missing";
|
||||
if (selection.kind === "unknown") {
|
||||
outcome = "undetermined";
|
||||
context.unknownArchitectureCandidates.add(lookup.path);
|
||||
} else if (selection.kind === "missing") outcome = "architecture-missing";
|
||||
// Dependency commands require a dylib; generic dyld image loadability
|
||||
// also admits main executables and bundles for different operations.
|
||||
else if (selection.slice.file_type_code !== 6) outcome = "not-loadable";
|
||||
@@ -672,6 +671,7 @@ const projectTraceResult = (input: {
|
||||
readonly edges: readonly Edge[];
|
||||
readonly withoutArchitecture: readonly string[];
|
||||
readonly environmentRoots: ReadonlySet<string>;
|
||||
readonly unknownArchitectureCandidates: ReadonlySet<string>;
|
||||
readonly unknownPlatformCandidates: ReadonlySet<string>;
|
||||
readonly undecodableSymlinkTargets: ReadonlyMap<string, string>;
|
||||
readonly implicitMacOSPlatformCandidates: ReadonlySet<string>;
|
||||
@@ -705,6 +705,7 @@ const projectTraceResult = (input: {
|
||||
unparsed.length === 0 &&
|
||||
input.withoutArchitecture.length === 0 &&
|
||||
input.environmentRoots.size === 0 &&
|
||||
input.unknownArchitectureCandidates.size === 0 &&
|
||||
input.unknownPlatformCandidates.size === 0 &&
|
||||
input.undecodableSymlinkTargets.size === 0 &&
|
||||
input.rootEnumeration?.status !== "unknown"
|
||||
@@ -726,6 +727,11 @@ const projectTraceResult = (input: {
|
||||
: [
|
||||
`Roots ${[...input.environmentRoots].join(", ")} request applicable image-selection inputs through LC_DYLD_ENVIRONMENT that are not modeled; affected dependencies or inserted images remain uncertain.`,
|
||||
]),
|
||||
...(input.unknownArchitectureCandidates.size === 0
|
||||
? []
|
||||
: [
|
||||
`In-root dylib candidates ${[...input.unknownArchitectureCandidates].sort(compare).join(", ")} have unknown architecture compatibility and are not treated as incompatible. Their dependent graphs may be incomplete.`,
|
||||
]),
|
||||
...(input.unknownPlatformCandidates.size === 0
|
||||
? []
|
||||
: [
|
||||
@@ -760,6 +766,7 @@ export const traceDylibLoading = async (
|
||||
const edges: Edge[] = [];
|
||||
const withoutArchitecture: string[] = [];
|
||||
const environmentRoots = new Set<string>();
|
||||
const unknownArchitectureCandidates = new Set<string>();
|
||||
const unknownPlatformCandidates = new Set<string>();
|
||||
const undecodableSymlinkTargets = new Map<string, string>();
|
||||
const implicitMacOSPlatformCandidates = new Set<string>();
|
||||
@@ -802,6 +809,7 @@ export const traceDylibLoading = async (
|
||||
},
|
||||
searchOverrides,
|
||||
environmentRoots,
|
||||
unknownArchitectureCandidates,
|
||||
unknownPlatformCandidates,
|
||||
undecodableSymlinkTargets,
|
||||
implicitMacOSPlatformCandidates,
|
||||
@@ -824,6 +832,7 @@ export const traceDylibLoading = async (
|
||||
edges,
|
||||
withoutArchitecture,
|
||||
environmentRoots,
|
||||
unknownArchitectureCandidates,
|
||||
unknownPlatformCandidates,
|
||||
undecodableSymlinkTargets,
|
||||
implicitMacOSPlatformCandidates,
|
||||
|
||||
@@ -164,7 +164,7 @@ const lazyConsequence = (weak: boolean): string =>
|
||||
export const DYLIB_RESOLUTION_LIMITATIONS = [
|
||||
"LC_LAZY_LOAD_DYLIB and LC_LAZY_LOAD_DYLIB_INFO dependencies are resolved but not traversed, because dyld loads them only on first use.",
|
||||
"Slices are matched by dyld's graded architectures (an x86_64h process also loads x86_64). arm64e processes that disable pointer authentication can also load arm64 slices; that fallback is not modeled.",
|
||||
"Absolute install names and rpaths are outside the analyzed root and are not evaluated, including /System and /usr/lib libraries that the dyld shared cache usually provides.",
|
||||
"Absolute install names and rpaths are evaluated only when spelled beneath the analyzed root. Other absolute paths remain outside the analyzed root, including /System and /usr/lib libraries that the dyld shared cache usually provides.",
|
||||
"Leaf and relative install names depend on dyld fallback paths, DYLD_* variables, and the working directory; they are undetermined.",
|
||||
"Load order follows dyld's dependents-first traversal in load-command order. An image reached through several chains is resolved once per process, with the rpath stack and conditionality of the first chain; a later @rpath request whose install name matches an already loaded image reuses it.",
|
||||
"@loader_path uses each image's symlink-resolved path within the analyzed root.",
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
import { expect, it } from "vitest";
|
||||
import { machoSliceEncryptionSchema } from "./machoEncryption.js";
|
||||
|
||||
it("requires a malformed cause exactly for malformed slice encryption", () => {
|
||||
const slice = {
|
||||
architecture: null,
|
||||
cpu_type: null,
|
||||
cpu_subtype: null,
|
||||
container_file_offset: 0,
|
||||
size: 32,
|
||||
reason: null,
|
||||
commands: [],
|
||||
range: null,
|
||||
};
|
||||
for (const status of [
|
||||
"absent",
|
||||
"encrypted",
|
||||
"not-encrypted",
|
||||
"unknown",
|
||||
"malformed",
|
||||
]) {
|
||||
for (const malformed_kind of [null, "structure", "duplicate-commands"]) {
|
||||
expect(
|
||||
machoSliceEncryptionSchema.safeParse({
|
||||
...slice,
|
||||
status,
|
||||
malformed_kind,
|
||||
}).success,
|
||||
`${status}/${String(malformed_kind)}`,
|
||||
).toBe((status === "malformed") === (malformed_kind !== null));
|
||||
}
|
||||
}
|
||||
expect(
|
||||
machoSliceEncryptionSchema.safeParse({ ...slice, status: "absent" })
|
||||
.success,
|
||||
).toBe(false);
|
||||
});
|
||||
@@ -78,8 +78,15 @@ export const machoEncryptionStatusSchema = z.enum([
|
||||
"unknown",
|
||||
]);
|
||||
|
||||
/** Load-command encryption state of one Mach-O slice. */
|
||||
export const machoSliceEncryptionSchema = z.object({
|
||||
const malformedKinds = ["structure", "duplicate-commands"] as const;
|
||||
const malformedKind = z
|
||||
.enum(malformedKinds)
|
||||
.nullable()
|
||||
.describe(
|
||||
"Malformed cause owned by the structural reader; duplicate-commands means every encryption command was structurally valid. Null for all other statuses.",
|
||||
);
|
||||
|
||||
const sliceEncryptionFields = {
|
||||
architecture: z
|
||||
.string()
|
||||
.nullable()
|
||||
@@ -93,14 +100,65 @@ export const machoSliceEncryptionSchema = z.object({
|
||||
status: machoEncryptionStatusSchema.describe(
|
||||
"absent only when every load command was read; malformed and unknown carry a reason.",
|
||||
),
|
||||
malformed_kind: malformedKind,
|
||||
reason: z.string().nullable(),
|
||||
commands: z
|
||||
.array(machoEncryptionCommandSchema)
|
||||
.describe(
|
||||
"Encryption load commands in table order; a slice with more than two keeps the first two and states the count in reason.",
|
||||
"Encryption load commands in table order; a completed slice with more than two keeps the first two and states the total count in reason. Structural failures identify the invalid command, including commands beyond the retained pair.",
|
||||
),
|
||||
range: machoEncryptedRangeSchema.nullable(),
|
||||
});
|
||||
};
|
||||
|
||||
const validateMalformedKind = (
|
||||
slice: { status: string; malformed_kind?: string | null | undefined },
|
||||
context: z.RefinementCtx,
|
||||
): void => {
|
||||
if (
|
||||
slice.malformed_kind !== undefined &&
|
||||
(slice.status === "malformed") !== (slice.malformed_kind !== null)
|
||||
)
|
||||
context.addIssue({
|
||||
code: "custom",
|
||||
path: ["malformed_kind"],
|
||||
message: "A malformed cause is required exactly when status is malformed",
|
||||
});
|
||||
};
|
||||
|
||||
/** Load-command encryption state of one newly inspected Mach-O slice. */
|
||||
export const machoSliceEncryptionSchema = z
|
||||
.object(sliceEncryptionFields)
|
||||
.superRefine(validateMalformedKind);
|
||||
|
||||
/** View rows also report when a historical malformed cause was not recorded. */
|
||||
export const machoSliceEncryptionViewSchema = z
|
||||
.strictObject({
|
||||
...sliceEncryptionFields,
|
||||
malformed_kind: z
|
||||
.enum([...malformedKinds, "unrecorded"])
|
||||
.nullable()
|
||||
.describe(
|
||||
"Structural cause or duplicate-command ambiguity. Unrecorded means the historical inspection did not classify the cause. Null for other statuses.",
|
||||
),
|
||||
})
|
||||
.superRefine(validateMalformedKind);
|
||||
|
||||
/** Interpret earlier slice records without inferring a cause from their command count. */
|
||||
export const retainedMachoSliceEncryptionSchema = z
|
||||
.object({
|
||||
...sliceEncryptionFields,
|
||||
malformed_kind: malformedKind.exactOptional(),
|
||||
})
|
||||
.superRefine(validateMalformedKind)
|
||||
.transform((slice): z.output<typeof machoSliceEncryptionViewSchema> => ({
|
||||
...slice,
|
||||
malformed_kind:
|
||||
slice.malformed_kind === undefined
|
||||
? slice.status === "malformed"
|
||||
? "unrecorded"
|
||||
: null
|
||||
: slice.malformed_kind,
|
||||
}));
|
||||
|
||||
export type MachoEncryptionCommand = z.infer<
|
||||
typeof machoEncryptionCommandSchema
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { z } from "zod";
|
||||
import { MFT_INLINE_HEADER_LIMIT } from "./windows/ntfsMft.js";
|
||||
|
||||
import { jsonRecordSchema } from "./jsonRecord.js";
|
||||
import { jsonValueSchema } from "./jsonValue.js";
|
||||
@@ -299,6 +300,56 @@ export const hexRecordRegionMetadataSchema = z.strictObject({
|
||||
last_line: offset,
|
||||
});
|
||||
|
||||
const ntfsFileReferenceSchema = z.strictObject({
|
||||
recordNumber: offset,
|
||||
sequenceNumber: offset,
|
||||
});
|
||||
const ntfsRecordHeaderSchema = z.strictObject({
|
||||
index: offset,
|
||||
fileOffset: offset,
|
||||
sequenceNumber: offset,
|
||||
hardLinkCount: offset,
|
||||
flags: z.strictObject({
|
||||
raw: offset,
|
||||
names: z.array(z.string()),
|
||||
unknownMask: offset,
|
||||
}),
|
||||
inUse: z.boolean(),
|
||||
directory: z.boolean(),
|
||||
usedBytes: offset,
|
||||
totalBytes: offset,
|
||||
extentValid: z.boolean(),
|
||||
baseRecordReference: ntfsFileReferenceSchema.nullable(),
|
||||
declaredRecordNumber: offset.nullable(),
|
||||
recordNumberMatchesSlot: z.boolean().nullable(),
|
||||
logFileSequenceNumber: z.string().regex(/^(?:0|[1-9][0-9]*)$/u),
|
||||
firstAttributeOffset: offset,
|
||||
nextAttributeId: offset,
|
||||
fixups: z.strictObject({
|
||||
sequenceNumber: offset,
|
||||
entries: offset,
|
||||
verifiedSectors: offset,
|
||||
coveredSectors: offset,
|
||||
mismatchSector: offset.nullable(),
|
||||
malformed: z.boolean(),
|
||||
}),
|
||||
});
|
||||
|
||||
/** NTFS $MFT record-header facts; attributes, names and the USN journal are later steps. */
|
||||
export const ntfsMftMetadataSchema = z.strictObject({
|
||||
kind: z.literal("ntfs-mft"),
|
||||
record_bytes: offset,
|
||||
record_count: offset,
|
||||
in_use_record_count: offset,
|
||||
directory_record_count: offset,
|
||||
extension_record_count: offset,
|
||||
fixup_mismatch_count: offset,
|
||||
fixup_unverified_record_count: offset,
|
||||
truncated_tail_bytes: offset,
|
||||
record_headers: z.array(ntfsRecordHeaderSchema).max(MFT_INLINE_HEADER_LIMIT),
|
||||
omitted_record_headers: offset,
|
||||
});
|
||||
|
||||
/**
|
||||
* U-Boot FIT root facts. Configuration references are declared names; a
|
||||
* reference that names no image is reported as a limitation, not removed.
|
||||
@@ -886,6 +937,7 @@ export const artifactFormatMetadataSchema = z.discriminatedUnion("kind", [
|
||||
espImageSignatureBlockMetadataSchema,
|
||||
uf2MetadataSchema,
|
||||
uf2RegionMetadataSchema,
|
||||
ntfsMftMetadataSchema,
|
||||
dfuSeMetadataSchema,
|
||||
dfuSeElementMetadataSchema,
|
||||
espFlashImageMetadataSchema,
|
||||
@@ -1036,6 +1088,10 @@ const declarationsByKind: {
|
||||
notCompared:
|
||||
"Its familyID and addresses are in its path, family_name is REA's label for the familyID, and its block counts and positions are layout; content comparison covers its bytes.",
|
||||
},
|
||||
"ntfs-mft": {
|
||||
notCompared:
|
||||
"Its fields come from the record headers in the file's own FILE records, which content comparison covers.",
|
||||
},
|
||||
dfuse: {
|
||||
notCompared:
|
||||
"Its fields come from the file's own prefix, target headers and suffix, which content comparison covers.",
|
||||
|
||||
@@ -103,6 +103,7 @@ export const ARTIFACT_FORMAT_IDS = [
|
||||
"dfuse",
|
||||
"esp-flash-image",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
"unknown",
|
||||
] as const;
|
||||
|
||||
@@ -124,6 +125,7 @@ const artifactContentFormatSchema = artifactFormatSchema.extract([
|
||||
"uf2",
|
||||
"dfuse",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
"mach-o-universal",
|
||||
"mach-o",
|
||||
"elf",
|
||||
|
||||
@@ -302,7 +302,8 @@ export type BinaryTarget =
|
||||
| "esp-image"
|
||||
| "uf2"
|
||||
| "dfuse"
|
||||
| "fit";
|
||||
| "fit"
|
||||
| "ntfs-mft";
|
||||
})
|
||||
| (BinaryTargetIdentity &
|
||||
NonExecutableMetadata & {
|
||||
|
||||
@@ -52,6 +52,7 @@ export const evidenceSubjectFormatSchema = z.enum([
|
||||
"dfuse",
|
||||
"esp-flash-image",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
]);
|
||||
|
||||
/** Format-owned architecture declarations shared by Evidence and persisted executions. */
|
||||
|
||||
@@ -137,7 +137,8 @@ describe("child-process options detection", () => {
|
||||
["negative-zero", `spawn("tool", [], { env: -0 })`, false],
|
||||
["bigint-zero", `spawn("tool", [], { env: 0n })`, false],
|
||||
["zero-float", `spawn("tool", [], { env: 0.0 })`, false],
|
||||
["nan", `spawn("tool", [], { env: NaN })`, true],
|
||||
["nan", `spawn("tool", [], { env: NaN })`, false],
|
||||
["shadowed-nan", `((NaN) => spawn("tool", [], { env: NaN }))({})`, true],
|
||||
["empty-string", `spawn("tool", [], { env: "" })`, false],
|
||||
["false", `spawn("tool", [], { env: false })`, false],
|
||||
["empty-object", `spawn("tool", [], { env: {} })`, true],
|
||||
|
||||
@@ -81,7 +81,7 @@ export const collectJavaScriptSemanticChildProcesses = (
|
||||
!rejectsOptionsShape(candidate, context, state),
|
||||
);
|
||||
const childProcessSpawns = candidates.map((candidate) =>
|
||||
immutableSpawn(candidate, context),
|
||||
immutableSpawn(candidate, context, state),
|
||||
);
|
||||
return {
|
||||
childProcessSpawns,
|
||||
@@ -146,6 +146,7 @@ const collectSpawns = (
|
||||
const immutableSpawn = (
|
||||
candidate: SpawnCandidate,
|
||||
context: ChildSpawnContext,
|
||||
state: JavaScriptSemanticAnalysisState,
|
||||
): JavaScriptSemanticChildProcessSpawn => {
|
||||
const { options, argvCount } = spawnArguments(candidate, context);
|
||||
const command = dataEffectLiteralString(candidate.node.arguments[0]);
|
||||
@@ -161,7 +162,7 @@ const immutableSpawn = (
|
||||
projectedResultBindings: candidate.projectedResultBindings,
|
||||
command,
|
||||
argvCount,
|
||||
environmentSupplied: environmentSupplied(options, context),
|
||||
environmentSupplied: environmentSupplied(options, context, state),
|
||||
stdioMode: stdioMode(options, candidate.method, context),
|
||||
resolution: command === null ? "partial" : "complete",
|
||||
};
|
||||
@@ -443,11 +444,17 @@ const spawnArguments = (
|
||||
const environmentSupplied = (
|
||||
options: t.Node | undefined,
|
||||
context: ChildSpawnContext,
|
||||
state: JavaScriptSemanticAnalysisState,
|
||||
): boolean => {
|
||||
const lookup = staticObjectProperty(options, "env", context.isNullish);
|
||||
if (lookup.status !== "explicit") return false;
|
||||
const value = unwrapJavaScriptExpression(lookup.value).node;
|
||||
if (context.isNullish(value)) return false;
|
||||
if (
|
||||
t.isIdentifier(value, { name: "NaN" }) &&
|
||||
isUnshadowedGlobal(value, state, "NaN")
|
||||
)
|
||||
return false;
|
||||
return staticJavaScriptTruthiness(value) !== false;
|
||||
};
|
||||
|
||||
|
||||
@@ -83,6 +83,7 @@ export const liveBinaryTargetSummaryVariants = [
|
||||
"uf2",
|
||||
"dfuse",
|
||||
"fit",
|
||||
"ntfs-mft",
|
||||
]),
|
||||
architecture: z.null(),
|
||||
}),
|
||||
|
||||
@@ -2,7 +2,10 @@ import { z } from "zod";
|
||||
import { bundleResourceRootSchema } from "../apple/bundleResourceRoot.js";
|
||||
import { jsonRecordSchema } from "../jsonRecord.js";
|
||||
import { jsonValueSchema } from "../jsonValue.js";
|
||||
import { machoSliceEncryptionSchema } from "../apple/machoEncryption.js";
|
||||
import {
|
||||
machoSliceEncryptionSchema,
|
||||
retainedMachoSliceEncryptionSchema,
|
||||
} from "../apple/machoEncryption.js";
|
||||
|
||||
const hexAddress = z.string().regex(/^0x[a-fA-F0-9]+$/u);
|
||||
const bytesHex = z.string().regex(/^(?:[0-9a-f]{2})*$/u);
|
||||
@@ -223,7 +226,9 @@ export const inspectMachoSchema = z.object({
|
||||
* slice is encrypted.
|
||||
*/
|
||||
export const retainedInspectMachoSchema = inspectMachoSchema
|
||||
.extend({ encryption: inspectMachoSchema.shape.encryption.optional() })
|
||||
.extend({
|
||||
encryption: coverage(retainedMachoSliceEncryptionSchema).optional(),
|
||||
})
|
||||
.transform(({ encryption, ...report }) => ({
|
||||
...report,
|
||||
encryption: encryption ?? {
|
||||
|
||||
@@ -0,0 +1,478 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
|
||||
import {
|
||||
MFT_DEFAULT_RECORD_BYTES,
|
||||
MFT_MAX_FILE_BYTES,
|
||||
createMftDecoder,
|
||||
parseMftImage,
|
||||
} from "./ntfsMft.js";
|
||||
|
||||
interface RecordOptions {
|
||||
readonly sequenceNumber?: number;
|
||||
readonly hardLinkCount?: number;
|
||||
readonly flags?: number;
|
||||
readonly baseRecordReference?: bigint;
|
||||
readonly recordBytes?: number;
|
||||
/** Write a wrong trailer value into this sector, leaving the others correct. */
|
||||
readonly corruptSector?: number;
|
||||
/** Truncate the update sequence array to this many entries; 0 omits it. */
|
||||
readonly usaEntries?: number;
|
||||
readonly usaOffset?: number;
|
||||
}
|
||||
|
||||
/** One FILE record with a zeroed body and fixups applied the way NTFS writes them. */
|
||||
const recordOf = (options: RecordOptions = {}): Uint8Array => {
|
||||
const recordBytes = options.recordBytes ?? MFT_DEFAULT_RECORD_BYTES;
|
||||
const record = new Uint8Array(recordBytes);
|
||||
const view = new DataView(record.buffer);
|
||||
record.set(Buffer.from("FILE", "latin1"), 0);
|
||||
const sequenceNumber = options.sequenceNumber ?? 1;
|
||||
const sectors = recordBytes / 512;
|
||||
|
||||
const usaEntries = options.usaEntries ?? sectors + 1;
|
||||
if (usaEntries > 0) {
|
||||
const usaOffset = options.usaOffset ?? 48;
|
||||
view.setUint16(4, usaOffset, true);
|
||||
view.setUint16(6, usaEntries, true);
|
||||
view.setUint16(usaOffset, sequenceNumber, true);
|
||||
for (let sector = 0; sector < sectors; sector += 1) {
|
||||
const trailer = sector * 512 + 510;
|
||||
// A saved trailer is what the sector held before the fixup replaced it.
|
||||
view.setUint16(usaOffset + 2 * (sector + 1), 0xa5a5, true);
|
||||
view.setUint16(
|
||||
trailer,
|
||||
sector >= usaEntries - 1
|
||||
? 0xa5a5
|
||||
: sector === options.corruptSector
|
||||
? 0x1234
|
||||
: sequenceNumber,
|
||||
true,
|
||||
);
|
||||
}
|
||||
} else {
|
||||
view.setUint16(4, 0, true);
|
||||
view.setUint16(6, 0, true);
|
||||
}
|
||||
|
||||
view.setUint16(16, sequenceNumber, true);
|
||||
view.setUint16(18, options.hardLinkCount ?? 1, true);
|
||||
const firstAttributeOffset =
|
||||
Math.ceil((48 + Math.max(0, usaEntries) * 2) / 8) * 8;
|
||||
view.setUint16(20, firstAttributeOffset, true);
|
||||
view.setUint16(22, options.flags ?? 0x0001, true);
|
||||
view.setUint32(24, firstAttributeOffset + 8, true);
|
||||
view.setUint32(firstAttributeOffset, 0xffff_ffff, true);
|
||||
view.setUint32(28, recordBytes, true);
|
||||
view.setBigUint64(32, options.baseRecordReference ?? 0n, true);
|
||||
view.setUint16(40, 0, true);
|
||||
return record;
|
||||
};
|
||||
|
||||
const streamOf = (...records: readonly Uint8Array[]): Uint8Array => {
|
||||
const total = records.reduce((sum, record) => sum + record.length, 0);
|
||||
const stream = new Uint8Array(total);
|
||||
let offset = 0;
|
||||
for (const record of records) {
|
||||
stream.set(record, offset);
|
||||
const view = new DataView(stream.buffer, offset, record.length);
|
||||
if (view.getUint16(4, true) >= 48)
|
||||
view.setUint32(44, offset / record.length, true);
|
||||
offset += record.length;
|
||||
}
|
||||
return stream;
|
||||
};
|
||||
|
||||
describe("MFT header facts", () => {
|
||||
it("inventories a clean record's header and verified fixups", () => {
|
||||
const parsed = parseMftImage(streamOf(recordOf({ sequenceNumber: 5 })));
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.metadata).toMatchObject({
|
||||
kind: "ntfs-mft",
|
||||
record_bytes: MFT_DEFAULT_RECORD_BYTES,
|
||||
record_count: 1,
|
||||
in_use_record_count: 1,
|
||||
directory_record_count: 0,
|
||||
extension_record_count: 0,
|
||||
fixup_mismatch_count: 0,
|
||||
fixup_unverified_record_count: 0,
|
||||
truncated_tail_bytes: 0,
|
||||
});
|
||||
expect(parsed.value.records[0]).toMatchObject({
|
||||
index: 0,
|
||||
fileOffset: 0,
|
||||
sequenceNumber: 5,
|
||||
inUse: true,
|
||||
directory: false,
|
||||
baseRecordReference: null,
|
||||
firstAttributeOffset: 56,
|
||||
fixups: {
|
||||
sequenceNumber: 5,
|
||||
verifiedSectors: 2,
|
||||
coveredSectors: 2,
|
||||
mismatchSector: null,
|
||||
malformed: false,
|
||||
},
|
||||
});
|
||||
expect(parsed.value.limitations).toEqual([]);
|
||||
});
|
||||
|
||||
it("identifies unrecognized flags without losing their source bits", () => {
|
||||
const parsed = parseMftImage(recordOf({ flags: 0x8001 }));
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.metadata.record_headers[0]?.flags).toEqual({
|
||||
raw: 0x8001,
|
||||
names: ["in-use"],
|
||||
unknownMask: 0x8000,
|
||||
});
|
||||
});
|
||||
|
||||
it.each([0, 49, 64, 72])(
|
||||
"reports an invalid first attribute offset %i",
|
||||
(offset) => {
|
||||
const record = recordOf();
|
||||
new DataView(record.buffer).setUint16(20, offset, true);
|
||||
const parsed = parseMftImage(record);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records[0]?.extentValid).toBe(false);
|
||||
expect(parsed.value.limitations.join(" ")).toContain("inconsistent");
|
||||
},
|
||||
);
|
||||
|
||||
it("reports a declared record number that contradicts its stream position", () => {
|
||||
const bytes = streamOf(recordOf(), recordOf());
|
||||
new DataView(bytes.buffer).setUint32(1024 + 44, 0, true);
|
||||
const parsed = parseMftImage(bytes);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records[1]).toMatchObject({
|
||||
index: 1,
|
||||
declaredRecordNumber: 0,
|
||||
recordNumberMatchesSlot: false,
|
||||
});
|
||||
expect(parsed.value.limitations.join(" ")).toContain(
|
||||
"disagrees with their stream slot",
|
||||
);
|
||||
});
|
||||
|
||||
it("keeps the inline header window separate from the parsed record count", () => {
|
||||
const parsed = parseMftImage(
|
||||
streamOf(...Array.from({ length: 33 }, () => recordOf())),
|
||||
);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.metadata).toMatchObject({
|
||||
record_count: 33,
|
||||
omitted_record_headers: 1,
|
||||
});
|
||||
expect(parsed.value.metadata.record_headers).toHaveLength(32);
|
||||
expect(parsed.value.records).toHaveLength(33);
|
||||
expect(parsed.value.limitations).toEqual([]);
|
||||
});
|
||||
|
||||
it("preserves a log sequence number above the safe integer range", () => {
|
||||
const record = recordOf();
|
||||
new DataView(record.buffer).setBigUint64(8, 9007199254740993n, true);
|
||||
const parsed = parseMftImage(record);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records[0]?.logFileSequenceNumber).toBe(
|
||||
"9007199254740993",
|
||||
);
|
||||
});
|
||||
|
||||
it("verifies the older FILE header without reading its fixup words as a record number", () => {
|
||||
const oldRecord = recordOf({ usaOffset: 42 });
|
||||
const newRecord = recordOf();
|
||||
new DataView(newRecord.buffer).setUint32(44, 1, true);
|
||||
|
||||
const parsed = parseMftImage(streamOf(oldRecord, newRecord));
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records).toMatchObject([
|
||||
{
|
||||
declaredRecordNumber: null,
|
||||
fixups: { malformed: false, verifiedSectors: 2 },
|
||||
},
|
||||
{
|
||||
declaredRecordNumber: 1,
|
||||
fixups: { malformed: false, verifiedSectors: 2 },
|
||||
},
|
||||
]);
|
||||
expect(parsed.value.limitations).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("MFT fixup coverage", () => {
|
||||
it.each([0, 0xffff])(
|
||||
"leaves reserved USA sequence %i unverified",
|
||||
(sequenceNumber) => {
|
||||
const parsed = parseMftImage(recordOf({ sequenceNumber }));
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records[0]?.fixups).toMatchObject({
|
||||
sequenceNumber,
|
||||
verifiedSectors: 0,
|
||||
malformed: true,
|
||||
});
|
||||
expect(parsed.value.metadata.fixup_unverified_record_count).toBe(1);
|
||||
expect(parsed.value.limitations.join(" ")).toContain(
|
||||
"invalid or incomplete",
|
||||
);
|
||||
},
|
||||
);
|
||||
|
||||
it("keeps a record whose sector trailer is not the sequence number, and reports it", () => {
|
||||
const parsed = parseMftImage(
|
||||
streamOf(recordOf(), recordOf({ sequenceNumber: 9, corruptSector: 1 })),
|
||||
);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.records[1]?.fixups).toMatchObject({
|
||||
sequenceNumber: 9,
|
||||
verifiedSectors: 1,
|
||||
mismatchSector: 1,
|
||||
});
|
||||
expect(parsed.value.metadata.fixup_mismatch_count).toBe(1);
|
||||
expect(parsed.value.limitations.join(" ")).toMatch(
|
||||
/1 record\(s\) hold a sector trailer/u,
|
||||
);
|
||||
});
|
||||
|
||||
it("treats a missing update sequence array as unverified rather than clean", () => {
|
||||
const parsed = parseMftImage(streamOf(recordOf({ usaEntries: 0 })));
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.records[0]?.fixups).toMatchObject({
|
||||
malformed: true,
|
||||
mismatchSector: null,
|
||||
coveredSectors: 0,
|
||||
});
|
||||
expect(parsed.value.metadata.fixup_mismatch_count).toBe(0);
|
||||
expect(parsed.value.metadata.fixup_unverified_record_count).toBe(1);
|
||||
expect(parsed.value.limitations.join(" ")).toMatch(
|
||||
/invalid or incomplete update sequence array/u,
|
||||
);
|
||||
});
|
||||
|
||||
it.each([
|
||||
[48, 4],
|
||||
[49, 3],
|
||||
[508, 3],
|
||||
])(
|
||||
"rejects a malformed update sequence array at %i with %i entries",
|
||||
(offset, count) => {
|
||||
const bytes = recordOf();
|
||||
const view = new DataView(bytes.buffer);
|
||||
view.setUint16(4, offset, true);
|
||||
view.setUint16(6, count, true);
|
||||
|
||||
const parsed = parseMftImage(bytes);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.records[0]?.fixups).toMatchObject({
|
||||
malformed: true,
|
||||
verifiedSectors: 0,
|
||||
});
|
||||
expect(parsed.value.metadata.fixup_unverified_record_count).toBe(1);
|
||||
},
|
||||
);
|
||||
|
||||
it("counts uncovered sectors independently of a mismatched trailer", () => {
|
||||
const parsed = parseMftImage(
|
||||
recordOf({ recordBytes: 4096, usaEntries: 3, corruptSector: 0 }),
|
||||
);
|
||||
if (!parsed.ok) throw new Error(parsed.error.message);
|
||||
expect(parsed.value.metadata).toMatchObject({
|
||||
fixup_mismatch_count: 1,
|
||||
fixup_unverified_record_count: 1,
|
||||
});
|
||||
expect(parsed.value.limitations.join(" ")).toContain(
|
||||
"invalid or incomplete",
|
||||
);
|
||||
});
|
||||
|
||||
it("reports an array that covers fewer sectors than the record has", () => {
|
||||
// A 4 KiB record holds eight sectors; a three-entry array leaves five unverified.
|
||||
const parsed = parseMftImage(
|
||||
streamOf(recordOf({ recordBytes: 4096, usaEntries: 3 })),
|
||||
);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.records[0]?.fixups).toMatchObject({
|
||||
coveredSectors: 2,
|
||||
verifiedSectors: 2,
|
||||
mismatchSector: null,
|
||||
malformed: false,
|
||||
});
|
||||
expect(parsed.value.metadata.fixup_unverified_record_count).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("MFT record slots", () => {
|
||||
it("distinguishes extension records from base records", () => {
|
||||
const parsed = parseMftImage(
|
||||
streamOf(
|
||||
recordOf(),
|
||||
recordOf({
|
||||
flags: 0x0005,
|
||||
baseRecordReference: 0xabcd_fedc_ba98_7654n,
|
||||
}),
|
||||
),
|
||||
);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.records[1]).toMatchObject({
|
||||
baseRecordReference: {
|
||||
recordNumber: 0xfedc_ba98_7654,
|
||||
sequenceNumber: 0xabcd,
|
||||
},
|
||||
flags: { raw: 0x0005, names: ["in-use", "system"] },
|
||||
});
|
||||
expect(parsed.value.metadata.extension_record_count).toBe(1);
|
||||
});
|
||||
|
||||
it("names directory records without losing the in-use flag", () => {
|
||||
const parsed = parseMftImage(streamOf(recordOf({ flags: 0x0003 })));
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.records[0]).toMatchObject({
|
||||
directory: true,
|
||||
inUse: true,
|
||||
flags: { names: ["in-use", "directory"] },
|
||||
});
|
||||
expect(parsed.value.metadata.directory_record_count).toBe(1);
|
||||
});
|
||||
|
||||
it("skips malformed and sparse slots without renumbering valid records", () => {
|
||||
const stream = streamOf(
|
||||
recordOf(),
|
||||
recordOf(),
|
||||
new Uint8Array(MFT_DEFAULT_RECORD_BYTES),
|
||||
recordOf(),
|
||||
);
|
||||
stream.set(Buffer.from("BAAD", "latin1"), MFT_DEFAULT_RECORD_BYTES);
|
||||
const parsed = parseMftImage(stream);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.metadata.record_count).toBe(2);
|
||||
expect(
|
||||
parsed.value.records.map(({ index, fileOffset }) => [index, fileOffset]),
|
||||
).toEqual([
|
||||
[0, 0],
|
||||
[3, 3 * MFT_DEFAULT_RECORD_BYTES],
|
||||
]);
|
||||
expect(parsed.value.limitations).toEqual([
|
||||
"record at 1024 does not begin with the FILE signature; 2 slot(s) without a FILE signature were found",
|
||||
]);
|
||||
});
|
||||
|
||||
it("keeps a trailing partial record out of the inventory", () => {
|
||||
const stream = new Uint8Array(1024 + 300);
|
||||
stream.set(recordOf(), 0);
|
||||
const parsed = parseMftImage(stream);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.metadata.record_count).toBe(1);
|
||||
expect(parsed.value.metadata.truncated_tail_bytes).toBe(300);
|
||||
expect(parsed.value.limitations.join(" ")).toMatch(
|
||||
/300 trailing byte\(s\)/u,
|
||||
);
|
||||
});
|
||||
|
||||
it("falls back to the default record size when record 0 declares none", () => {
|
||||
const record = recordOf();
|
||||
new DataView(record.buffer).setUint32(28, 0, true);
|
||||
const parsed = parseMftImage(record);
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.recordBytes).toBe(MFT_DEFAULT_RECORD_BYTES);
|
||||
expect(parsed.value.limitations.join(" ")).toMatch(
|
||||
/not a supported power of two/u,
|
||||
);
|
||||
});
|
||||
|
||||
it("reads a 4 KiB record at its declared size", () => {
|
||||
const parsed = parseMftImage(streamOf(recordOf({ recordBytes: 4096 })));
|
||||
expect(parsed.ok).toBe(true);
|
||||
if (!parsed.ok) return;
|
||||
expect(parsed.value.recordBytes).toBe(4096);
|
||||
expect(parsed.value.metadata.record_count).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("parseMftImage refusals and limits", () => {
|
||||
it("refuses a file shorter than one record header", () => {
|
||||
const parsed = parseMftImage(new Uint8Array(32));
|
||||
expect(parsed.ok).toBe(false);
|
||||
if (parsed.ok) return;
|
||||
expect(parsed.error.message).toMatch(
|
||||
/shorter than one 42-byte record header/u,
|
||||
);
|
||||
});
|
||||
|
||||
it("refuses bytes that do not start with the FILE signature", () => {
|
||||
const parsed = parseMftImage(Buffer.alloc(2048, 0x41));
|
||||
expect(parsed.ok).toBe(false);
|
||||
if (parsed.ok) return;
|
||||
expect(parsed.error.message).toMatch(
|
||||
/does not begin with the FILE signature/u,
|
||||
);
|
||||
});
|
||||
|
||||
it("refuses a file above the fixed ceiling", () => {
|
||||
const decoder = createMftDecoder(MFT_MAX_FILE_BYTES + 1);
|
||||
expect(decoder.ok).toBe(false);
|
||||
if (decoder.ok) return;
|
||||
expect(decoder.error).toMatchObject({
|
||||
kind: "limit",
|
||||
boundary: "file-size",
|
||||
});
|
||||
});
|
||||
|
||||
it("refuses streams that differ from the admitted byte count", () => {
|
||||
const stream = recordOf();
|
||||
const short = createMftDecoder(stream.length + 1);
|
||||
if (!short.ok) throw new Error(short.error.message);
|
||||
expect(short.value.write(stream).ok).toBe(true);
|
||||
expect(short.value.finish()).toMatchObject({
|
||||
ok: false,
|
||||
error: {
|
||||
kind: "format",
|
||||
message: "stream ended before the admitted file length",
|
||||
},
|
||||
});
|
||||
|
||||
const long = createMftDecoder(stream.length - 1);
|
||||
if (!long.ok) throw new Error(long.error.message);
|
||||
expect(long.value.write(stream)).toMatchObject({
|
||||
ok: false,
|
||||
error: {
|
||||
kind: "format",
|
||||
message: "received more bytes than the admitted file length",
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("returns the same inventory without retaining all the decoded records", () => {
|
||||
const bytes = streamOf(...Array.from({ length: 33 }, () => recordOf()));
|
||||
const decoder = createMftDecoder(bytes.length);
|
||||
const parsed = parseMftImage(bytes);
|
||||
if (!decoder.ok || !parsed.ok) throw new Error("invalid fixture");
|
||||
expect(decoder.value.write(bytes).ok).toBe(true);
|
||||
const inventory = decoder.value.finish();
|
||||
if (!inventory.ok) throw new Error(inventory.error.message);
|
||||
expect(inventory.value).not.toHaveProperty("records");
|
||||
expect(inventory.value.metadata).toEqual(parsed.value.metadata);
|
||||
expect(inventory.value.limitations).toEqual(parsed.value.limitations);
|
||||
});
|
||||
|
||||
it("decodes the same stream through the chunked decoder", () => {
|
||||
const stream = streamOf(recordOf(), recordOf({ flags: 0x0003 }));
|
||||
const decoder = createMftDecoder(stream.length);
|
||||
expect(decoder.ok).toBe(true);
|
||||
if (!decoder.ok) return;
|
||||
// Feed one byte past a record boundary so a chunk never aligns with a record.
|
||||
for (const chunk of [stream.subarray(0, 1025), stream.subarray(1025)])
|
||||
expect(decoder.value.write(chunk).ok).toBe(true);
|
||||
const image = decoder.value.finish();
|
||||
expect(image.ok).toBe(true);
|
||||
if (!image.ok) return;
|
||||
expect(image.value.metadata.record_count).toBe(2);
|
||||
expect(image.value.metadata.directory_record_count).toBe(1);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,512 @@
|
||||
import { err, ok, type Result } from "../result.js";
|
||||
import type {
|
||||
RegionDecodeFailure,
|
||||
RegionDecoder,
|
||||
} from "../firmware/regionDecoder.js";
|
||||
|
||||
/** An NTFS FILE record begins with this signature. */
|
||||
const MFT_FILE_RECORD_MAGIC = "FILE";
|
||||
const MFT_FILE_RECORD_MAGIC_BYTES = 4;
|
||||
/** The shortest header worth reading: a FILE record header ends at `nextAttributeId`. */
|
||||
const NTFS_MFT_MIN_RECORD_BYTES = 42;
|
||||
|
||||
const hasMftFileRecordSignature = (prefix: Uint8Array): boolean =>
|
||||
prefix.length >= MFT_FILE_RECORD_MAGIC_BYTES &&
|
||||
text(prefix.subarray(0, MFT_FILE_RECORD_MAGIC_BYTES)) ===
|
||||
MFT_FILE_RECORD_MAGIC;
|
||||
|
||||
/** A record's declared size is a power of two from 512 upward; 1024 is NTFS's default. */
|
||||
export const MFT_DEFAULT_RECORD_BYTES = 1024;
|
||||
const MFT_MIN_RECORD_BYTES = 512;
|
||||
const MFT_MAX_RECORD_BYTES = 65536;
|
||||
/** An update sequence array holds at least the sequence number and one fixup word. */
|
||||
const USA_MIN_ENTRIES = 2;
|
||||
/** NTFS fixes up one 512-byte sector at a time. */
|
||||
const FIXUP_SECTOR_BYTES = 512;
|
||||
/**
|
||||
* Fixed whole-file ceiling. Records are inventoried from their headers only;
|
||||
* attributes and their payloads are not decoded, so this is deliberately
|
||||
* smaller than a volume's MFT can be.
|
||||
*/
|
||||
export const MFT_MAX_FILE_BYTES = 512 * 1024 * 1024;
|
||||
/** Limit the inline header sample independently of full stream coverage. */
|
||||
export const MFT_INLINE_HEADER_LIMIT = 32;
|
||||
|
||||
/** FILE record header fields; offsets are from the record start. */
|
||||
const RECORD_HEADER = {
|
||||
updateSequenceOffset: 4,
|
||||
updateSequenceCount: 6,
|
||||
logFileSequenceNumber: 8,
|
||||
sequenceNumber: 16,
|
||||
hardLinkCount: 18,
|
||||
firstAttributeOffset: 20,
|
||||
flags: 22,
|
||||
usedBytes: 24,
|
||||
totalBytes: 28,
|
||||
baseRecordReference: 32,
|
||||
nextAttributeId: 40,
|
||||
recordNumber: 44,
|
||||
} as const;
|
||||
const RECORD_HEADER_WITH_NUMBER_BYTES = 48;
|
||||
|
||||
const FILE_RECORD_IN_USE = 0x0001;
|
||||
const FILE_RECORD_IS_DIRECTORY = 0x0002;
|
||||
const FILE_RECORD_NAMES = new Map<number, string>([
|
||||
[FILE_RECORD_IN_USE, "in-use"],
|
||||
[FILE_RECORD_IS_DIRECTORY, "directory"],
|
||||
[0x0004, "system"],
|
||||
[0x0008, "view-index"],
|
||||
]);
|
||||
|
||||
export interface MftRecordFixups {
|
||||
/** The update sequence number the array's first entry holds, or 0 when absent. */
|
||||
readonly sequenceNumber: number;
|
||||
readonly entries: number;
|
||||
/** Sectors whose trailer held the sequence number before a mismatch. */
|
||||
readonly verifiedSectors: number;
|
||||
/** Sectors the array covers; fewer than the record's sectors leaves a tail unverified. */
|
||||
readonly coveredSectors: number;
|
||||
/** The first sector whose trailer did not hold the sequence number, if any. */
|
||||
readonly mismatchSector: number | null;
|
||||
/** The array itself is missing, misplaced or too short to cover one sector. */
|
||||
readonly malformed: boolean;
|
||||
}
|
||||
|
||||
export interface MftFileReference {
|
||||
readonly recordNumber: number;
|
||||
readonly sequenceNumber: number;
|
||||
}
|
||||
|
||||
const decodeMftFileReference = (reference: bigint): MftFileReference => ({
|
||||
recordNumber: Number(reference & 0xffff_ffff_ffffn),
|
||||
sequenceNumber: Number(reference >> 48n),
|
||||
});
|
||||
|
||||
export interface MftRecord {
|
||||
/** Zero-based ordinal of this record in the stream. */
|
||||
readonly index: number;
|
||||
/** File offset where the record starts. */
|
||||
readonly fileOffset: number;
|
||||
readonly sequenceNumber: number;
|
||||
/** Hard link count as recorded; a zero count marks a record with no names. */
|
||||
readonly hardLinkCount: number;
|
||||
readonly flags: {
|
||||
readonly raw: number;
|
||||
readonly names: readonly string[];
|
||||
readonly unknownMask: number;
|
||||
};
|
||||
readonly inUse: boolean;
|
||||
readonly directory: boolean;
|
||||
/** Used and allocated byte counts as declared by the FILE record. */
|
||||
readonly usedBytes: number;
|
||||
readonly totalBytes: number;
|
||||
readonly extentValid: boolean;
|
||||
/** The base record this is an extension of, or `null` for a base record. */
|
||||
readonly baseRecordReference: MftFileReference | null;
|
||||
/** The record number the header declares; `null` when the header predates the field. */
|
||||
readonly declaredRecordNumber: number | null;
|
||||
readonly recordNumberMatchesSlot: boolean | null;
|
||||
/** `$LogFile` sequence number as recorded; no log is read. */
|
||||
readonly logFileSequenceNumber: string;
|
||||
/** Declared offset of the first attribute; no attribute decoding follows yet. */
|
||||
readonly firstAttributeOffset: number;
|
||||
/** Declared id of the next attribute; no attribute decoding follows yet. */
|
||||
readonly nextAttributeId: number;
|
||||
readonly fixups: MftRecordFixups;
|
||||
}
|
||||
|
||||
export interface MftInventory {
|
||||
readonly metadata: MftMetadata;
|
||||
/** The record size the stream declared, or the fixed default when it did not. */
|
||||
readonly recordBytes: number;
|
||||
readonly limitations: readonly string[];
|
||||
}
|
||||
|
||||
export interface MftImage extends MftInventory {
|
||||
readonly records: readonly MftRecord[];
|
||||
}
|
||||
|
||||
export interface MftMetadata {
|
||||
readonly kind: "ntfs-mft";
|
||||
readonly record_bytes: number;
|
||||
readonly record_count: number;
|
||||
readonly in_use_record_count: number;
|
||||
readonly directory_record_count: number;
|
||||
readonly extension_record_count: number;
|
||||
readonly fixup_mismatch_count: number;
|
||||
readonly fixup_unverified_record_count: number;
|
||||
readonly truncated_tail_bytes: number;
|
||||
readonly record_headers: readonly MftRecord[];
|
||||
readonly omitted_record_headers: number;
|
||||
}
|
||||
|
||||
const text = (ascii: Uint8Array): string =>
|
||||
Buffer.from(ascii).toString("latin1");
|
||||
|
||||
const failure = (
|
||||
message: string,
|
||||
boundary?: RegionDecodeFailure["boundary"],
|
||||
): RegionDecodeFailure => ({
|
||||
kind: "format",
|
||||
message,
|
||||
...(boundary === undefined ? {} : { boundary }),
|
||||
});
|
||||
|
||||
const limit = (
|
||||
message: string,
|
||||
boundary?: RegionDecodeFailure["boundary"],
|
||||
): RegionDecodeFailure => ({
|
||||
kind: "limit",
|
||||
message,
|
||||
...(boundary === undefined ? {} : { boundary }),
|
||||
});
|
||||
|
||||
const parseRecordFlags = (raw: number): MftRecord["flags"] => {
|
||||
const names: string[] = [];
|
||||
let unknownMask = raw;
|
||||
for (const [bit, name] of FILE_RECORD_NAMES) {
|
||||
if ((raw & bit) !== 0) names.push(name);
|
||||
unknownMask &= ~bit;
|
||||
}
|
||||
return { raw, names, unknownMask };
|
||||
};
|
||||
|
||||
const isRecordSize = (bytes: number): boolean =>
|
||||
bytes >= MFT_MIN_RECORD_BYTES &&
|
||||
bytes <= MFT_MAX_RECORD_BYTES &&
|
||||
(bytes & (bytes - 1)) === 0;
|
||||
|
||||
const updateSequenceArrayFits = (
|
||||
offset: number,
|
||||
entries: number,
|
||||
sectors: number,
|
||||
): boolean =>
|
||||
entries >= USA_MIN_ENTRIES &&
|
||||
entries <= sectors + 1 &&
|
||||
offset >= NTFS_MFT_MIN_RECORD_BYTES &&
|
||||
offset % 2 === 0 &&
|
||||
offset + entries * 2 <= FIXUP_SECTOR_BYTES - 2;
|
||||
|
||||
/** Recognize a FILE header without requiring its trailers or attributes to verify. */
|
||||
export const hasMftFileRecordHeader = (prefix: Uint8Array): boolean => {
|
||||
if (
|
||||
prefix.length < NTFS_MFT_MIN_RECORD_BYTES ||
|
||||
!hasMftFileRecordSignature(prefix)
|
||||
)
|
||||
return false;
|
||||
const view = new DataView(
|
||||
prefix.buffer,
|
||||
prefix.byteOffset,
|
||||
prefix.byteLength,
|
||||
);
|
||||
return (
|
||||
isRecordSize(view.getUint32(RECORD_HEADER.totalBytes, true)) ||
|
||||
updateSequenceArrayFits(
|
||||
view.getUint16(RECORD_HEADER.updateSequenceOffset, true),
|
||||
view.getUint16(RECORD_HEADER.updateSequenceCount, true),
|
||||
MFT_DEFAULT_RECORD_BYTES / FIXUP_SECTOR_BYTES,
|
||||
)
|
||||
);
|
||||
};
|
||||
|
||||
/**
|
||||
* Parse FILE record headers and verify their update-sequence fixups.
|
||||
*
|
||||
* Only the record structure is established: attributes, their names, the
|
||||
* filenames and the USN journal are left to later steps, so no path, timestamp
|
||||
* or file identity beyond the record itself is claimed. A record whose fixup
|
||||
* does not match keeps its header facts, because the stream still declares it,
|
||||
* and the mismatch is reported on the record and counted in the metadata.
|
||||
*/
|
||||
export const parseMftImage = (
|
||||
bytes: Uint8Array,
|
||||
): Result<MftImage, RegionDecodeFailure> => {
|
||||
const records: MftRecord[] = [];
|
||||
const inventory = scanMft(bytes, records);
|
||||
return inventory.ok ? ok({ ...inventory.value, records }) : inventory;
|
||||
};
|
||||
|
||||
const scanMft = (
|
||||
bytes: Uint8Array,
|
||||
retainedRecords?: MftRecord[],
|
||||
): Result<MftInventory, RegionDecodeFailure> => {
|
||||
if (bytes.length < NTFS_MFT_MIN_RECORD_BYTES)
|
||||
return err(
|
||||
failure(
|
||||
`file is ${String(bytes.length)} bytes, shorter than one ${String(NTFS_MFT_MIN_RECORD_BYTES)}-byte record header`,
|
||||
),
|
||||
);
|
||||
if (!hasMftFileRecordSignature(bytes))
|
||||
return err(failure("record 0 does not begin with the FILE signature"));
|
||||
|
||||
const limitations: string[] = [];
|
||||
const header = new DataView(bytes.buffer, bytes.byteOffset, bytes.byteLength);
|
||||
const declaredRecordBytes = header.getUint32(RECORD_HEADER.totalBytes, true);
|
||||
const recordBytes = isRecordSize(declaredRecordBytes)
|
||||
? declaredRecordBytes
|
||||
: MFT_DEFAULT_RECORD_BYTES;
|
||||
if (!isRecordSize(declaredRecordBytes))
|
||||
limitations.push(
|
||||
`record 0 declares a record size of ${String(declaredRecordBytes)} bytes, which is not a supported power of two from ${String(MFT_MIN_RECORD_BYTES)} to ${String(MFT_MAX_RECORD_BYTES)}; records were read at the ${String(MFT_DEFAULT_RECORD_BYTES)}-byte default`,
|
||||
);
|
||||
|
||||
const recordHeaders: MftRecord[] = [];
|
||||
let recordCount = 0;
|
||||
let inUseCount = 0;
|
||||
let directoryCount = 0;
|
||||
let extensionCount = 0;
|
||||
let mismatchCount = 0;
|
||||
let unverifiedCount = 0;
|
||||
let invalidSlots = 0;
|
||||
let invalidExtents = 0;
|
||||
let inconsistentRecordNumbers = 0;
|
||||
let firstInvalidExtentOffset: number | undefined;
|
||||
let firstInvalidOffset: number | undefined;
|
||||
for (
|
||||
let offset = 0;
|
||||
offset + recordBytes <= bytes.length;
|
||||
offset += recordBytes
|
||||
) {
|
||||
if (
|
||||
!hasMftFileRecordSignature(
|
||||
bytes.subarray(offset, offset + MFT_FILE_RECORD_MAGIC_BYTES),
|
||||
)
|
||||
) {
|
||||
invalidSlots += 1;
|
||||
firstInvalidOffset ??= offset;
|
||||
if (!isRecordSize(declaredRecordBytes)) break;
|
||||
continue;
|
||||
}
|
||||
const record = readRecord(bytes, offset, offset / recordBytes, recordBytes);
|
||||
retainedRecords?.push(record);
|
||||
if (recordHeaders.length < MFT_INLINE_HEADER_LIMIT)
|
||||
recordHeaders.push(record);
|
||||
recordCount += 1;
|
||||
if (record.inUse) inUseCount += 1;
|
||||
if (record.directory) directoryCount += 1;
|
||||
if (record.baseRecordReference !== null) extensionCount += 1;
|
||||
if (record.fixups.mismatchSector !== null) mismatchCount += 1;
|
||||
if (
|
||||
record.fixups.malformed ||
|
||||
record.fixups.coveredSectors < recordBytes / FIXUP_SECTOR_BYTES
|
||||
)
|
||||
unverifiedCount += 1;
|
||||
if (record.recordNumberMatchesSlot === false)
|
||||
inconsistentRecordNumbers += 1;
|
||||
if (!record.extentValid) {
|
||||
invalidExtents += 1;
|
||||
firstInvalidExtentOffset ??= offset;
|
||||
}
|
||||
}
|
||||
if (firstInvalidOffset !== undefined)
|
||||
limitations.push(
|
||||
`record at ${String(firstInvalidOffset)} does not begin with the FILE signature; ${String(invalidSlots)} slot(s) without a FILE signature were found`,
|
||||
);
|
||||
|
||||
if (firstInvalidExtentOffset !== undefined)
|
||||
limitations.push(
|
||||
`${String(invalidExtents)} FILE record(s) declare inconsistent record extents, beginning at offset ${String(firstInvalidExtentOffset)}`,
|
||||
);
|
||||
|
||||
if (inconsistentRecordNumbers !== 0)
|
||||
limitations.push(
|
||||
`${String(inconsistentRecordNumbers)} FILE record(s) declare a record number that disagrees with their stream slot`,
|
||||
);
|
||||
|
||||
const truncatedTailBytes = bytes.length % recordBytes;
|
||||
if (truncatedTailBytes !== 0)
|
||||
limitations.push(
|
||||
`${String(truncatedTailBytes)} trailing byte(s) do not fill a ${String(recordBytes)}-byte record and were not parsed`,
|
||||
);
|
||||
|
||||
if (mismatchCount !== 0)
|
||||
limitations.push(
|
||||
`${String(mismatchCount)} record(s) hold a sector trailer that is not the update sequence number; their attributes were not read and no later step should trust them`,
|
||||
);
|
||||
if (unverifiedCount !== 0)
|
||||
limitations.push(
|
||||
`${String(unverifiedCount)} record(s) carry an invalid or incomplete update sequence array; their sector trailers were not fully verified`,
|
||||
);
|
||||
|
||||
const metadata: MftMetadata = {
|
||||
kind: "ntfs-mft",
|
||||
record_bytes: recordBytes,
|
||||
record_count: recordCount,
|
||||
in_use_record_count: inUseCount,
|
||||
directory_record_count: directoryCount,
|
||||
extension_record_count: extensionCount,
|
||||
fixup_mismatch_count: mismatchCount,
|
||||
fixup_unverified_record_count: unverifiedCount,
|
||||
truncated_tail_bytes: truncatedTailBytes,
|
||||
record_headers: recordHeaders,
|
||||
omitted_record_headers: recordCount - recordHeaders.length,
|
||||
};
|
||||
|
||||
return ok({ metadata, recordBytes, limitations });
|
||||
};
|
||||
|
||||
const readRecord = (
|
||||
bytes: Uint8Array,
|
||||
fileOffset: number,
|
||||
index: number,
|
||||
recordBytes: number,
|
||||
): MftRecord => {
|
||||
const record = bytes.subarray(fileOffset, fileOffset + recordBytes);
|
||||
const view = new DataView(
|
||||
record.buffer,
|
||||
record.byteOffset,
|
||||
record.byteLength,
|
||||
);
|
||||
|
||||
const flags = view.getUint16(RECORD_HEADER.flags, true);
|
||||
const baseRecordReference = view.getBigUint64(
|
||||
RECORD_HEADER.baseRecordReference,
|
||||
true,
|
||||
);
|
||||
|
||||
const usaOffset = view.getUint16(RECORD_HEADER.updateSequenceOffset, true);
|
||||
const fixups = verifyFixups(record, view, usaOffset);
|
||||
const usedBytes = view.getUint32(RECORD_HEADER.usedBytes, true);
|
||||
const totalBytes = view.getUint32(RECORD_HEADER.totalBytes, true);
|
||||
const firstAttributeOffset = view.getUint16(
|
||||
RECORD_HEADER.firstAttributeOffset,
|
||||
true,
|
||||
);
|
||||
|
||||
const declaredRecordNumber =
|
||||
!fixups.malformed && usaOffset >= RECORD_HEADER_WITH_NUMBER_BYTES
|
||||
? view.getUint32(RECORD_HEADER.recordNumber, true)
|
||||
: null;
|
||||
|
||||
return {
|
||||
index,
|
||||
fileOffset,
|
||||
sequenceNumber: view.getUint16(RECORD_HEADER.sequenceNumber, true),
|
||||
hardLinkCount: view.getUint16(RECORD_HEADER.hardLinkCount, true),
|
||||
flags: parseRecordFlags(flags),
|
||||
inUse: (flags & FILE_RECORD_IN_USE) !== 0,
|
||||
directory: (flags & FILE_RECORD_IS_DIRECTORY) !== 0,
|
||||
usedBytes,
|
||||
totalBytes,
|
||||
extentValid:
|
||||
totalBytes === recordBytes &&
|
||||
usedBytes >= NTFS_MFT_MIN_RECORD_BYTES &&
|
||||
usedBytes % 8 === 0 &&
|
||||
usedBytes <= totalBytes &&
|
||||
firstAttributeOffset % 8 === 0 &&
|
||||
firstAttributeOffset >= NTFS_MFT_MIN_RECORD_BYTES &&
|
||||
firstAttributeOffset + 4 <= usedBytes &&
|
||||
(fixups.malformed ||
|
||||
firstAttributeOffset >= usaOffset + fixups.entries * 2),
|
||||
baseRecordReference:
|
||||
baseRecordReference === 0n
|
||||
? null
|
||||
: decodeMftFileReference(baseRecordReference),
|
||||
declaredRecordNumber,
|
||||
recordNumberMatchesSlot:
|
||||
declaredRecordNumber === null ? null : declaredRecordNumber === index,
|
||||
logFileSequenceNumber: view
|
||||
.getBigUint64(RECORD_HEADER.logFileSequenceNumber, true)
|
||||
.toString(),
|
||||
firstAttributeOffset,
|
||||
nextAttributeId: view.getUint16(RECORD_HEADER.nextAttributeId, true),
|
||||
fixups,
|
||||
};
|
||||
};
|
||||
|
||||
/**
|
||||
* Each sector's last two bytes are replaced on disk by the update sequence
|
||||
* number; the array's first entry is that number and the rest are the saved
|
||||
* trailer words. A sector whose trailer is not the sequence number was not
|
||||
* cleanly written, so the record's attributes cannot be trusted.
|
||||
*/
|
||||
const verifyFixups = (
|
||||
record: Uint8Array,
|
||||
view: DataView,
|
||||
usaOffset: number,
|
||||
): MftRecordFixups => {
|
||||
const usaCount = view.getUint16(RECORD_HEADER.updateSequenceCount, true);
|
||||
const sectors = Math.floor(record.length / FIXUP_SECTOR_BYTES);
|
||||
// Entry 0 holds the sequence number, so sector n's saved trailer is entry n+1.
|
||||
const coveredSectors = Math.max(0, usaCount - 1);
|
||||
|
||||
if (!updateSequenceArrayFits(usaOffset, usaCount, sectors))
|
||||
return {
|
||||
sequenceNumber: 0,
|
||||
entries: usaCount,
|
||||
verifiedSectors: 0,
|
||||
coveredSectors: 0,
|
||||
mismatchSector: null,
|
||||
malformed: true,
|
||||
};
|
||||
|
||||
const sequenceNumber = view.getUint16(usaOffset, true);
|
||||
if (sequenceNumber === 0 || sequenceNumber === 0xffff)
|
||||
return {
|
||||
sequenceNumber,
|
||||
entries: usaCount,
|
||||
verifiedSectors: 0,
|
||||
coveredSectors,
|
||||
mismatchSector: null,
|
||||
malformed: true,
|
||||
};
|
||||
for (let sector = 0; sector < coveredSectors; sector += 1) {
|
||||
const trailerOffset = sector * FIXUP_SECTOR_BYTES + FIXUP_SECTOR_BYTES - 2;
|
||||
if (view.getUint16(trailerOffset, true) !== sequenceNumber)
|
||||
return {
|
||||
sequenceNumber,
|
||||
entries: usaCount,
|
||||
verifiedSectors: sector,
|
||||
coveredSectors,
|
||||
mismatchSector: sector,
|
||||
malformed: false,
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
sequenceNumber,
|
||||
entries: usaCount,
|
||||
verifiedSectors: coveredSectors,
|
||||
coveredSectors,
|
||||
mismatchSector: null,
|
||||
malformed: false,
|
||||
};
|
||||
};
|
||||
|
||||
/** Buffer the admitted input once while accepting arbitrary chunk boundaries. */
|
||||
class StreamingMftDecoder implements RegionDecoder<MftInventory> {
|
||||
readonly #bytes: Uint8Array;
|
||||
#written = 0;
|
||||
|
||||
constructor(fileBytes: number) {
|
||||
this.#bytes = new Uint8Array(fileBytes);
|
||||
}
|
||||
|
||||
write(chunk: Uint8Array): Result<void, RegionDecodeFailure> {
|
||||
if (chunk.length > this.#bytes.length - this.#written)
|
||||
return err(failure("received more bytes than the admitted file length"));
|
||||
this.#bytes.set(chunk, this.#written);
|
||||
this.#written += chunk.length;
|
||||
return ok(undefined);
|
||||
}
|
||||
|
||||
finish(): Result<MftInventory, RegionDecodeFailure> {
|
||||
if (this.#written !== this.#bytes.length)
|
||||
return err(failure("stream ended before the admitted file length"));
|
||||
return scanMft(this.#bytes);
|
||||
}
|
||||
}
|
||||
|
||||
export const createMftDecoder = (
|
||||
fileBytes: number,
|
||||
): Result<RegionDecoder<MftInventory>, RegionDecodeFailure> =>
|
||||
Number.isSafeInteger(fileBytes) &&
|
||||
fileBytes >= 0 &&
|
||||
fileBytes <= MFT_MAX_FILE_BYTES
|
||||
? ok(new StreamingMftDecoder(fileBytes))
|
||||
: err(
|
||||
limit(
|
||||
`file is ${String(fileBytes)} bytes, exceeding the fixed ${String(MFT_MAX_FILE_BYTES)}-byte (512 MiB) ceiling`,
|
||||
"file-size",
|
||||
),
|
||||
);
|
||||
@@ -1,4 +1,3 @@
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { describe, expect, it } from "vitest";
|
||||
|
||||
import type { JsonValue } from "../domain/jsonValue.js";
|
||||
@@ -1120,25 +1119,6 @@ describe("Ghidra native instruction decoder context for ARM TMode and MIPS ISA_M
|
||||
});
|
||||
});
|
||||
|
||||
describe("Ghidra bridge script processor context contract", () => {
|
||||
it("binds TMode to ARM and ISA_MODE to MIPS in ReaGhidraBridge.java", async () => {
|
||||
const bridgePath = new URL(
|
||||
"../../bridge/ghidra/ReaGhidraBridge.java",
|
||||
import.meta.url,
|
||||
);
|
||||
const content = await readFile(bridgePath, "utf8");
|
||||
expect(content).toContain(
|
||||
'currentProgram.getLanguageID().getIdAsString().startsWith("ARM:")',
|
||||
);
|
||||
expect(content).toContain(
|
||||
'currentProgram.getLanguageID().getIdAsString().startsWith("MIPS:")',
|
||||
);
|
||||
expect(content).toContain('"TMode"');
|
||||
expect(content).toContain('"ISA_MODE"');
|
||||
expect(content).toContain('"ghidra-program-context"');
|
||||
});
|
||||
});
|
||||
|
||||
describe("Ghidra dossier nested boundary composition", () => {
|
||||
const identityLocations = [
|
||||
"caller",
|
||||
|
||||
@@ -307,6 +307,7 @@ const swiftExternalSwiftBindingImage = (
|
||||
...Buffer.from(
|
||||
`${boundField === "protocol" ? "_$sSQMp" : boundField === "objc-class" ? "_OBJC_CLASS_$_NSObject" : "_$sSiMn"}\0`,
|
||||
),
|
||||
0x51, // SET_TYPE_IMM pointer
|
||||
0x70,
|
||||
0x80,
|
||||
0x16, // SET_SEGMENT_AND_OFFSET_ULEB segment 0 + offset 0xb00
|
||||
@@ -373,6 +374,7 @@ const swiftBoundWitnessSlotImage = () => {
|
||||
0x11,
|
||||
0x40,
|
||||
...Buffer.from("_externalWitnessImpl\0"),
|
||||
0x51, // SET_TYPE_IMM pointer
|
||||
0x70,
|
||||
0x88,
|
||||
0x1c, // SET_SEGMENT_AND_OFFSET_ULEB segment 0 + witness slot 0xe08
|
||||
@@ -1107,6 +1109,7 @@ describe("Apple dispatch pointer fixup metadata", () => {
|
||||
const bindings = Buffer.from([
|
||||
0x40,
|
||||
...Buffer.from("_OBJC_CLASS_$_NSObject\0"),
|
||||
0x51, // SET_TYPE_IMM pointer
|
||||
0x70,
|
||||
0x88,
|
||||
0x04,
|
||||
@@ -1456,6 +1459,7 @@ describe("Objective-C category class references without a class name", () => {
|
||||
const bindings = Buffer.from([
|
||||
0x40,
|
||||
...Buffer.from("_$s4Main3FooCN\0"),
|
||||
0x51, // SET_TYPE_IMM pointer
|
||||
0x70,
|
||||
0xc8,
|
||||
0x16,
|
||||
@@ -1653,6 +1657,42 @@ describe("Objective-C category-local record-budget coverage", () => {
|
||||
});
|
||||
|
||||
describe("malformed Objective-C property records", () => {
|
||||
it.each(["class", "category"] as const)(
|
||||
"retains the %s identity when its property-list pointer field is unmapped",
|
||||
(owner) => {
|
||||
const bytes = fixture(false, "partial-method");
|
||||
if (owner === "class") {
|
||||
bytes.writeBigUInt64LE(base + 0xfc0n, 0x220);
|
||||
bytes.writeUInt32LE(2, 0xfc0);
|
||||
bytes.writeUInt32LE(16, 0xfc8);
|
||||
bytes.writeBigUInt64LE(base + 0x450n, 0xfd8);
|
||||
} else {
|
||||
bytes.writeBigUInt64LE(base + 0xfd8n, 0xb00);
|
||||
bytes.writeBigUInt64LE(base + 0xbc0n, 0xfd8);
|
||||
bytes.writeBigUInt64LE(base + 0x200n, 0xfe0);
|
||||
}
|
||||
const result = decodeAppleDispatchMetadata(bytes, 100, provenance);
|
||||
if (owner === "class")
|
||||
expect(result.objc_classes).toContainEqual(
|
||||
expect.objectContaining({ name: "Fixture", is_meta_class: false }),
|
||||
);
|
||||
else
|
||||
expect(result.objc_categories).toMatchObject([
|
||||
{ name: "FixtureCategory", class_name: "Fixture", properties: [] },
|
||||
]);
|
||||
expect(
|
||||
result.coverage.find(
|
||||
({ facet }) => facet === "objc_properties_categories",
|
||||
),
|
||||
).toMatchObject({
|
||||
status: "partial",
|
||||
reason: expect.stringContaining(
|
||||
"property_decode_failed at 0x100001000",
|
||||
),
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
it.each([
|
||||
["an unmapped name", { secondNameOffset: 0x2000 }, "first", "0x100000518"],
|
||||
["an empty name", { firstName: "" }, "second", "0x100000508"],
|
||||
|
||||
@@ -209,6 +209,7 @@ it.each(["bind", "weak", "lazy"] as const)(
|
||||
"base64",
|
||||
);
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
0x11,
|
||||
0x40,
|
||||
...Buffer.from("_first\0"),
|
||||
@@ -354,6 +355,7 @@ it.each(["bind", "weak", "lazy"] as const)(
|
||||
]);
|
||||
const literalName = "_OBJC_CLASS_$_�";
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
0x11,
|
||||
0x71,
|
||||
0x08,
|
||||
@@ -806,6 +808,7 @@ describe("incomplete legacy bind applicability", () => {
|
||||
|
||||
it("retains a positive bind prefix while leaving unmatched slots unknown", () => {
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
0x11,
|
||||
0x40,
|
||||
...Buffer.from("_x\0"),
|
||||
@@ -1085,11 +1088,20 @@ describe("parsed chained pointer membership", () => {
|
||||
target: BASE + 0x4321n,
|
||||
},
|
||||
);
|
||||
const plain = data.readBigUInt64LE(0x400b);
|
||||
expect(fixups.decode(BASE + 0x400bn, plain)).toEqual({
|
||||
kind: "raw",
|
||||
target: plain,
|
||||
});
|
||||
for (const offset of [0x4002, 0x400b, 0x4012])
|
||||
expect(
|
||||
fixups.decode(BASE + BigInt(offset), data.readBigUInt64LE(offset)),
|
||||
).toEqual({
|
||||
kind: "unsupported",
|
||||
reason: "A chained fixup partially overlaps the pointer slot",
|
||||
});
|
||||
for (const offset of [0x4000, 0x4019]) {
|
||||
const plain = data.readBigUInt64LE(offset);
|
||||
expect(fixups.decode(BASE + BigInt(offset), plain)).toEqual({
|
||||
kind: "raw",
|
||||
target: plain,
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
it.each(["shared", "exhausted"])(
|
||||
@@ -1613,6 +1625,85 @@ it("keeps both pointer slots unresolved when a legacy bind overlaps them", () =>
|
||||
expect(fixups.decode(BASE + 0x4008n, 456n).kind).toBe("unsupported");
|
||||
});
|
||||
|
||||
describe("legacy bind write types", () => {
|
||||
it.each([2, 3])(
|
||||
"keeps four-byte bind type %i unresolved without claiming writes to adjacent bytes",
|
||||
(type) => {
|
||||
const opcodes = Buffer.from([
|
||||
0x50 | type,
|
||||
0x11,
|
||||
0x40,
|
||||
...Buffer.from("_text\0"),
|
||||
0x71,
|
||||
0x08,
|
||||
0x90,
|
||||
0x51,
|
||||
0x90,
|
||||
0,
|
||||
]);
|
||||
const bytes = Buffer.alloc(0x8000);
|
||||
opcodes.copy(bytes, 0x7000);
|
||||
const fixups = parsePointerFixups(
|
||||
bytes,
|
||||
{
|
||||
chained: null,
|
||||
rebases: [],
|
||||
binds: [{ offset: 0x7000, size: opcodes.length, stream: "bind" }],
|
||||
dylibs: ["/library"],
|
||||
},
|
||||
SEGMENTS,
|
||||
BASE,
|
||||
);
|
||||
expect(fixups.decode(BASE + 0x4008n, 0n)).toMatchObject({
|
||||
kind: "unsupported",
|
||||
reason: "Legacy non-pointer bind is not a 64-bit metadata pointer",
|
||||
});
|
||||
expect(fixups.decode(BASE + 0x400cn, 0x1234n)).toEqual({
|
||||
kind: "unsupported",
|
||||
reason: "A legacy fixup partially overlaps the pointer slot",
|
||||
});
|
||||
expect(fixups.hasUnresolvedLegacyBytes(BASE + 0x400bn, 1)).toBe(true);
|
||||
expect(fixups.hasUnresolvedLegacyBytes(BASE + 0x400cn, 4)).toBe(false);
|
||||
expect(fixups.decode(BASE + 0x4010n, 0n)).toMatchObject({
|
||||
kind: "bind",
|
||||
symbol: "_text",
|
||||
});
|
||||
expect(fixups.issues).toMatchObject([{ code: "non_pointer_bind" }]);
|
||||
expect(fixups.decoded).toBe(1);
|
||||
},
|
||||
);
|
||||
|
||||
it.each(["bind", "weak", "lazy"] as const)(
|
||||
"preserves %s type defaults instead of inventing a pointer bind",
|
||||
(stream) => {
|
||||
const opcodes = Buffer.from([
|
||||
0x11,
|
||||
0x40,
|
||||
...Buffer.from("_x\0"),
|
||||
0x71,
|
||||
0x08,
|
||||
0x90,
|
||||
0,
|
||||
]);
|
||||
const fixups = parsePointerFixups(
|
||||
opcodes,
|
||||
{
|
||||
chained: null,
|
||||
rebases: [],
|
||||
binds: [{ offset: 0, size: opcodes.length, stream }],
|
||||
dylibs: ["/library"],
|
||||
},
|
||||
SEGMENTS,
|
||||
BASE,
|
||||
);
|
||||
expect(fixups.decode(BASE + 0x4008n, 0n).kind).toBe(
|
||||
stream === "lazy" ? "bind" : "unknown",
|
||||
);
|
||||
expect(fixups.decoded).toBe(stream === "lazy" ? 1 : 0);
|
||||
},
|
||||
);
|
||||
});
|
||||
|
||||
describe("legacy pointer fixup streams", () => {
|
||||
it("interprets legacy bind, weak-bind and lazy-bind opcodes", () => {
|
||||
const opcodes = Buffer.from([
|
||||
@@ -1685,6 +1776,7 @@ describe("legacy pointer fixup streams", () => {
|
||||
// The unsigned 64-bit encoding of -8 revisits the current pointer slot.
|
||||
const back = [0xf8, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x01];
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
0x11, // SET_DYLIB_ORDINAL_IMM 1
|
||||
0x40,
|
||||
...Buffer.from("__ZdlPv\0"),
|
||||
@@ -1724,6 +1816,7 @@ describe("legacy pointer fixup streams", () => {
|
||||
|
||||
it("retains weak-bind stream provenance independently from its default ordinal", () => {
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
0x40,
|
||||
...Buffer.from("_OBJC_CLASS_$_NSObject\0"),
|
||||
0x71,
|
||||
@@ -1754,6 +1847,7 @@ describe("legacy pointer fixup streams", () => {
|
||||
describe("legacy bind operand decoding", () => {
|
||||
const addendStream = (addend: readonly number[]) =>
|
||||
Buffer.from([
|
||||
0x51,
|
||||
0x11, // SET_DYLIB_ORDINAL_IMM 1
|
||||
0x40,
|
||||
...Buffer.from("_x\0"),
|
||||
@@ -1859,6 +1953,7 @@ describe("legacy bind operand decoding", () => {
|
||||
|
||||
const addressStream = (operand: readonly number[]) =>
|
||||
Buffer.from([
|
||||
0x51,
|
||||
0x40,
|
||||
...Buffer.from("_x\0"),
|
||||
0x71,
|
||||
@@ -1907,6 +2002,7 @@ it("preserves classic special ordinals and returns unsupported at invalid bind l
|
||||
const parseOrdinal = (ordinal: number, dylibs: readonly string[]) => {
|
||||
const immediate = ordinal < 0 ? ordinal + 16 : ordinal;
|
||||
const opcodes = Buffer.from([
|
||||
0x51,
|
||||
ordinal > 0 ? 0x10 | ordinal : 0x30 | immediate,
|
||||
0x40,
|
||||
...Buffer.from("_OBJC_CLASS_$_NSObject\0"),
|
||||
@@ -1955,6 +2051,7 @@ it("preserves classic special ordinals and returns unsupported at invalid bind l
|
||||
}
|
||||
encoded.push(Number(remaining));
|
||||
const oversizedStream = Buffer.from([
|
||||
0x51,
|
||||
0x20,
|
||||
...encoded,
|
||||
0x40,
|
||||
|
||||
+128
-25
@@ -116,6 +116,8 @@ interface BindRun {
|
||||
readonly start: bigint;
|
||||
count: bigint;
|
||||
readonly stride: bigint;
|
||||
readonly type: number;
|
||||
readonly width: 4 | 8;
|
||||
readonly binding:
|
||||
| {
|
||||
readonly kind: "bind";
|
||||
@@ -377,6 +379,28 @@ const readChainedPage = (
|
||||
return { locations, lastOffset, failure };
|
||||
};
|
||||
|
||||
/** A known eight-byte chain word starting elsewhere overlaps this pointer read. */
|
||||
const hasPartialChainedPointer = (
|
||||
chain: ChainedSegment,
|
||||
within: number,
|
||||
readPage: (page: number) => ChainedPage | null,
|
||||
): boolean => {
|
||||
let page = -1;
|
||||
let facts: ChainedPage | null = null;
|
||||
for (let at = Math.max(0, within - 7); at <= within + 7; at++) {
|
||||
if (at === within || BigInt(at) >= chain.segment.size) continue;
|
||||
const candidatePage = Math.floor(at / chain.pageSize);
|
||||
if (candidatePage !== page) {
|
||||
page = candidatePage;
|
||||
facts = readPage(page);
|
||||
}
|
||||
const offset = at % chain.pageSize;
|
||||
if (((facts?.locations[offset >>> 3] ?? 0) & (1 << (offset & 7))) !== 0)
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
};
|
||||
|
||||
const chainedFixups = (
|
||||
image: FixupImage,
|
||||
range: { readonly offset: number; readonly size: number },
|
||||
@@ -654,6 +678,45 @@ const chainedFixups = (
|
||||
raw,
|
||||
reason: `Legacy bind opcodes could overlap this rebase location: ${binds.failures.join("; ")}`,
|
||||
};
|
||||
// Reuse one transient view within this lookup even when retained page
|
||||
// storage is full; overlap inspection and value decoding share its facts.
|
||||
let queried:
|
||||
| { chain: ChainedSegment; page: number; facts: ChainedPage }
|
||||
| undefined;
|
||||
const queryPageFacts = (
|
||||
chain: ChainedSegment,
|
||||
page: number,
|
||||
start: number,
|
||||
): ChainedPage => {
|
||||
if (queried?.chain === chain && queried.page === page)
|
||||
return queried.facts;
|
||||
const facts = pageFacts(chain, page, start);
|
||||
queried = { chain, page, facts };
|
||||
return facts;
|
||||
};
|
||||
if (
|
||||
ranges.some(
|
||||
(chain) =>
|
||||
POINTER_FORMATS[chain.format] !== undefined &&
|
||||
address + 8n > chain.segment.address &&
|
||||
address < chain.segment.address + chain.segment.size &&
|
||||
hasPartialChainedPointer(
|
||||
chain,
|
||||
Number(address - chain.segment.address),
|
||||
(page) => {
|
||||
if (page >= chain.pageCount) return null;
|
||||
const start = bytes.readUInt16LE(chain.pageStarts + page * 2);
|
||||
return start === 0xffff
|
||||
? null
|
||||
: queryPageFacts(chain, page, start);
|
||||
},
|
||||
),
|
||||
)
|
||||
)
|
||||
return {
|
||||
kind: "unsupported",
|
||||
reason: "A chained fixup partially overlaps the pointer slot",
|
||||
};
|
||||
const chainIndex = ranges.findIndex(
|
||||
({ segment }) =>
|
||||
address >= segment.address &&
|
||||
@@ -675,7 +738,7 @@ const chainedFixups = (
|
||||
reason: `Unsupported chained pointer format ${chain.format}`,
|
||||
};
|
||||
try {
|
||||
const facts = pageFacts(chain, page, start);
|
||||
const facts = queryPageFacts(chain, page, start);
|
||||
const at = within % chain.pageSize;
|
||||
const locations = facts.locations;
|
||||
if (((locations[at >>> 3] ?? 0) & (1 << (at & 7))) !== 0) {
|
||||
@@ -1022,6 +1085,7 @@ const sleb = (bytes: Buffer, cursor: { at: number }, end: number): bigint => {
|
||||
|
||||
/** Registers of the `LC_DYLD_INFO` bind state machine. */
|
||||
interface BindState {
|
||||
type: number;
|
||||
ordinal: number;
|
||||
ordinalFailure: string | null;
|
||||
segmentIndex: number;
|
||||
@@ -1072,6 +1136,7 @@ const setBindRegister = (
|
||||
return true;
|
||||
}
|
||||
case 0x50:
|
||||
state.type = immediate;
|
||||
return true;
|
||||
case 0x60:
|
||||
state.addend = sleb(bytes, cursor, end);
|
||||
@@ -1106,6 +1171,7 @@ function* readBindStreamSteps(
|
||||
throw new RangeError("Bind opcodes exceed the target");
|
||||
const cursor = { at: range.offset };
|
||||
const state: BindState = {
|
||||
type: range.stream === "lazy" ? 1 : 0,
|
||||
ordinal: 0,
|
||||
ordinalFailure: null,
|
||||
segmentIndex: -1,
|
||||
@@ -1116,11 +1182,14 @@ function* readBindStreamSteps(
|
||||
};
|
||||
const preflightRun = (count: bigint, skip: bigint): void => {
|
||||
if (count === 0n) return;
|
||||
if (state.type < 1 || state.type > 3)
|
||||
throw new RangeError(`Unsupported legacy bind type ${state.type}`);
|
||||
const segment = image.segments[state.segmentIndex];
|
||||
if (segment === undefined)
|
||||
throw new RangeError("Bind location has no selected segment");
|
||||
const stride = 8n + skip;
|
||||
const end = state.address + (count - 1n) * stride + 8n;
|
||||
const width = state.type === 1 ? 8n : 4n;
|
||||
const end = state.address + (count - 1n) * stride + width;
|
||||
if (state.address < segment.address || end > segment.address + segment.size)
|
||||
throw new RangeError("Bind expansion leaves its file-backed segment");
|
||||
};
|
||||
@@ -1128,22 +1197,29 @@ function* readBindStreamSteps(
|
||||
if (count === 0n) return;
|
||||
preflightRun(count, skip);
|
||||
const stride = 8n + skip;
|
||||
const width = state.type === 1 ? 8 : 4;
|
||||
let binding: BindRun["binding"];
|
||||
try {
|
||||
if (state.ordinalFailure !== null)
|
||||
throw new RangeError(state.ordinalFailure);
|
||||
const resolvedLibrary = libraryFacts(state.ordinal, image.dylibs);
|
||||
const decoded = resolvedBind(
|
||||
{
|
||||
...state.symbol,
|
||||
binding_source: range.stream,
|
||||
library_ordinal: state.ordinal,
|
||||
...(range.stream === "weak" ? { library: null } : resolvedLibrary),
|
||||
weak: state.weak,
|
||||
addend: state.addend,
|
||||
},
|
||||
0n,
|
||||
);
|
||||
const imported: Import = {
|
||||
...state.symbol,
|
||||
binding_source: range.stream,
|
||||
library_ordinal: state.ordinal,
|
||||
...(range.stream === "weak" ? { library: null } : resolvedLibrary),
|
||||
weak: state.weak,
|
||||
addend: state.addend,
|
||||
};
|
||||
const decoded =
|
||||
state.type === 1
|
||||
? resolvedBind(imported, 0n)
|
||||
: {
|
||||
kind: "unsupported" as const,
|
||||
reason:
|
||||
"Legacy non-pointer bind is not a 64-bit metadata pointer",
|
||||
binding: imported,
|
||||
};
|
||||
binding =
|
||||
decoded.kind === "bind" ? { kind: "bind", value: decoded } : decoded;
|
||||
} catch (cause: unknown) {
|
||||
@@ -1167,13 +1243,21 @@ function* readBindStreamSteps(
|
||||
: false;
|
||||
if (
|
||||
previous !== undefined &&
|
||||
previous.type === state.type &&
|
||||
previous.stride === stride &&
|
||||
previous.start + previous.count * stride === state.address &&
|
||||
sameBinding(previous.binding, binding)
|
||||
) {
|
||||
previous.count += count;
|
||||
} else {
|
||||
binds.push({ start: state.address, count, stride, binding });
|
||||
binds.push({
|
||||
start: state.address,
|
||||
count,
|
||||
stride,
|
||||
type: state.type,
|
||||
width,
|
||||
binding,
|
||||
});
|
||||
}
|
||||
// The dyld bind stream advances addresses modulo 64 bits; ld uses -8 to
|
||||
// bind the current pointer slot again with DO_BIND_ADD_ADDR_ULEB.
|
||||
@@ -1237,6 +1321,18 @@ const indexBindRuns = (
|
||||
};
|
||||
};
|
||||
|
||||
/** First producer-owned bind start in an inclusive address interval. */
|
||||
const firstBindIn = (
|
||||
run: BindRun,
|
||||
low: bigint,
|
||||
high: bigint,
|
||||
): bigint | undefined => {
|
||||
const index =
|
||||
low <= run.start ? 0n : (low - run.start + run.stride - 1n) / run.stride;
|
||||
const address = run.start + index * run.stride;
|
||||
return index < run.count && address <= high ? address : undefined;
|
||||
};
|
||||
|
||||
/** Visit runs with a bind start in the inclusive interval, without expanding runs. */
|
||||
function* bindRunsIn(
|
||||
index: BindRunIndex,
|
||||
@@ -1263,9 +1359,7 @@ function* bindRunsIn(
|
||||
index.remaining--;
|
||||
candidates++;
|
||||
const run = index.runs[at]!;
|
||||
const first =
|
||||
low <= run.start ? 0n : (low - run.start + run.stride - 1n) / run.stride;
|
||||
if (first < run.count && run.start + first * run.stride <= high) yield run;
|
||||
if (firstBindIn(run, low, high) !== undefined) yield run;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1318,9 +1412,11 @@ function* parseLegacyBindsSteps(
|
||||
issues.push(
|
||||
issue(
|
||||
"pointer_fixups",
|
||||
run.binding.binding.symbol === null
|
||||
? "bind_symbol_text_unavailable"
|
||||
: "bind_library_text_unavailable",
|
||||
run.type !== 1
|
||||
? "non_pointer_bind"
|
||||
: run.binding.binding.symbol === null
|
||||
? "bind_symbol_text_unavailable"
|
||||
: "bind_library_text_unavailable",
|
||||
run.binding.reason,
|
||||
`0x${run.start.toString(16)}`,
|
||||
),
|
||||
@@ -1350,7 +1446,11 @@ const hasUnresolvedLegacyBytes = (
|
||||
return true;
|
||||
const first = address - 7n;
|
||||
const end = address + BigInt(size);
|
||||
for (const _run of bindRunsIn(binds.index, first, end - 1n)) return true;
|
||||
for (const run of bindRunsIn(binds.index, first, end - 1n))
|
||||
if (
|
||||
firstBindIn(run, address - BigInt(run.width) + 1n, end - 1n) !== undefined
|
||||
)
|
||||
return true;
|
||||
if (binds.index.exhausted) return true;
|
||||
if (rebases.membership !== null)
|
||||
for (let slot = first; slot < end; slot++) {
|
||||
@@ -1376,10 +1476,13 @@ const hasPartialLegacyPointerWrite = (
|
||||
const low = address - 7n;
|
||||
const high = address + 7n;
|
||||
for (const run of bindRunsIn(binds.index, low, high)) {
|
||||
const first =
|
||||
low <= run.start ? 0n : (low - run.start + run.stride - 1n) / run.stride;
|
||||
const at = run.start + first * run.stride;
|
||||
if (at !== address || (first + 1n < run.count && at + run.stride <= high))
|
||||
const at = firstBindIn(run, address - BigInt(run.width) + 1n, high);
|
||||
if (at === undefined) continue;
|
||||
if (
|
||||
run.width !== 8 ||
|
||||
at !== address ||
|
||||
firstBindIn(run, at + 1n, high) !== undefined
|
||||
)
|
||||
return true;
|
||||
}
|
||||
if (binds.index.exhausted) return true;
|
||||
|
||||
@@ -234,6 +234,7 @@ describe("Mach-O metadata span mapping", () => {
|
||||
const opcodes = Buffer.from([
|
||||
0x40,
|
||||
...Buffer.from("_local\0"),
|
||||
0x51,
|
||||
0x72,
|
||||
8,
|
||||
0x90,
|
||||
@@ -340,6 +341,19 @@ describe("Mach-O metadata span mapping", () => {
|
||||
});
|
||||
});
|
||||
|
||||
it("rejects a segment command of the wrong width before claiming metadata absence", () => {
|
||||
const segment = Buffer.alloc(56);
|
||||
segment.writeUInt32LE(1, 0);
|
||||
segment.writeUInt32LE(segment.length, 4);
|
||||
const bytes = Buffer.from(machoImage({ commands: [segment] }));
|
||||
expect(() => readMachoMetadataImage(bytes)).toThrow(
|
||||
"Mach-O segment command does not match the header width",
|
||||
);
|
||||
expect(() => parseMachoLayout(bytes, "arm64")).toThrow(
|
||||
"Mach-O segment command does not match the header width",
|
||||
);
|
||||
});
|
||||
|
||||
describe("native Mach-O slice selection", () => {
|
||||
it("rejects misaligned load commands", () => {
|
||||
expect(() =>
|
||||
|
||||
@@ -227,6 +227,10 @@ export const parseMachoLayout = (
|
||||
kind: frame.value.command,
|
||||
size: frame.value.size,
|
||||
};
|
||||
if (command.kind === 1)
|
||||
throw new RangeError(
|
||||
"Mach-O segment command does not match the header width",
|
||||
);
|
||||
if (command.kind === 0x19) collectSegment(bytes, command, state);
|
||||
else collectFixupCommand(bytes, command, state);
|
||||
}
|
||||
|
||||
@@ -134,17 +134,12 @@ export const decodeObjcCategories = (input: {
|
||||
`0x${(category + 32n).toString(16)}`,
|
||||
),
|
||||
);
|
||||
const properties = readObjcPropertiesOf(
|
||||
read,
|
||||
read.pointer(category + 40n),
|
||||
{
|
||||
owner: `category ${name}`,
|
||||
admit: input.admit,
|
||||
issues: input.issues,
|
||||
location: `0x${read.pointer(category + 40n).toString(16)}`,
|
||||
onTruncated,
|
||||
},
|
||||
);
|
||||
const properties = readObjcPropertiesOf(read, category + 40n, {
|
||||
owner: `category ${name}`,
|
||||
admit: input.admit,
|
||||
issues: input.issues,
|
||||
onTruncated,
|
||||
});
|
||||
const decodeReasons = [
|
||||
...(className === null ? ["category_class_unresolved"] : []),
|
||||
...(protocols.ok ? [] : ["protocol_list_unreadable"]),
|
||||
|
||||
@@ -354,11 +354,10 @@ export const decodeObjcDispatchFacets = (input: {
|
||||
undefined,
|
||||
onTruncated,
|
||||
);
|
||||
const properties = readObjcPropertiesOf(read, read.pointer(ro + 64n), {
|
||||
const properties = readObjcPropertiesOf(read, ro + 64n, {
|
||||
owner: name,
|
||||
admit: () => budget.admit(),
|
||||
issues: categoryIssues,
|
||||
location: hex(read.pointer(ro + 64n)),
|
||||
onTruncated,
|
||||
});
|
||||
const adoptedProtocols = protocolReader.readList(ro + 40n, onTruncated);
|
||||
|
||||
@@ -154,19 +154,21 @@ export const readObjcPropertyList = (
|
||||
return { properties, issues };
|
||||
};
|
||||
|
||||
/** Decode a property list, recording a failure for `owner` instead of throwing. */
|
||||
/** Own the property-list pointer field and list, retaining the declaring owner on failure. */
|
||||
export const readObjcPropertiesOf = (
|
||||
read: ObjcPropertyReaders,
|
||||
list: bigint,
|
||||
field: bigint,
|
||||
context: {
|
||||
readonly owner: string;
|
||||
readonly admit: () => boolean;
|
||||
readonly issues: DecodeIssue[];
|
||||
readonly location?: string;
|
||||
readonly onTruncated?: () => void;
|
||||
},
|
||||
): ObjcProperty[] => {
|
||||
let location = `0x${field.toString(16)}`;
|
||||
try {
|
||||
const list = read.pointer(field);
|
||||
location = `0x${list.toString(16)}`;
|
||||
const { properties, issues } = readObjcPropertyList(
|
||||
read,
|
||||
list,
|
||||
@@ -189,7 +191,7 @@ export const readObjcPropertiesOf = (
|
||||
"objc_properties_categories",
|
||||
"property_decode_failed",
|
||||
`${context.owner}: ${cause instanceof Error ? cause.message : String(cause)}`,
|
||||
context.location,
|
||||
location,
|
||||
),
|
||||
);
|
||||
return [];
|
||||
|
||||
@@ -234,9 +234,29 @@ export const createSwiftRelativeReader = (input: {
|
||||
);
|
||||
let fileOffset: number | null = null;
|
||||
let reason: string | null = null;
|
||||
const unknownIndirect = (reason: string): SwiftRelativeValue => {
|
||||
if (budget.admit())
|
||||
result.relative_pointers.push({
|
||||
field: read.location(field),
|
||||
target: { address: null, file_offset: null },
|
||||
displacement,
|
||||
indirectable,
|
||||
indirect,
|
||||
decode: { status: "partial", reason },
|
||||
evidence: read.evidence(field, "Swift ABI indirect relative pointer"),
|
||||
});
|
||||
return { kind: "unknown", reason };
|
||||
};
|
||||
try {
|
||||
if (indirect && target !== null) {
|
||||
const pointer = read.resolvePointer(target);
|
||||
let pointer: PointerResolution;
|
||||
try {
|
||||
pointer = read.resolvePointer(target);
|
||||
} catch (cause) {
|
||||
const failure = expectedSwiftMetadataReadFailure(cause);
|
||||
if (failure === null) throw cause;
|
||||
return unknownIndirect(failure);
|
||||
}
|
||||
if (pointer.kind === "bind") {
|
||||
if (budget.admit())
|
||||
result.relative_pointers.push({
|
||||
@@ -259,21 +279,7 @@ export const createSwiftRelativeReader = (input: {
|
||||
};
|
||||
}
|
||||
if (pointer.kind === "unknown" || pointer.kind === "unsupported") {
|
||||
const unresolved = pointer.reason;
|
||||
if (budget.admit())
|
||||
result.relative_pointers.push({
|
||||
field: read.location(field),
|
||||
target: { address: null, file_offset: null },
|
||||
displacement,
|
||||
indirectable,
|
||||
indirect,
|
||||
decode: { status: "partial", reason: unresolved },
|
||||
evidence: read.evidence(
|
||||
field,
|
||||
"Swift ABI indirect relative pointer",
|
||||
),
|
||||
});
|
||||
return { kind: "unknown", reason: unresolved };
|
||||
return unknownIndirect(pointer.reason);
|
||||
}
|
||||
const indirectTarget = pointer.target;
|
||||
target =
|
||||
@@ -283,7 +289,8 @@ export const createSwiftRelativeReader = (input: {
|
||||
}
|
||||
if (target !== null) fileOffset = read.offset(target);
|
||||
} catch (cause) {
|
||||
reason = cause instanceof Error ? cause.message : String(cause);
|
||||
reason = expectedSwiftMetadataReadFailure(cause);
|
||||
if (reason === null) throw cause;
|
||||
}
|
||||
if (budget.admit())
|
||||
result.relative_pointers.push({
|
||||
@@ -553,7 +560,8 @@ export const decodeSwiftDispatchFacets = (input: {
|
||||
}
|
||||
}
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
const message = expectedSwiftMetadataReadFailure(cause);
|
||||
if (message === null) throw cause;
|
||||
issues.push(
|
||||
issue(
|
||||
"swift_conformances_static_witness_slots",
|
||||
|
||||
@@ -276,3 +276,37 @@ it("retains unsafe target addresses as partial decode facts", () => {
|
||||
decode: { status: "partial", reason: "outside fixture bytes" },
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
new RangeError("indirect pointer cell is unreadable"),
|
||||
new Error("reader invariant failed"),
|
||||
])(
|
||||
"distinguishes indirect pointer read failure from a known unmapped target: %s",
|
||||
(failure) => {
|
||||
const bytes = Buffer.alloc(0x80);
|
||||
bytes.writeInt32LE(0x25, 0x24);
|
||||
const result = objcSwiftMetadataSchema.parse({ db_save_result: null });
|
||||
const relative = createSwiftRelativeReader({
|
||||
bytes,
|
||||
readers: {
|
||||
...readers(bytes),
|
||||
resolvePointer: () => {
|
||||
throw failure;
|
||||
},
|
||||
},
|
||||
budget: budget(),
|
||||
result,
|
||||
});
|
||||
if (failure instanceof RangeError) {
|
||||
expect(relative(0x24n, "conformanceProtocol")).toEqual({
|
||||
kind: "unknown",
|
||||
reason: failure.message,
|
||||
});
|
||||
expect(result.relative_pointers[0]).toMatchObject({
|
||||
target: { address: null, file_offset: null },
|
||||
decode: { status: "partial", reason: failure.message },
|
||||
});
|
||||
} else
|
||||
expect(() => relative(0x24n, "conformanceProtocol")).toThrow(failure);
|
||||
},
|
||||
);
|
||||
@@ -9,9 +9,66 @@ import {
|
||||
type SwiftNominalReaders,
|
||||
} from "./AppleSwiftNominalTypes.js";
|
||||
import { decodeSwiftDispatchFacets } from "./AppleSwiftDispatchFacets.js";
|
||||
import type { DispatchRecordBudget } from "./AppleSwiftDispatchFacets.js";
|
||||
import type {
|
||||
DispatchRecordBudget,
|
||||
SwiftDispatchReaders,
|
||||
} from "./AppleSwiftDispatchFacets.js";
|
||||
import { issue } from "./AppleDispatchDecodeFacts.js";
|
||||
|
||||
it("propagates unexpected conformance reader failures", () => {
|
||||
const failure = new Error("conformance reader invariant failed");
|
||||
expect(() =>
|
||||
decodeSwiftDispatchFacets({
|
||||
sections: [{ name: "__swift5_proto", address: 0x100n, size: 4 }],
|
||||
segments: [],
|
||||
readers: {} as SwiftDispatchReaders,
|
||||
relative: () => {
|
||||
throw failure;
|
||||
},
|
||||
budget: {
|
||||
truncated: false,
|
||||
isFull: () => false,
|
||||
markTruncated: () => {},
|
||||
admit: () => true,
|
||||
},
|
||||
result: objcSwiftMetadataSchema.parse({ db_save_result: null }),
|
||||
}),
|
||||
).toThrow(failure);
|
||||
});
|
||||
|
||||
it("propagates unexpected vtable reader failures", () => {
|
||||
const failure = new Error("vtable reader invariant failed");
|
||||
const vtables = createSwiftClassVtableDecoder({
|
||||
result: objcSwiftMetadataSchema.parse({ db_save_result: null }),
|
||||
readers: {
|
||||
u32: () => {
|
||||
throw failure;
|
||||
},
|
||||
relative: () => ({ kind: "null" }),
|
||||
location: () => ({ address: null, file_offset: null }),
|
||||
evidence: () => [],
|
||||
executable: () => false,
|
||||
admit: () => true,
|
||||
},
|
||||
});
|
||||
expect(() =>
|
||||
vtables.visitor.descriptor({
|
||||
record: 0x100n,
|
||||
descriptor: 0x200n,
|
||||
flags: 0x80000010,
|
||||
name: "Widget",
|
||||
context: {
|
||||
module: "Test",
|
||||
path: "Widget",
|
||||
depth: 2,
|
||||
anonymous: false,
|
||||
reason: null,
|
||||
walkLimited: false,
|
||||
},
|
||||
}),
|
||||
).toThrow(failure);
|
||||
});
|
||||
|
||||
it("preserves unsupported type-metadata tag reasons instead of reporting null", () => {
|
||||
const result = objcSwiftMetadataSchema.parse({ db_save_result: null });
|
||||
const vtables = createSwiftClassVtableDecoder({
|
||||
|
||||
@@ -14,6 +14,7 @@ import type {
|
||||
SwiftNominalRecordFailure,
|
||||
SwiftNominalVisitor,
|
||||
} from "./AppleSwiftNominalTypes.js";
|
||||
import { expectedSwiftMetadataReadFailure } from "./AppleSwiftMetadataReadFailure.js";
|
||||
|
||||
/** Byte readers shared with the validated Mach-O metadata boundary. */
|
||||
export interface SwiftMetadataReaders {
|
||||
@@ -63,13 +64,13 @@ export const createSwiftClassVtableDecoder = (input: {
|
||||
try {
|
||||
const specific = flags >>> 16;
|
||||
if ((flags & 0x80) !== 0 || (specific & 0x2000) !== 0)
|
||||
throw new TypeError(
|
||||
throw new RangeError(
|
||||
"Generic class or resilient superclass metadata is unsupported",
|
||||
);
|
||||
if ((specific & 0x8000) === 0) return;
|
||||
const initialization = specific & 3;
|
||||
if (initialization === 3)
|
||||
throw new TypeError("Unknown metadata initialization kind");
|
||||
throw new RangeError("Unknown metadata initialization kind");
|
||||
const header =
|
||||
descriptor +
|
||||
44n +
|
||||
@@ -167,7 +168,8 @@ export const createSwiftClassVtableDecoder = (input: {
|
||||
);
|
||||
}
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
const message = expectedSwiftMetadataReadFailure(cause);
|
||||
if (message === null) throw cause;
|
||||
issues.push(
|
||||
issue(
|
||||
"swift_class_vtable_descriptors",
|
||||
|
||||
@@ -214,15 +214,44 @@ export const readMachoCommandNames = async (
|
||||
chargeProjection(table.commandCount, PROJECTED_COMMAND_BYTES);
|
||||
let records = table.commandCount;
|
||||
let retainedStringBytes = 0;
|
||||
const retain = (bytes: Uint8Array): Uint8Array => {
|
||||
if (bytes.byteLength > maximumStringBytes - retainedStringBytes)
|
||||
const stringAllowance = (): number =>
|
||||
Math.min(
|
||||
maximumStringBytes - retainedStringBytes,
|
||||
Math.floor(
|
||||
(maximumProjectedBytes - projectedBytes) / PROJECTED_STRING_EXPANSION,
|
||||
),
|
||||
);
|
||||
const admitStringBytes = (count: number): void => {
|
||||
if (count > maximumStringBytes - retainedStringBytes)
|
||||
throw new MachoCommandNamesLimitError(maximumStringBytes, "bytes");
|
||||
if (count > stringAllowance())
|
||||
throw new MachoCommandNamesLimitError(
|
||||
maximumProjectedBytes,
|
||||
"projected_bytes",
|
||||
);
|
||||
};
|
||||
const retain = (bytes: Uint8Array): Uint8Array => {
|
||||
admitStringBytes(bytes.byteLength);
|
||||
chargeProjection(bytes.byteLength, PROJECTED_STRING_EXPANSION);
|
||||
retainedStringBytes += bytes.byteLength;
|
||||
// Range readers may return Buffer views into a much larger read window.
|
||||
// Charge the retained length before allocating an independently owned copy.
|
||||
return Uint8Array.from(bytes);
|
||||
};
|
||||
const readString = async (
|
||||
offset: number,
|
||||
extent: number,
|
||||
label: string,
|
||||
): Promise<Uint8Array> => {
|
||||
const length = Math.min(extent, stringAllowance() + 1);
|
||||
const bytes = await exact(offset, length);
|
||||
const end = bytes.indexOf(0);
|
||||
if (end < 0) {
|
||||
if (length < extent) admitStringBytes(length);
|
||||
throw new MachoBinaryFormatError(`${label} is unterminated`);
|
||||
}
|
||||
return retain(bytes.subarray(0, end));
|
||||
};
|
||||
const commands: MachoCommandNames["commands"][number][] = [];
|
||||
while (cursor.nextOffset !== null) {
|
||||
const row = cursor.read(
|
||||
@@ -372,17 +401,11 @@ export const readMachoCommandNames = async (
|
||||
throw new MachoBinaryFormatError(
|
||||
"Mach-O command string offset is invalid",
|
||||
);
|
||||
const limit = Math.min(frame.size - offset, maximumStringBytes + 1);
|
||||
const bytes = await exact(at + offset, limit);
|
||||
const end = bytes.indexOf(0);
|
||||
if (end < 0) {
|
||||
if (limit < frame.size - offset)
|
||||
throw new MachoCommandNamesLimitError(maximumStringBytes, "bytes");
|
||||
throw new MachoBinaryFormatError(
|
||||
"Mach-O command string is unterminated",
|
||||
);
|
||||
}
|
||||
commandString = retain(bytes.subarray(0, end));
|
||||
commandString = await readString(
|
||||
at + offset,
|
||||
frame.size - offset,
|
||||
"Mach-O command string",
|
||||
);
|
||||
commandStringOffset = offset;
|
||||
if (DYLIB_COMMANDS.has(frame.command)) {
|
||||
const fixed = await exact(at + 12, 12);
|
||||
@@ -434,8 +457,7 @@ export const readMachoCommandNames = async (
|
||||
throw new MachoBinaryFormatError(
|
||||
"Mach-O prebound module bitmap exceeds its command",
|
||||
);
|
||||
if (length > maximumStringBytes - retainedStringBytes)
|
||||
throw new MachoCommandNamesLimitError(maximumStringBytes, "bytes");
|
||||
admitStringBytes(length);
|
||||
prebound = {
|
||||
moduleCount,
|
||||
linkedModulesOffset,
|
||||
@@ -501,12 +523,8 @@ export const readMachoCommandNames = async (
|
||||
currentLength = 0;
|
||||
if (linkerOptions.length === count) break;
|
||||
} else {
|
||||
const remaining = maximumStringBytes - retainedStringBytes;
|
||||
if (currentLength >= remaining)
|
||||
throw new MachoCommandNamesLimitError(
|
||||
maximumStringBytes,
|
||||
"bytes",
|
||||
);
|
||||
const remaining = stringAllowance();
|
||||
if (currentLength >= remaining) admitStringBytes(currentLength + 1);
|
||||
if (currentLength === current.byteLength) {
|
||||
const capacity = Math.min(
|
||||
remaining,
|
||||
@@ -565,20 +583,14 @@ export const readMachoCommandNames = async (
|
||||
throw new MachoBinaryFormatError(
|
||||
"Mach-O fileset entry string offset is invalid",
|
||||
);
|
||||
const length = Math.min(frame.size - offset, maximumStringBytes + 1);
|
||||
const value = await exact(at + offset, length);
|
||||
const end = value.indexOf(0);
|
||||
if (end < 0) {
|
||||
if (length < frame.size - offset)
|
||||
throw new MachoCommandNamesLimitError(maximumStringBytes, "bytes");
|
||||
throw new MachoBinaryFormatError(
|
||||
"Mach-O fileset entry string is unterminated",
|
||||
);
|
||||
}
|
||||
fileset = {
|
||||
address: view.getBigUint64(0, table.littleEndian),
|
||||
fileOffset: view.getBigUint64(8, table.littleEndian),
|
||||
entryId: retain(value.subarray(0, end)),
|
||||
entryId: await readString(
|
||||
at + offset,
|
||||
frame.size - offset,
|
||||
"Mach-O fileset entry string",
|
||||
),
|
||||
reserved: view.getUint32(20, table.littleEndian),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -100,3 +100,69 @@ it("reserves the projection envelope for an empty command table", async () => {
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
it("bounds a growing linker option before reading its remaining payload", async () => {
|
||||
const commandSize = 8208;
|
||||
const image = Buffer.alloc(32 + commandSize);
|
||||
image.writeUInt32LE(0xfeedfacf, 0);
|
||||
image.writeUInt32LE(1, 16);
|
||||
image.writeUInt32LE(commandSize, 20);
|
||||
image.writeUInt32LE(0x2d, 32);
|
||||
image.writeUInt32LE(commandSize, 36);
|
||||
image.writeUInt32LE(1, 40);
|
||||
image.fill(0x41, 44, 44 + 8000);
|
||||
const projectedBudget = 8192 + 2048 + 256 + 32 * 24;
|
||||
const read = async (offset: number, size: number) => {
|
||||
if (offset >= 44 + 4096)
|
||||
throw new Error("linker option read beyond its projection allowance");
|
||||
return image.subarray(offset, offset + size);
|
||||
};
|
||||
await expect(
|
||||
readMachoCommandNames(read, image.length, 16384, 2, projectedBudget),
|
||||
).rejects.toMatchObject({
|
||||
maximum: projectedBudget,
|
||||
unit: "projected_bytes",
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
["rpath", 0x8000001c, 12],
|
||||
["fileset", 0x80000035, 32],
|
||||
] as const)(
|
||||
"bounds %s strings before reading their declared extent",
|
||||
async (_name, command, nameOffset) => {
|
||||
const commandSize = 8208;
|
||||
const image = Buffer.alloc(32 + commandSize);
|
||||
image.writeUInt32LE(0xfeedfacf, 0);
|
||||
image.writeUInt32LE(1, 16);
|
||||
image.writeUInt32LE(commandSize, 20);
|
||||
image.writeUInt32LE(command, 32);
|
||||
image.writeUInt32LE(commandSize, 36);
|
||||
image.writeUInt32LE(nameOffset, command === 0x80000035 ? 56 : 40);
|
||||
const stringAt = 32 + nameOffset;
|
||||
image.fill(0x41, stringAt, stringAt + 8000);
|
||||
const projectedBudget = 8192 + 2048 + 32 * 24;
|
||||
const read = async (offset: number, size: number) => {
|
||||
if (offset === stringAt && size > 33)
|
||||
throw new Error("string read beyond its projection allowance");
|
||||
return image.subarray(offset, offset + size);
|
||||
};
|
||||
await expect(
|
||||
readMachoCommandNames(read, image.length, 16384, 1, projectedBudget),
|
||||
).rejects.toMatchObject({
|
||||
maximum: projectedBudget,
|
||||
unit: "projected_bytes",
|
||||
});
|
||||
image[stringAt + 32] = 0;
|
||||
const parsed = await readMachoCommandNames(
|
||||
async (offset, size) => image.subarray(offset, offset + size),
|
||||
image.length,
|
||||
16384,
|
||||
1,
|
||||
projectedBudget,
|
||||
);
|
||||
const name =
|
||||
parsed.commands[0]?.commandString ?? parsed.commands[0]?.fileset?.entryId;
|
||||
expect(name).toHaveLength(32);
|
||||
},
|
||||
);
|
||||
@@ -1,11 +1,15 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { projectAnalysisError } from "../domain/analysisErrorProjection.js";
|
||||
import { fat } from "../domain/binaryTarget.fixture.js";
|
||||
import type { JsonValue } from "../domain/jsonValue.js";
|
||||
import {
|
||||
NativeFixtureRunner,
|
||||
nativeMachoTarget,
|
||||
nativeMachoTargetForFile,
|
||||
} from "../../tests/fixtures/nativeCommands.js";
|
||||
import { createTestTempDirectory } from "../../tests/fixtures/temporaryDirectory.js";
|
||||
import {
|
||||
OwnedCommandFailure,
|
||||
runOwnedCommand,
|
||||
@@ -45,8 +49,11 @@ const execute = async (
|
||||
runner: NativeCommandRunner,
|
||||
parameters: Readonly<Record<string, JsonValue>>,
|
||||
) => {
|
||||
const root = await createTestTempDirectory("rea-native-deadline-");
|
||||
const path = join(root, "app");
|
||||
await writeFile(path, fat([0x01000007, 0x0100000c]));
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
nativeMachoTarget("/fixture/app"),
|
||||
await nativeMachoTargetForFile(path),
|
||||
);
|
||||
try {
|
||||
return await client.execute("list_architectures", parameters);
|
||||
|
||||
@@ -141,6 +141,7 @@ import {
|
||||
inspectNativeMacho,
|
||||
} from "./NativeMachoInspection.js";
|
||||
import { analysisErrorWithCleanupFailure } from "../domain/analysisErrorCleanup.js";
|
||||
import { analysisErrorWithCancellation } from "../domain/analysisErrorCancellation.js";
|
||||
import { ArtifactResourceScope } from "../artifacts/ArtifactResourceScope.js";
|
||||
import { ArtifactReaderFailure } from "../artifacts/ArtifactReader.js";
|
||||
import { projectAnalysisError } from "../domain/analysisErrorProjection.js";
|
||||
@@ -654,13 +655,14 @@ class NativeMacOSClient implements AnalysisClient {
|
||||
case "inspect_plist":
|
||||
return this.#inspectPlist(parameters, signal, timeoutMs);
|
||||
case "list_architectures":
|
||||
return this.#listArchitectures(signal, timeoutMs);
|
||||
return this.#listArchitectures(parameters, signal, timeoutMs);
|
||||
case "demangle_swift":
|
||||
return this.#demangle(parameters, signal, timeoutMs);
|
||||
}
|
||||
}
|
||||
|
||||
async #listArchitectures(
|
||||
parameters: Readonly<Record<string, JsonValue>>,
|
||||
signal: AbortSignal | undefined,
|
||||
timeoutMs: number,
|
||||
): Promise<Result<NativeObservation, AnalysisError>> {
|
||||
@@ -674,39 +676,59 @@ class NativeMacOSClient implements AnalysisClient {
|
||||
"Active artifact is not Mach-O.",
|
||||
),
|
||||
);
|
||||
const capture = await this.#run(
|
||||
"list_architectures",
|
||||
"lipo",
|
||||
["-detailed_info", this.target.path],
|
||||
{ signal, timeoutMs },
|
||||
);
|
||||
if (!capture.ok) return capture;
|
||||
const provenance = [invocation(capture.value, this.target.path)];
|
||||
const parsed = parseLipoCapture(
|
||||
capture.value,
|
||||
"list_architectures",
|
||||
this.target.path,
|
||||
);
|
||||
if (!parsed.ok) return parsed;
|
||||
const { architectures } = parsed.value;
|
||||
const limitations = architectures.flatMap(
|
||||
(architecture) => architecture.limitations,
|
||||
);
|
||||
const result = listArchitecturesSchema.parse({
|
||||
architectures: {
|
||||
items: architectures,
|
||||
total: architectures.length,
|
||||
exhaustive: true,
|
||||
limitations: [],
|
||||
},
|
||||
provenance,
|
||||
limitations,
|
||||
});
|
||||
return ok({
|
||||
result: jsonValueSchema.parse(result),
|
||||
limitations,
|
||||
locations: architectureLocations(result.architectures.items),
|
||||
});
|
||||
try {
|
||||
return await this.#machoResources.run(() =>
|
||||
withNativeMachoSource(
|
||||
this.target,
|
||||
this.#machoResources,
|
||||
signal,
|
||||
async () => {
|
||||
const capture = await this.#run(
|
||||
"list_architectures",
|
||||
"lipo",
|
||||
["-detailed_info", this.target.path],
|
||||
{ signal, timeoutMs },
|
||||
);
|
||||
if (!capture.ok) return capture;
|
||||
const provenance = [invocation(capture.value, this.target.path)];
|
||||
const parsed = parseLipoCapture(
|
||||
capture.value,
|
||||
"list_architectures",
|
||||
this.target.path,
|
||||
);
|
||||
if (!parsed.ok) return parsed;
|
||||
const { architectures } = parsed.value;
|
||||
const limitations = architectures.flatMap(
|
||||
(architecture) => architecture.limitations,
|
||||
);
|
||||
const result = listArchitecturesSchema.parse({
|
||||
architectures: {
|
||||
items: architectures,
|
||||
total: architectures.length,
|
||||
exhaustive: true,
|
||||
limitations: [],
|
||||
},
|
||||
provenance,
|
||||
limitations,
|
||||
});
|
||||
return ok({
|
||||
result: jsonValueSchema.parse(result),
|
||||
limitations,
|
||||
locations: architectureLocations(result.architectures.items),
|
||||
});
|
||||
},
|
||||
),
|
||||
);
|
||||
} catch (cause: unknown) {
|
||||
return err(
|
||||
nativeMachoSourceFailure(
|
||||
cause,
|
||||
this.target,
|
||||
parameters,
|
||||
"list_architectures",
|
||||
),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
async #demangle(
|
||||
@@ -1409,14 +1431,26 @@ class NativeMacOSClient implements AnalysisClient {
|
||||
return await inspect(operand);
|
||||
} catch (cause: unknown) {
|
||||
return err(
|
||||
nativeMachoSourceFailure(cause, this.target, parameters),
|
||||
nativeMachoSourceFailure(
|
||||
cause,
|
||||
this.target,
|
||||
parameters,
|
||||
"inspect_macho",
|
||||
),
|
||||
);
|
||||
}
|
||||
})
|
||||
: inspect(),
|
||||
);
|
||||
} catch (cause: unknown) {
|
||||
return err(nativeMachoSourceFailure(cause, this.target, parameters));
|
||||
return err(
|
||||
nativeMachoSourceFailure(
|
||||
cause,
|
||||
this.target,
|
||||
parameters,
|
||||
"inspect_macho",
|
||||
),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1676,13 +1710,14 @@ const nativeMachoCompletedFailure = (
|
||||
const nativeMachoSourcePrimary = (
|
||||
{ cause }: ArtifactFilePrimaryFacts,
|
||||
path: string,
|
||||
operation: "inspect_macho" | "list_architectures",
|
||||
): AnalysisError => {
|
||||
if (cause instanceof AnalysisError) return cause;
|
||||
if (cause instanceof MachoBinaryFormatError)
|
||||
return new AnalysisOutputError("inspect_macho", cause.message, { cause });
|
||||
return new AnalysisOutputError(operation, cause.message, { cause });
|
||||
if (cause instanceof MachoCommandNamesLimitError)
|
||||
return new AnalysisResourceConstraintError(
|
||||
"inspect_macho",
|
||||
operation,
|
||||
"memory",
|
||||
cause.message,
|
||||
{ maximum: cause.maximum, unit: cause.unit },
|
||||
@@ -1698,9 +1733,11 @@ const nativeMachoSourcePrimary = (
|
||||
? nativeMachoSourcePrimary(
|
||||
artifactFilePrimaryFacts(cause.outcome.cause),
|
||||
path,
|
||||
operation,
|
||||
)
|
||||
: undefined;
|
||||
const previous = failed ?? nativeMachoCompletedFailure(completed);
|
||||
const completedFailure = nativeMachoCompletedFailure(completed);
|
||||
const previous = failed ?? completedFailure;
|
||||
const options = {
|
||||
cause,
|
||||
...(previous === undefined
|
||||
@@ -1713,21 +1750,31 @@ const nativeMachoSourcePrimary = (
|
||||
},
|
||||
}),
|
||||
};
|
||||
if (cause instanceof ArtifactReaderFailure && cause.reason === "cancelled")
|
||||
return new AnalysisCancelledError("inspect_macho", {
|
||||
if (cause instanceof ArtifactReaderFailure && cause.reason === "cancelled") {
|
||||
// A returned failure is already the producer's physical outcome. A later
|
||||
// cancelled identity check must not replace its output or cleanup owner.
|
||||
if (completedFailure !== undefined)
|
||||
return analysisErrorWithCancellation(
|
||||
completedFailure,
|
||||
new AnalysisCancelledError(operation, {
|
||||
cause: artifactFileCancellationCause(cause),
|
||||
}),
|
||||
);
|
||||
return new AnalysisCancelledError(operation, {
|
||||
...options,
|
||||
cause: artifactFileCancellationCause(cause),
|
||||
});
|
||||
}
|
||||
if (cause instanceof ArtifactReaderFailure && cause.reason === "format")
|
||||
return new AnalysisOutputError("inspect_macho", cause.message, options);
|
||||
return new AnalysisOutputError(operation, cause.message, options);
|
||||
if (cause instanceof ArtifactReaderFailure && cause.reason === "integrity")
|
||||
return new AnalysisArtifactChangedError(
|
||||
"inspect_macho",
|
||||
operation,
|
||||
path,
|
||||
cause.message,
|
||||
options,
|
||||
);
|
||||
return new ProviderAdapterError(IDENTITY.id, "inspect_macho", {
|
||||
return new ProviderAdapterError(IDENTITY.id, operation, {
|
||||
...options,
|
||||
userMessage: "The selected Mach-O source could not be read safely.",
|
||||
remediationAction:
|
||||
@@ -1739,17 +1786,18 @@ const nativeMachoCompletion = (
|
||||
cause: unknown,
|
||||
target: BinaryTarget,
|
||||
parameters: Readonly<Record<string, JsonValue>>,
|
||||
operation: "inspect_macho" | "list_architectures",
|
||||
) => {
|
||||
const completion = artifactFileCompletion(cause);
|
||||
// The file operation only completes after the producer result has passed
|
||||
// the final identity check. Its callback is owned by #inspectMacho.
|
||||
// the final identity check. Both Mach-O command workflows own their callbacks.
|
||||
const outcome = completion?.value as
|
||||
| Result<NativeObservation, AnalysisError>
|
||||
| undefined;
|
||||
const observation =
|
||||
outcome?.ok === true
|
||||
? createAnalysisExecutionEvidence(
|
||||
"inspect_macho",
|
||||
operation,
|
||||
parameters,
|
||||
{
|
||||
...createAnalysisExecution(outcome.value.result, IDENTITY, {
|
||||
@@ -1766,7 +1814,7 @@ const nativeMachoCompletion = (
|
||||
const completionCancellation =
|
||||
completion?.cancellation === undefined
|
||||
? undefined
|
||||
: new AnalysisCancelledError("inspect_macho", {
|
||||
: new AnalysisCancelledError(operation, {
|
||||
cause: completion.cancellation.reason,
|
||||
...(completedFailure === undefined ||
|
||||
(cause instanceof ArtifactReaderFailure &&
|
||||
@@ -1787,9 +1835,10 @@ const nativeMachoSourceFailure = (
|
||||
cause: unknown,
|
||||
target: BinaryTarget,
|
||||
parameters: Readonly<Record<string, JsonValue>>,
|
||||
operation: "inspect_macho" | "list_architectures",
|
||||
): AnalysisError => {
|
||||
const { observation, completedFailure, completionCancellation } =
|
||||
nativeMachoCompletion(cause, target, parameters);
|
||||
nativeMachoCompletion(cause, target, parameters, operation);
|
||||
if (cause instanceof ArtifactReaderFailure && cause.cleanup !== undefined) {
|
||||
const physical =
|
||||
cause instanceof ArtifactFileCleanupFailure
|
||||
@@ -1797,7 +1846,11 @@ const nativeMachoSourceFailure = (
|
||||
: undefined;
|
||||
const previous =
|
||||
physical?.outcome.kind === "failed"
|
||||
? nativeMachoSourcePrimary(artifactFilePrimaryFacts(cause), target.path)
|
||||
? nativeMachoSourcePrimary(
|
||||
artifactFilePrimaryFacts(cause),
|
||||
target.path,
|
||||
operation,
|
||||
)
|
||||
: physical?.outcome.kind === "completed"
|
||||
? (completedFailure ?? completionCancellation)
|
||||
: completionCancellation;
|
||||
@@ -1820,7 +1873,7 @@ const nativeMachoSourceFailure = (
|
||||
: {}),
|
||||
},
|
||||
{
|
||||
operation: "inspect_macho",
|
||||
operation,
|
||||
cause,
|
||||
cleanupPrimary: previous,
|
||||
partialObservation: observation,
|
||||
@@ -1841,7 +1894,11 @@ const nativeMachoSourceFailure = (
|
||||
completionCancellation.retainPartialObservation(observation);
|
||||
return completionCancellation;
|
||||
}
|
||||
return nativeMachoSourcePrimary(artifactFilePrimaryFacts(cause), target.path);
|
||||
return nativeMachoSourcePrimary(
|
||||
artifactFilePrimaryFacts(cause),
|
||||
target.path,
|
||||
operation,
|
||||
);
|
||||
};
|
||||
|
||||
interface NativeObservation {
|
||||
|
||||
@@ -170,3 +170,47 @@ it("declares the temporary private operand write in inspect_macho provider capab
|
||||
)?.effects,
|
||||
).toMatchObject({ mayWriteFilesystem: true, mutatesArtifact: false });
|
||||
});
|
||||
|
||||
it.each(["before command", "during command"] as const)(
|
||||
"rejects architecture facts when the admitted target changes %s",
|
||||
async (phase) => {
|
||||
const root = await createTestTempDirectory("rea-lipo-target-identity-");
|
||||
const path = join(root, "fixture.macho");
|
||||
const original = inspectionImage();
|
||||
await writeFile(path, original);
|
||||
const target = await nativeMachoTargetForFile(path);
|
||||
const runner = new NativeFixtureRunner({
|
||||
lipo: `Non-fat file: ${path} is architecture: arm64\n`,
|
||||
});
|
||||
const run = runner.run.bind(runner);
|
||||
const capture = vi
|
||||
.spyOn(runner, "run")
|
||||
.mockImplementation(async (...args) => {
|
||||
if (phase === "during command")
|
||||
await writeFile(
|
||||
path,
|
||||
Buffer.concat([original, Buffer.from("changed")]),
|
||||
);
|
||||
return run(...args);
|
||||
});
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
target,
|
||||
);
|
||||
try {
|
||||
if (phase === "before command")
|
||||
await writeFile(
|
||||
path,
|
||||
Buffer.concat([original, Buffer.from("changed")]),
|
||||
);
|
||||
const result = await client.execute("list_architectures", {});
|
||||
if (result.ok) throw new Error("Expected target identity refusal");
|
||||
expect(result.error).toMatchObject({
|
||||
_tag: "AnalysisArtifactChangedError",
|
||||
operation: "list_architectures",
|
||||
});
|
||||
expect(capture).toHaveBeenCalledTimes(phase === "before command" ? 0 : 1);
|
||||
} finally {
|
||||
await client.close();
|
||||
}
|
||||
},
|
||||
);
|
||||
@@ -9,12 +9,12 @@ export const APPLE_DISPATCH_METADATA_ANALYSIS_PROFILE = createAnalysisProfile(
|
||||
{
|
||||
id: NATIVE_MACOS_PROVIDER_IDENTITY.id,
|
||||
name: NATIVE_MACOS_PROVIDER_IDENTITY.name,
|
||||
version: "apple-metadata-reader-3",
|
||||
version: "apple-metadata-reader-4",
|
||||
},
|
||||
{
|
||||
operation: "inspect_native_dispatch_metadata",
|
||||
reader: "apple-dispatch-metadata",
|
||||
revision: 3,
|
||||
revision: 4,
|
||||
},
|
||||
);
|
||||
/** Operations whose target process can show UI, use the network and write files. */
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
import { expect, it } from "vitest";
|
||||
import type { NativeCommandCapture } from "./CommandRunner.js";
|
||||
import { parseDyldFileTypeRefusal } from "./NativeMachoCommandDiagnostics.js";
|
||||
|
||||
const capture = (stdout: string, stderr = ""): NativeCommandCapture => ({
|
||||
tool: "dyld_info",
|
||||
executable: "/usr/bin/dyld_info",
|
||||
executableSha256: "a".repeat(64),
|
||||
toolVersion: null,
|
||||
versionReason: null,
|
||||
arguments: ["-imports", "/selected/target"],
|
||||
stdout,
|
||||
stderr,
|
||||
stdoutBytes: Buffer.byteLength(stdout),
|
||||
stderrBytes: Buffer.byteLength(stderr),
|
||||
exitCode: 1,
|
||||
signal: null,
|
||||
});
|
||||
|
||||
it.each([
|
||||
["unknown filetype 3", "3"],
|
||||
["unknown mh.filetype 4", "4"],
|
||||
])("recognizes a sole dyld file-type refusal (%s)", (diagnostic, fileType) => {
|
||||
expect(
|
||||
parseDyldFileTypeRefusal(capture(`/selected/target:\n${diagnostic}\n`)),
|
||||
).toEqual({ fileType, diagnostic });
|
||||
});
|
||||
|
||||
it.each([
|
||||
["unknown mh.filetype 4\nmalformed load command\n", ""],
|
||||
["unknown mh.filetype 4\n", "read failed\n"],
|
||||
])("keeps mixed dyld diagnostics unclassified (%s, %s)", (stdout, stderr) => {
|
||||
expect(parseDyldFileTypeRefusal(capture(stdout, stderr))).toBeNull();
|
||||
});
|
||||
@@ -91,22 +91,17 @@ export const isUnbackedTextDyldFailure = (
|
||||
dyldFailureDiagnostic(capture) ===
|
||||
"section '__TEXT/__text' has offset=0 but is not a zero-fill section type";
|
||||
|
||||
/** Reported CORE/FVMLIB refusals still require an independently matching header. */
|
||||
/** A sole CORE/FVMLIB refusal still requires an independently matching header. */
|
||||
export const parseDyldFileTypeRefusal = (
|
||||
capture: NativeCommandCapture,
|
||||
): {
|
||||
readonly fileType: "3" | "4";
|
||||
readonly diagnostic: string;
|
||||
} | null => {
|
||||
for (const line of dyldFailureDiagnostics(capture, [
|
||||
capture.stdout,
|
||||
capture.stderr,
|
||||
])) {
|
||||
const fileType = /^unknown (?:mh\.)?filetype ([34])$/u.exec(line)?.[1];
|
||||
if (fileType === "3" || fileType === "4")
|
||||
return { fileType, diagnostic: line };
|
||||
}
|
||||
return null;
|
||||
const diagnostic = dyldFailureDiagnostic(capture);
|
||||
if (diagnostic === null) return null;
|
||||
const fileType = /^unknown (?:mh\.)?filetype ([34])$/u.exec(diagnostic)?.[1];
|
||||
return fileType === "3" || fileType === "4" ? { fileType, diagnostic } : null;
|
||||
};
|
||||
|
||||
/** Complete captures come from the settled native command owner. */
|
||||
|
||||
@@ -519,6 +519,7 @@ describe("Mach-O encryption reporting", () => {
|
||||
container_file_offset: 32768,
|
||||
size: 8192,
|
||||
status: "absent",
|
||||
malformed_kind: null,
|
||||
reason: null,
|
||||
commands: [],
|
||||
range: null,
|
||||
@@ -602,6 +603,7 @@ describe("Mach-O encryption reporting", () => {
|
||||
slice({
|
||||
container_file_offset: 49152,
|
||||
status: "malformed",
|
||||
malformed_kind: "structure",
|
||||
reason: "load commands is truncated",
|
||||
}),
|
||||
],
|
||||
|
||||
@@ -16,9 +16,16 @@ const control = vi.hoisted(() => ({
|
||||
read: undefined as undefined | (() => Promise<never>),
|
||||
}));
|
||||
|
||||
it.each([false, true])(
|
||||
"retains verified inspection evidence through close retry (late cancellation: %s)",
|
||||
async (cancelDuringClose) => {
|
||||
it.each(
|
||||
(["inspect_macho", "list_architectures"] as const).flatMap((operation) =>
|
||||
[false, true].map((cancelDuringClose) => ({
|
||||
operation,
|
||||
cancelDuringClose,
|
||||
})),
|
||||
),
|
||||
)(
|
||||
"retains verified $operation evidence through close retry (late cancellation: $cancelDuringClose)",
|
||||
async ({ operation, cancelDuringClose }) => {
|
||||
const root = await createTestTempDirectory("rea-macho-completed-close-");
|
||||
const path = join(root, "fixture.macho");
|
||||
await writeFile(path, inspectionImage());
|
||||
@@ -60,7 +67,7 @@ it.each([false, true])(
|
||||
await client.close();
|
||||
});
|
||||
const result = await client.execute(
|
||||
"inspect_macho",
|
||||
operation,
|
||||
{ native_command_timeout_ms: 5000 },
|
||||
{ signal: controller.signal },
|
||||
);
|
||||
@@ -71,7 +78,7 @@ it.each([false, true])(
|
||||
expect(result.error.cleanupIncomplete).toBe(true);
|
||||
expect(result.error.cleanupResources).toEqual([path]);
|
||||
expect(result.error.partialObservation).toMatchObject({
|
||||
operation: "inspect_macho",
|
||||
operation,
|
||||
parameters: { native_command_timeout_ms: 5000 },
|
||||
subject: { local_path: path, digest: { sha256: target.sha256 } },
|
||||
normalized_result: { provenance: expect.any(Array) },
|
||||
@@ -108,9 +115,13 @@ it.each([false, true])(
|
||||
},
|
||||
);
|
||||
|
||||
it.each([false, true])(
|
||||
"retains the producer outcome when cancellation arrives during successful close (producer fails: %s)",
|
||||
async (producerFails) => {
|
||||
it.each(
|
||||
(["inspect_macho", "list_architectures"] as const).flatMap((operation) =>
|
||||
[false, true].map((producerFails) => ({ operation, producerFails })),
|
||||
),
|
||||
)(
|
||||
"retains the $operation producer outcome when cancellation arrives during successful close (producer fails: $producerFails)",
|
||||
async ({ operation, producerFails }) => {
|
||||
const root = await createTestTempDirectory("rea-macho-cancel-close-");
|
||||
const path = join(root, "fixture.macho");
|
||||
await writeFile(path, inspectionImage());
|
||||
@@ -148,7 +159,7 @@ it.each([false, true])(
|
||||
await client.close();
|
||||
});
|
||||
const result = await client.execute(
|
||||
"inspect_macho",
|
||||
operation,
|
||||
{},
|
||||
{ signal: controller.signal },
|
||||
);
|
||||
@@ -174,7 +185,7 @@ it.each([false, true])(
|
||||
});
|
||||
} else {
|
||||
expect(result.error.partialObservation).toMatchObject({
|
||||
operation: "inspect_macho",
|
||||
operation,
|
||||
subject: { local_path: path, digest: { sha256: target.sha256 } },
|
||||
normalized_result: { provenance: expect.any(Array) },
|
||||
});
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { expect, it, vi } from "vitest";
|
||||
|
||||
import * as machoReader from "../../artifacts/apple/MachoLoadCommandReader.js";
|
||||
import { inspectAppleIpsInputSchema } from "../../domain/native/appleIps.js";
|
||||
import { createTestTempDirectory } from "../../../tests/fixtures/temporaryDirectory.js";
|
||||
import { appleIpsBytes } from "../../../tests/fixtures/binaryDiagnostics/appleIps.js";
|
||||
import { AppleIpsProvider } from "./AppleIpsProvider.js";
|
||||
|
||||
it("retains completed join facts when cancellation arrives during join parsing", async () => {
|
||||
const root = await createTestTempDirectory("rea-ips-join-cancel-");
|
||||
const path = join(root, "report.ips");
|
||||
const joinPath = join(root, "image.bin");
|
||||
await writeFile(path, appleIpsBytes());
|
||||
const image = Buffer.alloc(32);
|
||||
image.writeUInt32LE(0xfeedfacf, 0);
|
||||
image.writeUInt32LE(0x0100000c, 4);
|
||||
image.writeUInt32LE(2, 12);
|
||||
await writeFile(joinPath, image);
|
||||
const input = inspectAppleIpsInputSchema.parse({ path, join_path: joinPath });
|
||||
const provider = new AppleIpsProvider();
|
||||
const controller = new AbortController();
|
||||
const reason = new Error("cancel while joining selected image");
|
||||
const readContainer = machoReader.readMachoContainer;
|
||||
const spy = vi
|
||||
.spyOn(machoReader, "readMachoContainer")
|
||||
.mockImplementationOnce(async (...arguments_) => {
|
||||
const container = await readContainer(...arguments_);
|
||||
controller.abort(reason);
|
||||
return container;
|
||||
});
|
||||
try {
|
||||
const cancelled = await provider.inspect(input, {
|
||||
signal: controller.signal,
|
||||
});
|
||||
if (cancelled.ok) throw new Error("Expected cancellation during join");
|
||||
expect(cancelled.error.cause).toBe(reason);
|
||||
expect(cancelled.error).toMatchObject({
|
||||
_tag: "AnalysisCancelledError",
|
||||
cause: reason,
|
||||
partialObservation: {
|
||||
artifact: { path },
|
||||
join: {
|
||||
status: "selected",
|
||||
path: joinPath,
|
||||
slices: [{ arch: "arm64" }],
|
||||
},
|
||||
join_artifact: { path: joinPath },
|
||||
},
|
||||
});
|
||||
const recovered = await provider.inspect(input);
|
||||
if (!recovered.ok) throw recovered.error;
|
||||
expect(recovered.value.join).toMatchObject({
|
||||
status: "selected",
|
||||
path: joinPath,
|
||||
});
|
||||
} finally {
|
||||
spy.mockRestore();
|
||||
await provider.close();
|
||||
}
|
||||
});
|
||||
@@ -112,7 +112,7 @@ export class AppleIpsProvider implements AppleIpsPort {
|
||||
);
|
||||
completedSnapshot = joinArtifact;
|
||||
assertArtifactReadActive(options?.signal);
|
||||
return ok({
|
||||
completedReport = {
|
||||
...report,
|
||||
join: await resolveAppleIpsJoin(
|
||||
report,
|
||||
@@ -123,7 +123,9 @@ export class AppleIpsProvider implements AppleIpsPort {
|
||||
},
|
||||
read,
|
||||
),
|
||||
});
|
||||
};
|
||||
assertArtifactReadActive(options?.signal);
|
||||
return ok(completedReport);
|
||||
});
|
||||
} catch (cause) {
|
||||
const primary = appleIpsFailurePrimary(
|
||||
|
||||
@@ -1186,6 +1186,20 @@ it("keeps header rows when a slice has conflicting encryption commands", async (
|
||||
});
|
||||
});
|
||||
|
||||
it("keeps a later malformed encryption command distinct from duplicate ambiguity", async () => {
|
||||
const bytes = machoHardeningFixture({
|
||||
extraCommands: [
|
||||
machoCommand(LC_ENCRYPTION_INFO_64, 24),
|
||||
machoCommand(LC_ENCRYPTION_INFO_64, 24),
|
||||
machoCommand(LC_ENCRYPTION_INFO_64, 8),
|
||||
],
|
||||
});
|
||||
await expect(readMachoHardening(bytes)).rejects.toMatchObject({
|
||||
kind: "malformed",
|
||||
message: expect.stringContaining("cmdsize 8"),
|
||||
});
|
||||
});
|
||||
|
||||
it("keeps a parsed fat slice when another slice is empty or past EOF", async () => {
|
||||
const arm = machoHardeningFixture();
|
||||
const images = await readMachoHardening(
|
||||
@@ -1414,6 +1428,32 @@ it("sizes an empty DT_GNU_HASH table only from an agreeing SHT_DYNSYM", () => {
|
||||
});
|
||||
});
|
||||
|
||||
it.each([32, 64] as const)(
|
||||
"does not interpret %i-bit Mach-O debug symbol type bits as an import",
|
||||
async (bits) => {
|
||||
const bytes = machoHardeningFixture({ bits, stackChk: true });
|
||||
let commandAt = bits === 64 ? 32 : 28;
|
||||
let symbolAt: number | undefined;
|
||||
for (let index = 0; index < bytes.readUInt32LE(16); index += 1) {
|
||||
if (bytes.readUInt32LE(commandAt) === 2)
|
||||
symbolAt = bytes.readUInt32LE(commandAt + 8);
|
||||
commandAt += bytes.readUInt32LE(commandAt + 4);
|
||||
}
|
||||
if (symbolAt === undefined) throw new Error("Missing LC_SYMTAB");
|
||||
expect(
|
||||
findRow(
|
||||
(await readMachoHardening(bytes))[0]?.rows ?? [],
|
||||
"stack_protector",
|
||||
).state,
|
||||
).toBe("enabled");
|
||||
// N_STAB takes precedence over ordinary N_TYPE and N_EXT interpretation.
|
||||
bytes.writeUInt8(0x21, symbolAt + 4);
|
||||
const image = (await readMachoHardening(bytes))[0];
|
||||
expect(findRow(image?.rows ?? [], "stack_protector").state).toBe("unknown");
|
||||
expect(findRow(image?.rows ?? [], "pie").state).toBe("enabled");
|
||||
},
|
||||
);
|
||||
|
||||
it("keeps an unresolved symbol count distinct from an absent table", () => {
|
||||
const image = readElfHardening(
|
||||
withEmptyGnuHash(elfHardeningFixture({ sections: false, stackChk: true })),
|
||||
|
||||
@@ -343,7 +343,10 @@ const readCommandFacts = (
|
||||
* wrong width, is structural and fails the slice before any row exists.
|
||||
*/
|
||||
const admitEncryption = (encrypted: MachoSliceEncryption): void => {
|
||||
if (encrypted.status === "malformed" && encrypted.commands.length < 2)
|
||||
if (
|
||||
encrypted.status === "malformed" &&
|
||||
encrypted.malformed_kind !== "duplicate-commands"
|
||||
)
|
||||
malformed(
|
||||
encrypted.reason ?? "Mach-O encryption load command is malformed",
|
||||
);
|
||||
@@ -595,10 +598,11 @@ const stackRow = (
|
||||
const entry = symbolAt + index * width;
|
||||
const nameOffset = bytes.readUInt32LE(entry);
|
||||
if (nameOffset === 0) continue;
|
||||
// N_EXT with N_TYPE clear is an undefined external. A defined export of
|
||||
// the same name, including libc itself, is not an import into this image.
|
||||
// N_STAB records use a different type namespace. Only an ordinary N_EXT
|
||||
// with N_TYPE clear is an undefined external; defined exports are not imports.
|
||||
const nType = bytes.readUInt8(entry + 4);
|
||||
if ((nType & 0x0e) !== 0 || (nType & 0x01) === 0) continue;
|
||||
if ((nType & 0xe0) !== 0 || (nType & 0x0e) !== 0 || (nType & 0x01) === 0)
|
||||
continue;
|
||||
// A common definition shares those type bits but carries its size in
|
||||
// n_value, so only a zero n_value names an import.
|
||||
if (
|
||||
|
||||
@@ -0,0 +1,53 @@
|
||||
import {
|
||||
ArtifactResourceScope,
|
||||
type ArtifactResourceOwner,
|
||||
} from "../../artifacts/ArtifactResourceScope.js";
|
||||
|
||||
/** Retain a cancelled response branch until its underlying cancellation settles. */
|
||||
export class StateResponseCleanup {
|
||||
readonly #scope = new ArtifactResourceScope();
|
||||
|
||||
constructor(private readonly changed: () => void = () => {}) {}
|
||||
|
||||
get cleanupResources(): readonly string[] {
|
||||
return this.#scope.cleanupResources;
|
||||
}
|
||||
|
||||
cancel(cancel: () => Promise<void>): void {
|
||||
let state:
|
||||
| { status: "pending" }
|
||||
| { status: "done" }
|
||||
| { status: "failed"; cause: unknown } = { status: "pending" };
|
||||
const owner: ArtifactResourceOwner = {
|
||||
kind: "lease",
|
||||
resource: "state response body",
|
||||
lease: {
|
||||
release: async () => {
|
||||
if (state.status === "pending")
|
||||
throw new Error("State response cancellation is still pending");
|
||||
if (state.status === "failed") throw state.cause;
|
||||
},
|
||||
},
|
||||
};
|
||||
this.#scope.retain(owner);
|
||||
this.changed();
|
||||
void Promise.resolve()
|
||||
.then(cancel)
|
||||
.then(
|
||||
async () => {
|
||||
state = { status: "done" };
|
||||
await this.#scope.release(owner);
|
||||
this.changed();
|
||||
},
|
||||
(cause: unknown) => {
|
||||
state = { status: "failed", cause };
|
||||
this.changed();
|
||||
},
|
||||
)
|
||||
.catch(() => undefined);
|
||||
}
|
||||
|
||||
close(): Promise<void> {
|
||||
return this.#scope.close();
|
||||
}
|
||||
}
|
||||
@@ -1,3 +1,4 @@
|
||||
import { StateResponseCleanup } from "./StateResponseCleanup.js";
|
||||
import type { EnvironmentStateStore } from "../../application/environment/environmentStateStore.js";
|
||||
import { ArtifactResourceScope } from "../../artifacts/ArtifactResourceScope.js";
|
||||
import type { AnalysisInputError } from "../../domain/analysisErrorCore.js";
|
||||
@@ -46,17 +47,24 @@ interface CallContext {
|
||||
readonly intake: StateIntake;
|
||||
readonly cancel: AbortSignal;
|
||||
readonly files: ArtifactResourceScope;
|
||||
readonly responses: StateResponseCleanup;
|
||||
}
|
||||
|
||||
/** `data/add`: exactly one part, whose document replaces the whole state only when it is valid and the call was not cancelled. */
|
||||
const addState = async (
|
||||
{ store, intake, cancel, files }: CallContext,
|
||||
{ store, intake, cancel, files, responses }: CallContext,
|
||||
params: unknown,
|
||||
): Promise<RpcOutcome> => {
|
||||
const parts = isRecord(params) ? params.parts : undefined;
|
||||
if (!Array.isArray(parts) || parts.length !== 1)
|
||||
return { error: invalidParams("data/add takes exactly one part") };
|
||||
const document = await partDocument(parts[0], intake, cancel, files);
|
||||
const document = await partDocument(
|
||||
parts[0],
|
||||
intake,
|
||||
cancel,
|
||||
files,
|
||||
responses,
|
||||
);
|
||||
if (!document.ok) return { error: document.error };
|
||||
// A file read is not interruptible, so a cancellation during it is honoured here, before the state changes.
|
||||
if (cancel.aborted) return { error: CANCELLED };
|
||||
@@ -101,6 +109,7 @@ export const stateDataPlane = (
|
||||
intake: StateIntake = DEFAULT_STATE_INTAKE,
|
||||
stopped: AbortSignal = new AbortController().signal,
|
||||
files: ArtifactResourceScope = new ArtifactResourceScope(),
|
||||
responses: StateResponseCleanup = new StateResponseCleanup(),
|
||||
): RpcMethods => {
|
||||
let previous: Promise<unknown> = Promise.resolve();
|
||||
return (method, params, signal) => {
|
||||
@@ -111,7 +120,7 @@ export const stateDataPlane = (
|
||||
const next = previous.then(() =>
|
||||
cancel.aborted
|
||||
? { error: CANCELLED }
|
||||
: run({ store, intake, cancel, files }, params),
|
||||
: run({ store, intake, cancel, files, responses }, params),
|
||||
);
|
||||
previous = next.catch(() => undefined);
|
||||
return next;
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { StateResponseCleanup } from "./StateResponseCleanup.js";
|
||||
import type { HttpHostname } from "../../domain/httpHostname.js";
|
||||
import { STATE_INTAKE_LIMIT_BYTES } from "../../application/environment/environmentStateDocument.js";
|
||||
import {
|
||||
@@ -477,6 +478,8 @@ export const serveEnvironment = async (
|
||||
};
|
||||
// A state file whose close failed stays owned here: later file reads retry it, and close reports it if it is still open.
|
||||
const stateFiles = new ArtifactResourceScope();
|
||||
let responseStateChanged = (): void => undefined;
|
||||
const stateResponses = new StateResponseCleanup(() => responseStateChanged());
|
||||
const served = await serveStreamableHttp({
|
||||
host,
|
||||
port,
|
||||
@@ -499,6 +502,7 @@ export const serveEnvironment = async (
|
||||
},
|
||||
stopping.signal,
|
||||
stateFiles,
|
||||
stateResponses,
|
||||
),
|
||||
),
|
||||
...(logger === undefined ? {} : { logger }),
|
||||
@@ -512,11 +516,14 @@ export const serveEnvironment = async (
|
||||
});
|
||||
let httpClosePending = false;
|
||||
let stateClosePending = false;
|
||||
let responseClosePending = false;
|
||||
let settledSuccessful = false;
|
||||
let closing: Promise<void> | undefined;
|
||||
const shutdownFailures = new Set<AnalysisError>();
|
||||
const owner: EnvironmentShutdownOwner = {
|
||||
get cleanupResources() {
|
||||
const stateResources = stateFiles.cleanupResources;
|
||||
const responseResources = stateResponses.cleanupResources;
|
||||
return [
|
||||
...(httpClosePending ? [served.url] : []),
|
||||
...(stateClosePending
|
||||
@@ -524,6 +531,11 @@ export const serveEnvironment = async (
|
||||
? stateResources
|
||||
: ["environment state-file scope"]
|
||||
: []),
|
||||
...(responseClosePending
|
||||
? responseResources.length > 0
|
||||
? responseResources
|
||||
: ["state response cleanup"]
|
||||
: []),
|
||||
];
|
||||
},
|
||||
close: () => {
|
||||
@@ -531,7 +543,7 @@ export const serveEnvironment = async (
|
||||
const attempt = (async () => {
|
||||
stop();
|
||||
const failures: {
|
||||
readonly stage: "http-server" | "state-files";
|
||||
readonly stage: "http-server" | "state-files" | "state-responses";
|
||||
readonly cause: unknown;
|
||||
}[] = [];
|
||||
try {
|
||||
@@ -548,6 +560,15 @@ export const serveEnvironment = async (
|
||||
stateClosePending = true;
|
||||
failures.push({ stage: "state-files", cause });
|
||||
}
|
||||
try {
|
||||
await stateResponses.close();
|
||||
if (stateResponses.cleanupResources.length > 0)
|
||||
throw new Error("State response cleanup remains pending");
|
||||
responseClosePending = false;
|
||||
} catch (cause: unknown) {
|
||||
responseClosePending = true;
|
||||
failures.push({ stage: "state-responses", cause });
|
||||
}
|
||||
if (failures.length > 0) {
|
||||
retainedEnvironmentShutdowns.add(owner);
|
||||
const failure = new AnalysisOutputError(
|
||||
@@ -583,6 +604,7 @@ export const serveEnvironment = async (
|
||||
retainedEnvironmentShutdowns.delete(owner);
|
||||
for (const failure of shutdownFailures) failure.resolveCleanup();
|
||||
shutdownFailures.clear();
|
||||
settledSuccessful = true;
|
||||
})();
|
||||
closing = attempt;
|
||||
void attempt.catch(() => {
|
||||
@@ -591,6 +613,26 @@ export const serveEnvironment = async (
|
||||
return attempt;
|
||||
},
|
||||
};
|
||||
// A fetcher may hand back a response after an earlier stop completed. Keep
|
||||
// that newly acquired body owned and make a later close observe its outcome.
|
||||
responseStateChanged = () => {
|
||||
if (!stopping.signal.aborted) return;
|
||||
if (stateResponses.cleanupResources.length > 0) {
|
||||
responseClosePending = true;
|
||||
retainedEnvironmentShutdowns.add(owner);
|
||||
if (settledSuccessful) {
|
||||
settledSuccessful = false;
|
||||
closing = undefined;
|
||||
}
|
||||
} else if (
|
||||
shutdownFailures.size === 0 &&
|
||||
!httpClosePending &&
|
||||
!stateClosePending
|
||||
) {
|
||||
responseClosePending = false;
|
||||
retainedEnvironmentShutdowns.delete(owner);
|
||||
}
|
||||
};
|
||||
return ok({
|
||||
...served,
|
||||
card,
|
||||
|
||||
@@ -1037,7 +1037,122 @@ describe("serveEnvironment with a state", () => {
|
||||
expect(missing.isError).toBe(true);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("state response cleanup", () => {
|
||||
it("reports pending teed response cleanup and retries after its sibling closes", async () => {
|
||||
let sourceCancelled = false;
|
||||
const stream = new ReadableStream<Uint8Array>({
|
||||
start(controller) {
|
||||
controller.enqueue(new Uint8Array([1]));
|
||||
},
|
||||
cancel() {
|
||||
sourceCancelled = true;
|
||||
},
|
||||
});
|
||||
const [body, sibling] = stream.tee();
|
||||
const environment = await serveState(
|
||||
{ source, state },
|
||||
{
|
||||
fetchState: async () =>
|
||||
new Response(body, {
|
||||
headers: { "content-length": String(STATE_INTAKE_LIMIT_BYTES + 1) },
|
||||
}),
|
||||
},
|
||||
);
|
||||
let timer: ReturnType<typeof setTimeout> | undefined;
|
||||
try {
|
||||
const response = await fetch(
|
||||
new URL(ENVIRONMENT_RPC_PATH, environment.url),
|
||||
{
|
||||
method: "POST",
|
||||
headers: { "content-type": "application/json" },
|
||||
body: JSON.stringify(addByUri(1)),
|
||||
signal: AbortSignal.timeout(10_000),
|
||||
},
|
||||
);
|
||||
await expect(response.json()).resolves.toMatchObject({
|
||||
error: { code: -32602 },
|
||||
});
|
||||
const closing = Promise.race([
|
||||
environment.close(),
|
||||
new Promise<never>((_, reject) => {
|
||||
timer = setTimeout(
|
||||
() => reject(new Error("server close waited for tee sibling")),
|
||||
10_000,
|
||||
);
|
||||
}),
|
||||
]);
|
||||
await expect(closing).rejects.toMatchObject({
|
||||
_tag: "AnalysisOutputError",
|
||||
cleanupIncomplete: true,
|
||||
diagnostics: { cleanup_stages: ["state-responses"] },
|
||||
});
|
||||
expect(sourceCancelled).toBe(false);
|
||||
await sibling.cancel();
|
||||
expect(sourceCancelled).toBe(true);
|
||||
await expect(environment.close()).resolves.toBeUndefined();
|
||||
} finally {
|
||||
if (timer !== undefined) clearTimeout(timer);
|
||||
await Promise.allSettled([body.cancel(), sibling.cancel()]);
|
||||
await environment.close();
|
||||
}
|
||||
});
|
||||
|
||||
it("retains a late response cleanup after an earlier successful stop", async () => {
|
||||
let giveResponse!: (response: Response) => void;
|
||||
const gate = new Promise<Response>((resolve) => {
|
||||
giveResponse = resolve;
|
||||
});
|
||||
const held = heldFetcher(() => gate);
|
||||
let release!: () => void;
|
||||
let acknowledge!: () => void;
|
||||
const cleanup = new Promise<void>((resolve) => {
|
||||
release = resolve;
|
||||
});
|
||||
const entered = new Promise<void>((resolve) => {
|
||||
acknowledge = resolve;
|
||||
});
|
||||
const environment = await serveState(
|
||||
{ source, state },
|
||||
{ fetchState: held.fetchState },
|
||||
);
|
||||
const answered = fetch(new URL(ENVIRONMENT_RPC_PATH, environment.url), {
|
||||
method: "POST",
|
||||
headers: { "content-type": "application/json" },
|
||||
body: JSON.stringify(addByUri(1)),
|
||||
signal: AbortSignal.timeout(10_000),
|
||||
}).catch(() => undefined);
|
||||
try {
|
||||
await held.fetching;
|
||||
await environment.close();
|
||||
giveResponse(
|
||||
new Response(
|
||||
new ReadableStream<Uint8Array>({
|
||||
cancel() {
|
||||
acknowledge();
|
||||
return cleanup;
|
||||
},
|
||||
}),
|
||||
),
|
||||
);
|
||||
await entered;
|
||||
await expect(environment.close()).rejects.toMatchObject({
|
||||
_tag: "AnalysisOutputError",
|
||||
cleanupIncomplete: true,
|
||||
diagnostics: { cleanup_stages: ["state-responses"] },
|
||||
});
|
||||
release();
|
||||
await expect(environment.close()).resolves.toBeUndefined();
|
||||
} finally {
|
||||
release();
|
||||
await answered;
|
||||
await environment.close();
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("serveEnvironment state file cleanup", () => {
|
||||
it("stops without waiting for a stalled download", async () => {
|
||||
const held = heldFetcher(() => new Promise<Response>(() => undefined));
|
||||
const environment = await serveState(
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { StateResponseCleanup } from "./StateResponseCleanup.js";
|
||||
import { expect, it, vi } from "vitest";
|
||||
|
||||
import { ArtifactResourceScope } from "../../artifacts/ArtifactResourceScope.js";
|
||||
@@ -11,14 +12,17 @@ import {
|
||||
|
||||
const inlineDocument = async (bytes: string) => {
|
||||
const files = new ArtifactResourceScope();
|
||||
const responses = new StateResponseCleanup();
|
||||
try {
|
||||
return await partDocument(
|
||||
{ kind: "file", file: { bytes } },
|
||||
DEFAULT_STATE_INTAKE,
|
||||
new AbortController().signal,
|
||||
files,
|
||||
responses,
|
||||
);
|
||||
} finally {
|
||||
await responses.close();
|
||||
await files.close();
|
||||
}
|
||||
};
|
||||
@@ -79,3 +83,109 @@ it("downloads with redirects refused and the 30 s timeout by default", async ()
|
||||
fetched.mockRestore();
|
||||
}
|
||||
});
|
||||
|
||||
it.each(["http-status", "declared-overflow", "stream-overflow"] as const)(
|
||||
"returns %s while a teed response's other branch remains open",
|
||||
async (scenario) => {
|
||||
const source = new ReadableStream<Uint8Array>({
|
||||
start(controller) {
|
||||
controller.enqueue(
|
||||
new Uint8Array(
|
||||
scenario === "stream-overflow" ? STATE_INTAKE_LIMIT_BYTES + 1 : 1,
|
||||
),
|
||||
);
|
||||
},
|
||||
});
|
||||
const [body, sibling] = source.tee();
|
||||
const response = new Response(body, {
|
||||
status: scenario === "http-status" ? 503 : 200,
|
||||
...(scenario === "declared-overflow"
|
||||
? {
|
||||
headers: { "content-length": String(STATE_INTAKE_LIMIT_BYTES + 1) },
|
||||
}
|
||||
: {}),
|
||||
});
|
||||
const files = new ArtifactResourceScope();
|
||||
const responses = new StateResponseCleanup();
|
||||
const operation = partDocument(
|
||||
{ kind: "file", file: { uri: "https://state.example.test/state.json" } },
|
||||
{ fetchState: async () => response, timeoutMs: 1_000 },
|
||||
new AbortController().signal,
|
||||
files,
|
||||
responses,
|
||||
);
|
||||
let timer: ReturnType<typeof setTimeout> | undefined;
|
||||
try {
|
||||
const outcome = await Promise.race([
|
||||
operation.then((result) => ({ kind: "result" as const, result })),
|
||||
new Promise<{ kind: "deadline" }>((resolve) => {
|
||||
timer = setTimeout(() => resolve({ kind: "deadline" }), 3_000);
|
||||
}),
|
||||
]);
|
||||
expect(outcome.kind).toBe("result");
|
||||
expect(responses.cleanupResources).toEqual(["state response body"]);
|
||||
await expect(responses.close()).rejects.toMatchObject({
|
||||
reason: "unavailable",
|
||||
});
|
||||
if (outcome.kind === "result") {
|
||||
expect(outcome.result).toMatchObject(
|
||||
scenario === "http-status"
|
||||
? { ok: false, error: { data: { reason: "http-status" } } }
|
||||
: {
|
||||
ok: false,
|
||||
error: {
|
||||
message: expect.stringContaining(
|
||||
String(STATE_INTAKE_LIMIT_BYTES),
|
||||
),
|
||||
},
|
||||
},
|
||||
);
|
||||
}
|
||||
} finally {
|
||||
if (timer !== undefined) clearTimeout(timer);
|
||||
await sibling.cancel();
|
||||
await operation;
|
||||
await responses.close();
|
||||
await files.close();
|
||||
}
|
||||
},
|
||||
);
|
||||
|
||||
it("retains the exact failure when response cancellation rejects", async () => {
|
||||
const failure = new Error("controlled cancellation failure");
|
||||
const body = new ReadableStream<Uint8Array>({
|
||||
cancel() {
|
||||
throw failure;
|
||||
},
|
||||
});
|
||||
const files = new ArtifactResourceScope();
|
||||
const responses = new StateResponseCleanup();
|
||||
const result = await partDocument(
|
||||
{ kind: "file", file: { uri: "https://state.example.test/state.json" } },
|
||||
{
|
||||
fetchState: async () => new Response(body, { status: 503 }),
|
||||
timeoutMs: 1_000,
|
||||
},
|
||||
new AbortController().signal,
|
||||
files,
|
||||
responses,
|
||||
);
|
||||
expect(result).toMatchObject({
|
||||
ok: false,
|
||||
error: { data: { reason: "http-status" } },
|
||||
});
|
||||
await new Promise<void>((resolve) => setImmediate(resolve));
|
||||
const rejected: unknown = await responses
|
||||
.close()
|
||||
.catch((cause: unknown) => cause);
|
||||
expect(rejected).toMatchObject({
|
||||
reason: "unavailable",
|
||||
cleanup: { resources: ["state response body"] },
|
||||
});
|
||||
expect((rejected as Error).cause).toBeInstanceOf(AggregateError);
|
||||
expect(((rejected as Error).cause as AggregateError).errors).toContain(
|
||||
failure,
|
||||
);
|
||||
expect(responses.cleanupResources).toEqual(["state response body"]);
|
||||
await files.close();
|
||||
});
|
||||
@@ -1,3 +1,4 @@
|
||||
import { StateResponseCleanup } from "./StateResponseCleanup.js";
|
||||
import { fileURLToPath } from "node:url";
|
||||
|
||||
import { mediaTypeEssence } from "../../domain/analysisView/recordedMediaType.js";
|
||||
@@ -228,6 +229,7 @@ const downloadBounds = (
|
||||
const readCapped = async (
|
||||
body: ReadableStream<Uint8Array> | null,
|
||||
bounds: DownloadBounds,
|
||||
responses: StateResponseCleanup,
|
||||
): Promise<Result<Buffer, RpcError>> => {
|
||||
if (body === null) return ok(Buffer.alloc(0));
|
||||
const reader = body.getReader();
|
||||
@@ -240,13 +242,15 @@ const readCapped = async (
|
||||
if (done) return ok(Buffer.concat(chunks, total));
|
||||
total += value.byteLength;
|
||||
if (total > STATE_INTAKE_LIMIT_BYTES) {
|
||||
await reader.cancel().catch(() => undefined);
|
||||
// A tee's sibling can be caller-owned; cancelling this branch must not
|
||||
// delay the refusal until that sibling finishes.
|
||||
responses.cancel(() => reader.cancel());
|
||||
return err(TOO_LARGE);
|
||||
}
|
||||
chunks.push(value);
|
||||
}
|
||||
} catch {
|
||||
void reader.cancel().catch(() => undefined);
|
||||
responses.cancel(() => reader.cancel());
|
||||
return err(fetchFailed(bounds.failure()));
|
||||
}
|
||||
};
|
||||
@@ -256,6 +260,7 @@ const downloadState = async (
|
||||
url: URL,
|
||||
intake: StateIntake,
|
||||
cancel: AbortSignal,
|
||||
responses: StateResponseCleanup,
|
||||
): Promise<Result<Buffer, RpcError>> => {
|
||||
const bounds = downloadBounds(intake.timeoutMs, cancel);
|
||||
const fetching = Promise.resolve().then(() =>
|
||||
@@ -268,7 +273,9 @@ const downloadState = async (
|
||||
// A response that arrives after the download ended is released unread.
|
||||
void fetching
|
||||
.then(
|
||||
(late) => late.body?.cancel(),
|
||||
(late) => {
|
||||
if (late.body !== null) responses.cancel(() => late.body!.cancel());
|
||||
},
|
||||
() => undefined,
|
||||
)
|
||||
.catch(() => undefined);
|
||||
@@ -276,7 +283,8 @@ const downloadState = async (
|
||||
}
|
||||
const declared = Number(response.headers.get("content-length") ?? "0");
|
||||
if (!response.ok || declared > STATE_INTAKE_LIMIT_BYTES) {
|
||||
await response.body?.cancel().catch(() => undefined);
|
||||
// Cancel this branch without waiting for a potentially independent tee sibling.
|
||||
if (response.body !== null) responses.cancel(() => response.body!.cancel());
|
||||
return err(
|
||||
response.ok
|
||||
? TOO_LARGE
|
||||
@@ -286,7 +294,7 @@ const downloadState = async (
|
||||
},
|
||||
);
|
||||
}
|
||||
return readCapped(response.body, bounds);
|
||||
return readCapped(response.body, bounds, responses);
|
||||
};
|
||||
|
||||
const NETWORK_SHARE = invalidParams(
|
||||
@@ -315,6 +323,7 @@ const fileBytes = async (
|
||||
intake: StateIntake,
|
||||
cancel: AbortSignal,
|
||||
files: ArtifactResourceScope,
|
||||
responses: StateResponseCleanup,
|
||||
): Promise<Result<Uint8Array, RpcError>> => {
|
||||
if (typeof file.bytes === "string" && file.uri === undefined) {
|
||||
if (file.bytes.length > MAX_INLINE_BASE64_CHARACTERS) return err(TOO_LARGE);
|
||||
@@ -333,7 +342,8 @@ const fileBytes = async (
|
||||
invalidParams("a file part carries exactly one of bytes or a uri"),
|
||||
);
|
||||
const url = new URL(file.uri);
|
||||
if (url.protocol === "https:") return downloadState(url, intake, cancel);
|
||||
if (url.protocol === "https:")
|
||||
return downloadState(url, intake, cancel, responses);
|
||||
if (url.protocol !== "file:")
|
||||
return err(invalidParams("a file uri is a file:// or https:// URL"));
|
||||
const path = localFilePath(url);
|
||||
@@ -346,6 +356,7 @@ export const partDocument = async (
|
||||
intake: StateIntake,
|
||||
cancel: AbortSignal,
|
||||
files: ArtifactResourceScope,
|
||||
responses: StateResponseCleanup,
|
||||
): Promise<Result<unknown, RpcError>> => {
|
||||
if (isRecord(part) && part.kind === "data" && isRecord(part.data))
|
||||
return ok(part.data);
|
||||
@@ -362,6 +373,6 @@ export const partDocument = async (
|
||||
mediaTypeEssence(mimeType) !== "application/json")
|
||||
)
|
||||
return err(invalidParams("a file part's mimeType is application/json"));
|
||||
const bytes = await fileBytes(part.file, intake, cancel, files);
|
||||
const bytes = await fileBytes(part.file, intake, cancel, files, responses);
|
||||
return bytes.ok ? parseDocumentBytes(bytes.value) : bytes;
|
||||
};
|
||||
@@ -15,6 +15,13 @@ const cases = [
|
||||
0,
|
||||
],
|
||||
['spawn("control", [], {stdio:"inherit"})', "control", "inherit", 0],
|
||||
['spawn("global-nan-env", [], {env:NaN})', "global-nan-env", "default", 0],
|
||||
[
|
||||
'((NaN) => spawn("shadowed-nan-env", [], {env:NaN}))({})',
|
||||
"shadowed-nan-env",
|
||||
"default",
|
||||
0,
|
||||
],
|
||||
[
|
||||
'spawn("spread-after", [], {stdio:"pipe",...input})',
|
||||
"spread-after",
|
||||
@@ -233,6 +240,12 @@ const exportAssignmentSource = `
|
||||
export = argv;
|
||||
`;
|
||||
|
||||
const environmentCommands = [
|
||||
"named-argv",
|
||||
"execfile-dynamic",
|
||||
"shadowed-nan-env",
|
||||
];
|
||||
|
||||
// Callback/options ambiguity cannot change exec's effective stdio.
|
||||
const opaqueExecCallbackCommands = [
|
||||
"eval-callback",
|
||||
@@ -342,7 +355,7 @@ cliTest.for(["CLI", "stdio MCP"] as const)(
|
||||
expect(child.properties.stdio_mode, String(command)).toBe(mode);
|
||||
expect(child.properties.argv_count, String(command)).toBe(count);
|
||||
expect(child.properties.environment_supplied, String(command)).toBe(
|
||||
["named-argv", "execfile-dynamic"].includes(String(command)),
|
||||
environmentCommands.includes(String(command)),
|
||||
);
|
||||
expect(child.identity.source_range).not.toBeNull();
|
||||
const stdio = graph.relations.filter(
|
||||
@@ -377,9 +390,7 @@ cliTest.for(["CLI", "stdio MCP"] as const)(
|
||||
relation.relation === "supplies-env" &&
|
||||
relation.target_node_id === child.node_id,
|
||||
),
|
||||
).toHaveLength(
|
||||
["named-argv", "execfile-dynamic"].includes(String(command)) ? 1 : 0,
|
||||
);
|
||||
).toHaveLength(environmentCommands.includes(String(command)) ? 1 : 0);
|
||||
expect(
|
||||
graph.relations.filter(
|
||||
(relation) =>
|
||||
|
||||
@@ -1,81 +1,72 @@
|
||||
import { execFile } from "node:child_process";
|
||||
import { readFile, readdir, writeFile } from "node:fs/promises";
|
||||
import { readFile, readdir } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { promisify } from "node:util";
|
||||
import { expect, it } from "vitest";
|
||||
import { expect } from "vitest";
|
||||
import { parse } from "yaml";
|
||||
import { resolveSwiftcCompileTimeoutMs } from "../../../src/process/DarwinProcessRunTokenReader.js";
|
||||
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
||||
import { processTest } from "../../support/process/processFixture.js";
|
||||
|
||||
const execute = promisify(execFile);
|
||||
const hostLabels: Partial<Record<NodeJS.Platform, string>> = {
|
||||
linux: "linux",
|
||||
darwin: "macOS",
|
||||
win32: "Windows",
|
||||
};
|
||||
const hostLabel = hostLabels[process.platform];
|
||||
const preparationBudget =
|
||||
process.platform === "darwin" ? resolveSwiftcCompileTimeoutMs() : 0;
|
||||
|
||||
it("enforces workflow platform labels before contacting Cutter", async () => {
|
||||
const workflow = parse(
|
||||
await readFile(".github/workflows/real-cutter.yml", "utf8"),
|
||||
);
|
||||
const labels = workflow.jobs["cutter-upstream"].strategy.matrix.include.map(
|
||||
(entry: { platform: string }) => entry.platform,
|
||||
);
|
||||
expect(labels).toEqual(["linux", "macOS", "Windows"]);
|
||||
const root = await createTestTempDirectory("rea-cutter-platform-");
|
||||
const preload = join(root, "preload.mjs");
|
||||
await writeFile(
|
||||
preload,
|
||||
`
|
||||
import childProcess from 'node:child_process';
|
||||
import { syncBuiltinESMExports } from 'node:module';
|
||||
Object.defineProperty(process, 'platform', { value: process.env.REA_PROBE_PLATFORM });
|
||||
childProcess.execFile = () => { throw new Error('fixture discovery reached'); };
|
||||
syncBuiltinESMExports();
|
||||
`,
|
||||
);
|
||||
const check = async (selected: string | undefined, actual: string) => {
|
||||
const env: NodeJS.ProcessEnv = {
|
||||
...process.env,
|
||||
TMPDIR: root,
|
||||
TMP: root,
|
||||
TEMP: root,
|
||||
REA_PROBE_PLATFORM: actual,
|
||||
processTest.skipIf(hostLabel === undefined)(
|
||||
"enforces workflow platform labels before contacting Cutter",
|
||||
{ timeout: Math.min(2_147_483_647, 2 * preparationBudget + 30_000) },
|
||||
async ({ processes }) => {
|
||||
const workflow = parse(
|
||||
await readFile(".github/workflows/real-cutter.yml", "utf8"),
|
||||
);
|
||||
const labels = workflow.jobs["cutter-upstream"].strategy.matrix.include.map(
|
||||
(entry: { platform: string }) => entry.platform,
|
||||
);
|
||||
expect(labels).toEqual(["linux", "macOS", "Windows"]);
|
||||
const root = await createTestTempDirectory("rea-cutter-platform-");
|
||||
// A private absent directory proves actual discovery without contacting a user's bridge.
|
||||
const bridgeDirectory = join(root, "absent-bridge");
|
||||
const check = async (selected: string | undefined) => {
|
||||
const env: NodeJS.ProcessEnv = {
|
||||
...process.env,
|
||||
TMPDIR: root,
|
||||
TMP: root,
|
||||
TEMP: root,
|
||||
REA_CUTTER_BRIDGE_DIR: bridgeDirectory,
|
||||
};
|
||||
if (selected === undefined) delete env.EXPECTED_PLATFORM;
|
||||
else env.EXPECTED_PLATFORM = selected;
|
||||
const result = await processes.run(
|
||||
process.execPath,
|
||||
["scripts/verify-real-cutter.mjs"],
|
||||
{
|
||||
env,
|
||||
timeoutMs: Math.min(2_147_483_647, preparationBudget + 15_000),
|
||||
},
|
||||
);
|
||||
expect(result.exitCode, result.stderr).toBe(1);
|
||||
return result.stderr;
|
||||
};
|
||||
if (selected === undefined) delete env.EXPECTED_PLATFORM;
|
||||
else env.EXPECTED_PLATFORM = selected;
|
||||
const result: unknown = await execute(
|
||||
process.execPath,
|
||||
["--import", preload, "scripts/verify-real-cutter.mjs"],
|
||||
{ env, timeout: 10_000 },
|
||||
).then(
|
||||
() => {
|
||||
throw new Error("Fixture discovery should stop the verifier");
|
||||
},
|
||||
(error: unknown) => error,
|
||||
for (const selected of [hostLabel, undefined]) {
|
||||
const stderr = await check(selected);
|
||||
expect(stderr).toContain("Open upstream Cutter with the REA plugin");
|
||||
expect(stderr).toContain("no_live_bridge_found");
|
||||
}
|
||||
const other = labels.find((label: string) => label !== hostLabel);
|
||||
expect(other).toBeDefined();
|
||||
expect(await check(other)).toContain(
|
||||
"Cutter runner did not match its declared platform",
|
||||
);
|
||||
if (
|
||||
!(result instanceof Error) ||
|
||||
!("stderr" in result) ||
|
||||
typeof result.stderr !== "string"
|
||||
)
|
||||
throw new Error("Missing verifier diagnostics");
|
||||
return result.stderr;
|
||||
};
|
||||
for (const [selected, actual] of [
|
||||
["linux", "linux"],
|
||||
["macOS", "darwin"],
|
||||
["Windows", "win32"],
|
||||
] as const)
|
||||
expect(await check(selected, actual)).toContain(
|
||||
"fixture discovery reached",
|
||||
expect(await check("unknown")).toContain(
|
||||
"Unrecognized Cutter runner platform",
|
||||
);
|
||||
expect(await check("linux", "darwin")).toContain(
|
||||
"Cutter runner did not match its declared platform",
|
||||
);
|
||||
expect(await check("unknown", "linux")).toContain(
|
||||
"Unrecognized Cutter runner platform",
|
||||
);
|
||||
expect(await check(undefined, "linux")).toContain(
|
||||
"fixture discovery reached",
|
||||
);
|
||||
expect(
|
||||
(await readdir(root)).filter((name) =>
|
||||
name.startsWith("rea-cutter-smoke-"),
|
||||
),
|
||||
).toEqual([]);
|
||||
});
|
||||
expect(
|
||||
(await readdir(root)).filter((name) =>
|
||||
name.startsWith("rea-cutter-smoke-"),
|
||||
),
|
||||
).toEqual([]);
|
||||
},
|
||||
);
|
||||
@@ -783,7 +783,7 @@ it.each([
|
||||
{ code: false, ghidra_bridge: true, runtime: false, package: false },
|
||||
],
|
||||
[
|
||||
"tests/conformance/ghidra/ReaArmContextProbe.java",
|
||||
"tests/conformance/ghidra/ReaInstructionContextProbe.java",
|
||||
{ ghidra_bridge: true, runtime: false, package: false },
|
||||
],
|
||||
[
|
||||
|
||||
@@ -1656,6 +1656,7 @@ it("advertises Mach-O pages whose selected facet owns their exact rows", async (
|
||||
size: 4096,
|
||||
status: "absent",
|
||||
reason: null,
|
||||
malformed_kind: null,
|
||||
commands: [],
|
||||
range: null,
|
||||
},
|
||||
@@ -1663,10 +1664,21 @@ it("advertises Mach-O pages whose selected facet owns their exact rows", async (
|
||||
provenance: [],
|
||||
limitations: [],
|
||||
});
|
||||
const { malformed_kind: _unrecorded, ...recordedEncryption } =
|
||||
report.encryption.items[0]!;
|
||||
const historicalEncryption = {
|
||||
...recordedEncryption,
|
||||
status: "malformed" as const,
|
||||
reason: "slice has 3 encryption load commands",
|
||||
};
|
||||
const parent = createEvidence(
|
||||
{ path: "/fixtures/tool", format: "mach-o", sha256: "a".repeat(64) },
|
||||
{ id: "native", name: "Native fixture", version: "1" },
|
||||
{ operation: "inspect_macho", parameters: {}, result: report },
|
||||
{
|
||||
operation: "inspect_macho",
|
||||
parameters: {},
|
||||
result: { ...report, encryption: coverage([historicalEncryption]) },
|
||||
},
|
||||
);
|
||||
const original = structuredClone(parent);
|
||||
expect(session.recordEvidence(parent).ok).toBe(true);
|
||||
@@ -1696,7 +1708,11 @@ it("advertises Mach-O pages whose selected facet owns their exact rows", async (
|
||||
const delivered = parseEvidence(response.structuredContent);
|
||||
const page = analysisViewResultSchema.parse(delivered.normalized_result);
|
||||
if (page.kind !== "macho") throw new Error("Expected Mach-O page");
|
||||
expect(page.item).toEqual(report[facet].items.slice(offset, offset + 64));
|
||||
const rows =
|
||||
facet === "encryption"
|
||||
? [{ ...historicalEncryption, malformed_kind: "unrecorded" }]
|
||||
: report[facet].items;
|
||||
expect(page.item).toEqual(rows.slice(offset, offset + 64));
|
||||
if (page.item.length > 0) {
|
||||
const mismatched = {
|
||||
...delivered,
|
||||
|
||||
@@ -0,0 +1,84 @@
|
||||
import { writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { expect } from "vitest";
|
||||
|
||||
import { createBinarySession } from "../../../src/composition/binary.js";
|
||||
import { parseConfig } from "../../../src/config/parseConfig.js";
|
||||
import { artifactInspectionResultSchema } from "../../../src/domain/artifactInspection.js";
|
||||
import { parseEvidence } from "../../../src/domain/evidence.js";
|
||||
import { silentLogger } from "../../../src/logger.js";
|
||||
import { createServer } from "../../../src/server/createServer.js";
|
||||
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
||||
import { mcpTest } from "../../support/mcp/mcpFixture.js";
|
||||
import { serveCli } from "../cli/cliServeHarness.js";
|
||||
|
||||
const expectMftInventory = (value: unknown): void => {
|
||||
const evidence = parseEvidence(value);
|
||||
const inspection = artifactInspectionResultSchema.parse(
|
||||
evidence.normalized_result,
|
||||
);
|
||||
const inventory = inspection.substeps[0]?.evidence.normalized_result;
|
||||
expect(inventory?.manifest.root_format).toBe("ntfs-mft");
|
||||
expect(inventory?.occurrences[0]?.format_metadata).toMatchObject({
|
||||
kind: "ntfs-mft",
|
||||
record_count: 1,
|
||||
fixup_unverified_record_count: 0,
|
||||
record_headers: [
|
||||
{
|
||||
index: 0,
|
||||
fileOffset: 0,
|
||||
sequenceNumber: 1,
|
||||
declaredRecordNumber: null,
|
||||
fixups: { verifiedSectors: 2 },
|
||||
},
|
||||
],
|
||||
omitted_record_headers: 0,
|
||||
});
|
||||
};
|
||||
|
||||
mcpTest(
|
||||
"admits an MFT capture by signature through CLI and MCP",
|
||||
async ({ mcp, onTestFinished }) => {
|
||||
const root = await createTestTempDirectory("rea-ntfs-mft-admission-");
|
||||
const path = join(root, "capture.bin");
|
||||
const record = Buffer.alloc(1024);
|
||||
record.write("FILE");
|
||||
record.writeUInt16LE(42, 4);
|
||||
record.writeUInt16LE(3, 6);
|
||||
record.writeUInt16LE(1, 16);
|
||||
record.writeUInt16LE(56, 20);
|
||||
record.writeUInt32LE(64, 24);
|
||||
record.writeUInt32LE(0xffff_ffff, 56);
|
||||
record.writeUInt32LE(1024, 28);
|
||||
record.writeUInt16LE(5, 42);
|
||||
record.writeUInt16LE(5, 510);
|
||||
record.writeUInt16LE(5, 1022);
|
||||
await writeFile(path, record);
|
||||
|
||||
const cli = await serveCli(["inspect-artifact", path, "--json"]);
|
||||
expect(cli.exitCode, cli.stdout).toBe(0);
|
||||
expectMftInventory(JSON.parse(cli.stdout));
|
||||
|
||||
const configured = parseConfig({ REA_ANALYSIS_PROVIDER: "auto" });
|
||||
if (!configured.ok) throw configured.error;
|
||||
const session = createBinarySession(configured.value, silentLogger, {});
|
||||
onTestFinished(async () => {
|
||||
await session.close();
|
||||
});
|
||||
const client = await mcp.connect(
|
||||
createServer({ kind: "session", session }),
|
||||
);
|
||||
const opened = await client.callTool({
|
||||
name: "open_binary",
|
||||
arguments: { path },
|
||||
});
|
||||
expect(opened.isError, JSON.stringify(opened.content)).not.toBe(true);
|
||||
const inspected = await client.callTool({
|
||||
name: "inspect_artifact",
|
||||
arguments: {},
|
||||
});
|
||||
expect(inspected.isError, JSON.stringify(inspected.content)).not.toBe(true);
|
||||
expectMftInventory(inspected.structuredContent);
|
||||
},
|
||||
);
|
||||
@@ -1,4 +1,4 @@
|
||||
import { readFile, writeFile } from "node:fs/promises";
|
||||
import { readFile, stat, writeFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import { expect } from "vitest";
|
||||
@@ -175,7 +175,11 @@ registerHooks({ load(url, context, nextLoad) {
|
||||
),
|
||||
],
|
||||
{
|
||||
env: { ...process.env, REA_AGENT_EVAL_ROOT: parent },
|
||||
env: {
|
||||
...process.env,
|
||||
REA_AGENT_EVAL_ROOT: parent,
|
||||
REA_AGENT_EVAL_KEEP_FIXTURES: "false",
|
||||
},
|
||||
timeoutMs: 10_000,
|
||||
},
|
||||
);
|
||||
@@ -190,14 +194,13 @@ registerHooks({ load(url, context, nextLoad) {
|
||||
if (incomplete) {
|
||||
expect(result.stderr).toContain("Artifact cleanup remains incomplete");
|
||||
expect(result.stderr).toContain("fixture cleanup denied");
|
||||
expect(await readFile(join(run, "codex/auth.json"), "utf8")).toBe(
|
||||
"inert fixture",
|
||||
);
|
||||
expect((await stat(run)).isDirectory()).toBe(true);
|
||||
} else {
|
||||
await expect(
|
||||
readFile(join(run, "codex/auth.json")),
|
||||
).rejects.toMatchObject({ code: "ENOENT" });
|
||||
await expect(stat(run)).rejects.toMatchObject({ code: "ENOENT" });
|
||||
}
|
||||
await expect(readFile(join(run, "codex/auth.json"))).rejects.toMatchObject({
|
||||
code: "ENOENT",
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
@@ -274,7 +277,11 @@ registerHooks({ load(url, context, nextLoad) {
|
||||
),
|
||||
],
|
||||
{
|
||||
env: { ...process.env, REA_AGENT_EVAL_ROOT: parent },
|
||||
env: {
|
||||
...process.env,
|
||||
REA_AGENT_EVAL_ROOT: parent,
|
||||
REA_AGENT_EVAL_KEEP_FIXTURES: "false",
|
||||
},
|
||||
timeoutMs: 10_000,
|
||||
},
|
||||
);
|
||||
@@ -298,13 +305,14 @@ registerHooks({ load(url, context, nextLoad) {
|
||||
if (incomplete) {
|
||||
expect(result.stderr).toContain("Artifact cleanup remains incomplete");
|
||||
expect(result.stderr).toContain("darwin-fixture-reader");
|
||||
expect(
|
||||
await readFile(join(observed.run, "codex/auth.json"), "utf8"),
|
||||
).toBe("inert preparation fixture");
|
||||
expect((await stat(observed.run)).isDirectory()).toBe(true);
|
||||
} else {
|
||||
await expect(
|
||||
readFile(join(observed.run, "codex/auth.json")),
|
||||
).rejects.toMatchObject({ code: "ENOENT" });
|
||||
await expect(stat(observed.run)).rejects.toMatchObject({
|
||||
code: "ENOENT",
|
||||
});
|
||||
}
|
||||
await expect(
|
||||
readFile(join(observed.run, "codex/auth.json")),
|
||||
).rejects.toMatchObject({ code: "ENOENT" });
|
||||
},
|
||||
);
|
||||
@@ -1,24 +1,57 @@
|
||||
import { execFile } from "node:child_process";
|
||||
import {
|
||||
copyFile,
|
||||
cp,
|
||||
mkdir,
|
||||
readFile,
|
||||
symlink,
|
||||
writeFile,
|
||||
} from "node:fs/promises";
|
||||
import { dirname, join, resolve } from "node:path";
|
||||
import { promisify } from "node:util";
|
||||
import { expect, it } from "vitest";
|
||||
import { join, resolve } from "node:path";
|
||||
import { expect } from "vitest";
|
||||
import { z } from "zod";
|
||||
import { createApplicationMcpHarness } from "../../fixtures/applicationMcpHarness.js";
|
||||
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
||||
import { processTest } from "../../support/process/processFixture.js";
|
||||
import { resolveSwiftcCompileTimeoutMs } from "../../../src/process/DarwinProcessRunTokenReader.js";
|
||||
|
||||
const execute = promisify(execFile);
|
||||
const preparationBudget =
|
||||
process.platform === "darwin" ? resolveSwiftcCompileTimeoutMs() : 0;
|
||||
|
||||
async function prepareController(controller: string, version: string) {
|
||||
// The verifier loads its production-owned TypeScript source graph at runtime.
|
||||
// Keep that graph in the isolated controller so imports cannot drift from a hand-maintained list.
|
||||
await mkdir(join(controller, "scripts"), { recursive: true });
|
||||
await copyFile(
|
||||
"scripts/verify-release-artifact.mjs",
|
||||
join(controller, "scripts/verify-release-artifact.mjs"),
|
||||
);
|
||||
await cp("scripts/lib", join(controller, "scripts/lib"), {
|
||||
recursive: true,
|
||||
});
|
||||
await mkdir(join(controller, "bridge"), { recursive: true });
|
||||
await cp("bridge/process", join(controller, "bridge/process"), {
|
||||
recursive: true,
|
||||
});
|
||||
await cp("src", join(controller, "src"), {
|
||||
recursive: true,
|
||||
filter: (source) => !/\.(?:test|spec)\.[cm]?[jt]sx?$/u.test(source),
|
||||
});
|
||||
await writeFile(
|
||||
join(controller, "package.json"),
|
||||
JSON.stringify({ name: "rea-agents", version, type: "module" }),
|
||||
);
|
||||
await symlink(
|
||||
resolve("node_modules"),
|
||||
join(controller, "node_modules"),
|
||||
process.platform === "win32" ? "junction" : "dir",
|
||||
);
|
||||
}
|
||||
|
||||
// Release rehearsal runs on Linux; the npm process adapter is also exercised on macOS.
|
||||
it.skipIf(process.platform === "win32")(
|
||||
processTest.skipIf(process.platform === "win32")(
|
||||
"fails without declared runtime, then rehearses an installed tarball and rejects catalog drift",
|
||||
async () => {
|
||||
{ timeout: Math.min(2_147_483_647, 3 * preparationBudget + 210_000) },
|
||||
async ({ processes }) => {
|
||||
const root = await createTestTempDirectory("rea-release-canary-");
|
||||
const candidate = join(root, "candidate");
|
||||
const controller = join(root, "controller");
|
||||
@@ -76,56 +109,46 @@ if (process.argv[2] === "mcp") {
|
||||
} else { process.exitCode = 1; }
|
||||
`,
|
||||
);
|
||||
const packed = await execute(
|
||||
"npm",
|
||||
["pack", "--ignore-scripts", "--json"],
|
||||
{
|
||||
cwd: candidate,
|
||||
},
|
||||
);
|
||||
const pack = async () => {
|
||||
const result = await processes.run(
|
||||
"npm",
|
||||
["pack", "--ignore-scripts", "--json"],
|
||||
{ cwd: candidate, timeoutMs: 30_000 },
|
||||
);
|
||||
expect(result.exitCode, result.stderr).toBe(0);
|
||||
return result;
|
||||
};
|
||||
const packed = await pack();
|
||||
const [{ filename }] = z
|
||||
.tuple([z.object({ filename: z.string() })])
|
||||
.parse(JSON.parse(packed.stdout));
|
||||
const tarball = join(candidate, filename);
|
||||
for (const file of [
|
||||
"scripts/verify-release-artifact.mjs",
|
||||
"scripts/lib/release-package-canary.mjs",
|
||||
"scripts/lib/verify-package-core.mjs",
|
||||
"scripts/lib/mcp-verifier-results.mjs",
|
||||
"scripts/lib/verifier-run.mjs",
|
||||
]) {
|
||||
const target = join(controller, file);
|
||||
await mkdir(dirname(target), { recursive: true });
|
||||
await copyFile(file, target);
|
||||
}
|
||||
await writeFile(
|
||||
join(controller, "package.json"),
|
||||
JSON.stringify({ name: "rea-agents", version, type: "module" }),
|
||||
);
|
||||
await symlink(
|
||||
resolve("node_modules"),
|
||||
join(controller, "node_modules"),
|
||||
process.platform === "win32" ? "junction" : "dir",
|
||||
);
|
||||
await prepareController(controller, version);
|
||||
const invoke = (selected = tarball) =>
|
||||
execute(
|
||||
processes.run(
|
||||
process.execPath,
|
||||
[
|
||||
join(controller, "scripts/verify-release-artifact.mjs"),
|
||||
selected,
|
||||
version,
|
||||
],
|
||||
{ cwd: controller, maxBuffer: 16 * 1024 * 1024 },
|
||||
{
|
||||
cwd: controller,
|
||||
timeoutMs: Math.min(2_147_483_647, preparationBudget + 30_000),
|
||||
},
|
||||
);
|
||||
await expect(invoke()).rejects.toMatchObject({
|
||||
stderr: expect.stringContaining("ERR_MODULE_NOT_FOUND"),
|
||||
});
|
||||
const missing = await invoke();
|
||||
expect(missing.exitCode).toBe(1);
|
||||
expect(missing.stderr).toContain("ERR_MODULE_NOT_FOUND");
|
||||
expect(missing.stderr).toMatch(/dist[/\\]catalogIdentity\.js/u);
|
||||
await symlink(
|
||||
resolve("dist"),
|
||||
join(controller, "dist"),
|
||||
process.platform === "win32" ? "junction" : "dir",
|
||||
);
|
||||
const result = JSON.parse((await invoke()).stdout);
|
||||
const successful = await invoke();
|
||||
expect(successful.exitCode, successful.stderr).toBe(0);
|
||||
const result = JSON.parse(successful.stdout);
|
||||
expect(result).toMatchObject({
|
||||
package: "rea-agents",
|
||||
version,
|
||||
@@ -144,12 +167,10 @@ if (process.argv[2] === "mcp") {
|
||||
join(candidate, "scripts/reply.json"),
|
||||
JSON.stringify(snapshot),
|
||||
);
|
||||
await execute("npm", ["pack", "--ignore-scripts", "--json"], {
|
||||
cwd: candidate,
|
||||
});
|
||||
await expect(invoke()).rejects.toMatchObject({
|
||||
stderr: expect.stringContaining("invalid canonical tool catalog"),
|
||||
});
|
||||
await pack();
|
||||
const drifted = await invoke();
|
||||
expect(drifted.exitCode).toBe(1);
|
||||
expect(drifted.stderr).toContain("invalid canonical tool catalog");
|
||||
await writeFile(
|
||||
join(candidate, "package.json"),
|
||||
JSON.stringify({
|
||||
@@ -159,15 +180,12 @@ if (process.argv[2] === "mcp") {
|
||||
files: ["scripts"],
|
||||
}),
|
||||
);
|
||||
const wrong = await execute("npm", ["pack", "--ignore-scripts", "--json"], {
|
||||
cwd: candidate,
|
||||
});
|
||||
const wrong = await pack();
|
||||
const [{ filename: wrongFilename }] = z
|
||||
.tuple([z.object({ filename: z.string() })])
|
||||
.parse(JSON.parse(wrong.stdout));
|
||||
await expect(invoke(join(candidate, wrongFilename))).rejects.toMatchObject({
|
||||
stderr: expect.stringContaining("Installed package identity"),
|
||||
});
|
||||
const mismatched = await invoke(join(candidate, wrongFilename));
|
||||
expect(mismatched.exitCode).toBe(1);
|
||||
expect(mismatched.stderr).toContain("Installed package identity");
|
||||
},
|
||||
30_000,
|
||||
);
|
||||
@@ -30,6 +30,7 @@ import {
|
||||
machoImage,
|
||||
} from "../../../../src/artifacts/apple/MachoImage.fixture.js";
|
||||
import { inspectionImage } from "../../../../src/native/NativeMachoInspection.fixture.js";
|
||||
import { fat } from "../../../../src/domain/binaryTarget.fixture.js";
|
||||
import {
|
||||
inspectPlistSchema,
|
||||
inspectSignatureSchema,
|
||||
@@ -94,6 +95,13 @@ const inspectionFixture = async (high = false) => {
|
||||
return nativeMachoTargetForFile(path);
|
||||
};
|
||||
|
||||
const architectureTargetFixture = async () => {
|
||||
const root = await createTestTempDirectory("rea-native-architectures-");
|
||||
const path = join(root, "fixture");
|
||||
await writeFile(path, fat([0x01000007, 0x0100000c]));
|
||||
return nativeMachoTargetForFile(path);
|
||||
};
|
||||
|
||||
const cleanupOwner = (runId: string): ProviderProcessSupervisor => {
|
||||
const child = Object.assign(new EventEmitter(), {
|
||||
stdout: new PassThrough(),
|
||||
@@ -538,7 +546,7 @@ describe("native owned cancellation boundary", () => {
|
||||
launcher,
|
||||
);
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
const controller = new AbortController();
|
||||
const cancellationReason = {
|
||||
@@ -653,7 +661,7 @@ describe("native cancellation cleanup provenance", () => {
|
||||
launcher,
|
||||
);
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
const controllers = [new AbortController(), new AbortController()];
|
||||
const cancellationReason = { source: "mixed native owner retry" };
|
||||
@@ -790,7 +798,7 @@ describe("native returned cleanup ownership", () => {
|
||||
launcher,
|
||||
);
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
const controller = new AbortController();
|
||||
const cancellationReason = { source: "native cleanup retry regression" };
|
||||
@@ -934,7 +942,7 @@ describe("native late cancellation with cleanup", () => {
|
||||
launcher,
|
||||
);
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
try {
|
||||
const pending = client.execute(
|
||||
@@ -1130,7 +1138,7 @@ describe("native command cleanup lifecycle", () => {
|
||||
},
|
||||
};
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
|
||||
const execution = client.execute("list_architectures", {});
|
||||
@@ -1216,7 +1224,7 @@ describe("native command failure projection", () => {
|
||||
retryCleanup: async () => failures,
|
||||
};
|
||||
const client = new NativeMacOSProvider({}, runner, "darwin").createClient(
|
||||
machoTarget("/private/fixture"),
|
||||
await architectureTargetFixture(),
|
||||
);
|
||||
try {
|
||||
const result = await client.execute("list_architectures", {});
|
||||
@@ -1268,7 +1276,7 @@ describe("native command failure projection", () => {
|
||||
},
|
||||
};
|
||||
const result = await new NativeMacOSProvider({}, runner, "darwin")
|
||||
.createClient(machoTarget("/private/fixture"))
|
||||
.createClient(await architectureTargetFixture())
|
||||
.execute("list_architectures", {});
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
@@ -1309,7 +1317,7 @@ describe("native command failure projection", () => {
|
||||
},
|
||||
};
|
||||
const result = await new NativeMacOSProvider({}, runner, "darwin")
|
||||
.createClient(machoTarget("/private/fixture"))
|
||||
.createClient(await architectureTargetFixture())
|
||||
.execute("list_architectures", {});
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
@@ -1429,7 +1437,7 @@ describe("native macOS provider inspection", () => {
|
||||
const app = join(directory, "Fixture.app");
|
||||
const executable = join(app, "Contents/MacOS/Fixture");
|
||||
await mkdir(join(app, "Contents/MacOS"), { recursive: true });
|
||||
await writeFile(executable, "fixture");
|
||||
await writeFile(executable, fat([0x01000007, 0x0100000c]));
|
||||
await writeFixturePlist(join(app, "Contents/Info.plist"));
|
||||
const externalPlist = join(directory, "Outside.plist");
|
||||
await writeFixturePlist(externalPlist);
|
||||
@@ -1697,7 +1705,7 @@ describe("native macOS provider failures and parsing", () => {
|
||||
{},
|
||||
new FailingRunner("unavailable"),
|
||||
"darwin",
|
||||
).createClient(machoTarget("/fixture"));
|
||||
).createClient(await architectureTargetFixture());
|
||||
const unavailableResult = await unavailable.execute(
|
||||
"list_architectures",
|
||||
{},
|
||||
@@ -1714,7 +1722,7 @@ describe("native macOS provider failures and parsing", () => {
|
||||
{},
|
||||
new FixtureRunner({ lipo: "malformed" }),
|
||||
"darwin",
|
||||
).createClient(machoTarget("/fixture"));
|
||||
).createClient(await architectureTargetFixture());
|
||||
const malformedResult = await malformed.execute("list_architectures", {});
|
||||
expect(!malformedResult.ok && malformedResult.error._tag).toBe(
|
||||
"AnalysisOutputError",
|
||||
@@ -1728,7 +1736,7 @@ describe("native macOS provider failures and parsing", () => {
|
||||
{},
|
||||
new FailingRunner(reason),
|
||||
"darwin",
|
||||
).createClient(machoTarget("/fixture"));
|
||||
).createClient(await architectureTargetFixture());
|
||||
const result = await client.execute("list_architectures", {});
|
||||
expect(!result.ok && result.error._tag).toBe(tag);
|
||||
}
|
||||
|
||||
@@ -21,6 +21,12 @@ no-overwrite CLI delivery. It checks the target and project files for changes.
|
||||
Clang/LLD/LLVM readelf/LLVM objdump; `REA_RISCV_CLANG`, `REA_RISCV_LLD`,
|
||||
`REA_RISCV_READELF` and `REA_RISCV_OBJDUMP` select existing tool commands.
|
||||
|
||||
- `ReaInstructionContextProbe.java` inspects source-owned ARM, Thumb, MIPS32
|
||||
and MIPS16 instructions through the production bridge in an ephemeral,
|
||||
read-only Ghidra project. It checks exact decoder-context register names,
|
||||
values and provenance; the ARM lane also injects an unavailable provider
|
||||
value. The `ghidra-bridge-sources` CI job runs both processor families. The
|
||||
input bytes are never executed.
|
||||
- `ReaDecodeProbe.java` decodes source-owned instruction bytes from a
|
||||
language's default context and checks each mnemonic, length and optional
|
||||
complete operand. The `ghidra-bridge-sources` CI job runs it for `ARM:LE:32:Cortex`,
|
||||
|
||||
+36
-9
@@ -15,16 +15,20 @@ import java.lang.reflect.Proxy;
|
||||
import java.math.BigInteger;
|
||||
|
||||
/** Real ARM/Thumb decoding; only the unavailable context value is injected. */
|
||||
public class ReaArmContextProbe extends GhidraScript {
|
||||
public class ReaInstructionContextProbe extends GhidraScript {
|
||||
@Override
|
||||
public void run() throws Exception {
|
||||
String[] args = getScriptArgs();
|
||||
require(args.length == 1, "Expected the exact production bridge directory");
|
||||
require(args.length == 1 || (args.length == 2 && args[1].equals("mips")), "Expected the bridge directory and optional MIPS mode");
|
||||
var source = GhidraScriptUtil.findScriptByName("ReaGhidraBridge.java");
|
||||
require(source != null && new File(source.getAbsolutePath()).getCanonicalFile().equals(
|
||||
new File(args[0], "ReaGhidraBridge.java").getCanonicalFile()), "Production bridge source");
|
||||
GhidraScript bridge = GhidraScriptUtil.getProvider(source).getScriptInstance(source, errorWriter);
|
||||
bridge.set(getState(), getControls());
|
||||
if (args.length == 2) {
|
||||
checkMips(bridge);
|
||||
return;
|
||||
}
|
||||
require(currentProgram.getLanguageID().getIdAsString().equals("ARM:LE:32:v7"), "ARM fixture language");
|
||||
var mode = currentProgram.getRegister("TMode");
|
||||
require(mode != null, "Real TMode register");
|
||||
@@ -40,8 +44,8 @@ public class ReaArmContextProbe extends GhidraScript {
|
||||
space.set(null, arm.getAddressSpace());
|
||||
Method inspect = bridge.getClass().getDeclaredMethod("inspectNativeInstruction", JsonObject.class, boolean.class);
|
||||
inspect.setAccessible(true);
|
||||
check(inspect, bridge, arm, "0", 4, "1eff2fe1");
|
||||
check(inspect, bridge, thumb, "1", 2, "7047");
|
||||
check(inspect, bridge, arm, "0", 4, "1eff2fe1", "TMode");
|
||||
check(inspect, bridge, thumb, "1", 2, "7047", "TMode");
|
||||
|
||||
// getValue includes language defaults. Inject only its unavailable result,
|
||||
// preserving the real instruction, register, language and all other APIs.
|
||||
@@ -57,26 +61,49 @@ public class ReaArmContextProbe extends GhidraScript {
|
||||
programField.setAccessible(true);
|
||||
try {
|
||||
programField.set(bridge, program);
|
||||
check(inspect, bridge, arm, null, 4, "1eff2fe1");
|
||||
check(inspect, bridge, arm, null, 4, "1eff2fe1", "TMode");
|
||||
} finally {
|
||||
programField.set(bridge, original);
|
||||
}
|
||||
println("REA_ARM_CONTEXT_OK arm=0 thumb=1 unavailable=null (injected provider value)");
|
||||
}
|
||||
|
||||
private void checkMips(GhidraScript bridge) throws Exception {
|
||||
require(currentProgram.getLanguageID().getIdAsString().equals("MIPS:LE:32:default"), "MIPS fixture language");
|
||||
var mode = currentProgram.getRegister("ISA_MODE");
|
||||
require(mode != null, "Real ISA_MODE register");
|
||||
Address standard = currentProgram.getMemory().getMinAddress();
|
||||
Address compressed = standard.add(4);
|
||||
var context = currentProgram.getProgramContext();
|
||||
context.setValue(mode, standard, standard.add(3), BigInteger.ZERO);
|
||||
require(disassemble(standard), "MIPS32 instruction decoded");
|
||||
// MIPS32 flow may have decoded following bytes in the default mode.
|
||||
clearListing(compressed, compressed.add(3));
|
||||
context.setValue(mode, compressed, compressed.add(1), BigInteger.ONE);
|
||||
require(disassemble(compressed), "MIPS16 instruction decoded");
|
||||
Field space = bridge.getClass().getDeclaredField("sessionDefaultAddressSpace");
|
||||
space.setAccessible(true);
|
||||
space.set(null, standard.getAddressSpace());
|
||||
Method inspect = bridge.getClass().getDeclaredMethod("inspectNativeInstruction", JsonObject.class, boolean.class);
|
||||
inspect.setAccessible(true);
|
||||
check(inspect, bridge, standard, "0", 4, "03008224", "ISA_MODE");
|
||||
check(inspect, bridge, compressed, "1", 2, "5a6a", "ISA_MODE");
|
||||
println("REA_MIPS_CONTEXT_OK standard=0 mips16=1");
|
||||
}
|
||||
|
||||
private static void check(Method inspect, Object bridge, Address address, String mode,
|
||||
int length, String bytes) throws Exception {
|
||||
int length, String bytes, String register) throws Exception {
|
||||
JsonObject input = new JsonObject();
|
||||
input.add("document", JsonNull.INSTANCE);
|
||||
input.addProperty("address", "0x" + Long.toUnsignedString(address.getOffset(), 16));
|
||||
JsonObject result = (JsonObject) inspect.invoke(bridge, input, false);
|
||||
require(result.get("status").getAsString().equals("decoded"), "Decoded bridge response");
|
||||
require(result.get("length").getAsInt() == length, "ARM/Thumb instruction width");
|
||||
require(result.get("status").getAsString().equals("decoded"), "Decoded bridge response: " + result);
|
||||
require(result.get("length").getAsInt() == length, "Instruction width");
|
||||
require(result.get("bytes").getAsString().equals(bytes), "Original instruction bytes");
|
||||
var contexts = result.getAsJsonArray("decoder_context");
|
||||
require(contexts != null && contexts.size() == 1, "One retained mode context");
|
||||
var value = contexts.get(0).getAsJsonObject();
|
||||
require(value.get("register").getAsString().equals("TMode"), "TMode register name");
|
||||
require(value.get("register").getAsString().equals(register), "Exact context register name");
|
||||
require(value.get("source").getAsString().equals("ghidra-program-context"), "Context provenance");
|
||||
require(mode == null ? value.get("value").isJsonNull()
|
||||
: mode.equals(value.get("value").getAsString()), "Exact mode value " + mode);
|
||||
+71
@@ -252,3 +252,74 @@ export const artifactReaderLifecycleCases = (setup: LifecycleFixture): void => {
|
||||
validationCases(setup);
|
||||
});
|
||||
};
|
||||
|
||||
/** An interrupted preparation belongs to its caller, not concurrent readers. */
|
||||
export const artifactPreparationRecoveryCases = ({
|
||||
image,
|
||||
createReader,
|
||||
}: LifecycleFixture): void => {
|
||||
it.each(["cancelled", "physical failure"] as const)(
|
||||
"preserves independent preparation after %s",
|
||||
async (scenario) => {
|
||||
const path = await fixture(image());
|
||||
const admitted = await openRegularFile(path, { symlinks: "reject" });
|
||||
const reader = createReader(path, admitted);
|
||||
const controller = new AbortController();
|
||||
const reason = { request: "first inventory" };
|
||||
const physical = Object.assign(new Error("controlled read failure"), {
|
||||
code: "EIO",
|
||||
});
|
||||
const reached = createDeferred<void>();
|
||||
const release = createDeferred<void>();
|
||||
const nativeRead = admitted.handle.read.bind(admitted.handle);
|
||||
let blocked = false;
|
||||
const read = vi.spyOn(admitted.handle, "read").mockImplementation((async (
|
||||
...args: unknown[]
|
||||
) => {
|
||||
const result = await Reflect.apply(nativeRead, admitted.handle, args);
|
||||
if (!blocked) {
|
||||
blocked = true;
|
||||
reached.resolve();
|
||||
await release.promise;
|
||||
if (scenario === "physical failure") throw physical;
|
||||
}
|
||||
return result;
|
||||
}) as typeof admitted.handle.read);
|
||||
const pending: Promise<unknown>[] = [];
|
||||
try {
|
||||
const first = (async () => {
|
||||
for await (const _ of reader.entries(controller.signal)) {
|
||||
}
|
||||
})();
|
||||
pending.push(first);
|
||||
void first.catch(() => undefined);
|
||||
await awaitAcknowledgement(reached.promise, first, "preparation read");
|
||||
const peer = entries(reader);
|
||||
pending.push(peer);
|
||||
void peer.catch(() => undefined);
|
||||
controller.abort(reason);
|
||||
release.resolve();
|
||||
if (scenario === "physical failure") {
|
||||
await expect(first).rejects.toBe(physical);
|
||||
await expect(peer).rejects.toBe(physical);
|
||||
} else {
|
||||
await expect(first).rejects.toMatchObject({
|
||||
reason: "cancelled",
|
||||
cause: reason,
|
||||
});
|
||||
const recovered = await peer;
|
||||
expect(recovered.length).toBeGreaterThan(0);
|
||||
expect(
|
||||
(await buffer(await reader.open(recovered[0]!))).length,
|
||||
).toBeGreaterThan(0);
|
||||
}
|
||||
} finally {
|
||||
release.resolve();
|
||||
await Promise.allSettled(pending);
|
||||
read.mockRestore();
|
||||
await reader.close();
|
||||
await admitted.handle.close();
|
||||
}
|
||||
},
|
||||
);
|
||||
};
|
||||
Reference in new issue
Block a user