GitNexus/gitnexus/test/unit/incremental-parse-cache.test.ts
mengkaka 79543c8f83
feat(storage): add configurable index storage and content retention tiers (#3060)
* feat(storage): add configurable index storage and content retention tiers

Rebase #3060 onto current origin/main. Keep GITNEXUS_STORAGE_PATH,
GITNEXUS_STORAGE_ROOT, and GITNEXUS_CONTENT_RETENTION, and fold in
main's FTS skip, embed-session, and help-text updates.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Address PR review feedback (#3060)

Keep legacy registry rows on the local storage fallback, resolve
symlinks before the destructive-path guard, and align hook lookup
with CLI branch slugs, branch-slot metadata, and longest-path match.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Address PR review feedback (#3060)

Only list swept upload directories after a successful removal so
callers cannot treat a permission or transient rm failure as gone.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Address PR review feedback (#3060)

Document that getStoragePath may consult registered storage while
this module still does not mutate the global registry.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(storage): close review findings for external indexes and retention

Re-inspect ownership under the analyze lock, fail-closed when the
registry file is missing, and keep skip-git hook discovery plus
retention fields on HTTP/MCP list surfaces. /api/file stays 410
unless contentRetention is full.

Co-authored-by: Cursor <cursoragent@cursor.com>

* chore(autofix): apply prettier + eslint fixes via /autofix command

* Address PR review feedback (#3060)

Treat lock-only index dirs as empty, honor HTTP --force storage policy, and prefer registered plus branch-aware slots in hooks and augment.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Address PR review feedback (#3060)

Keep hook fallbacks inside the current worktree, compare foreign-local slots canonically, and make storage fixtures survive ownership validation.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix macOS hook test expecting realpath'd registry paths.

resolveHookRepo returns the written registry path, not a filesystem realpath, so the assertion must match that.

* Address gitnexus-check warnings on hook install docs and slot tests.

The Cursor troubleshooting list omitted registry-query.cjs, and the writable-slot test only checked that isDirectory exists instead of that the path is a directory.

* Align the HTTP catalog source-scan with skippable resolveRepo validation.

resolveRepo lists fresh repos with validate: options.validateStorage !== false so DELETE can skip prune; the test still required a literal validate: true.

* Harden storage path sinks so CodeQL path-injection and ReDoS alerts clear.

Contain every filesystem probe inside the resolved storage slot with the inline path.relative idiom, reject filesystem-root slots, and trim slot basenames in linear time.

* Settle bridge stamps before writing so CI size/mtime matches stay stable.

LadybugDB can still flush into bridge.lbug after close+rename; persist whole-millisecond mtimes and wait for consecutive stats to agree so a freshly written pair matches.

* Type the settled bridge stat as fs.Stats so tsc does not see bigint.

Awaited<ReturnType<typeof fsp.stat>> collapsed the bigint overload and broke prepare/typecheck on CI.

* Keep the bridge mtime stamp exact so same-size swaps still fail the pair check.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Wrap the bridge stamp predicate so prettier --check stays green.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Require a quiet interval before stamping a settled bridge file.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Reuse shared storage and settle helpers instead of local copies.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Gergo Magyar <gergomagyar0@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-09-12 20:31:55 +00:00

1046 lines
45 KiB
TypeScript

import { describe, it, expect } from 'vitest';
import { mkdtemp, rm, readdir, writeFile, readFile } from 'fs/promises';
import { tmpdir } from 'os';
import path from 'path';
import {
PARSE_CACHE_VERSION,
PARSE_CACHE_BUCKET_COUNT,
computeChunkHash,
fileContentHash,
packParseCacheChunks,
parseCacheBucketId,
loadParseCache,
loadParseCacheChunk,
persistParseCacheChunk,
saveParseCache,
pruneCache,
slimParseWorkerResultsForCache,
getColdParseRebuildDir,
createColdParseRebuildDir,
type ParseCache,
} from '../../src/storage/parse-cache.js';
import { writeV8CacheFile } from '../../src/storage/v8-sidecar.js';
import type { ParseWorkerResult } from '../../src/core/ingestion/workers/parse-worker.js';
const minimalResult = (overrides: Partial<ParseWorkerResult> = {}): ParseWorkerResult => ({
nodes: [],
relationships: [],
symbols: [],
imports: [],
calls: [],
assignments: [],
heritage: [],
routes: [],
fetchCalls: [],
fetchWrapperDefs: [],
decoratorRoutes: [],
routerIncludes: [],
routerImports: [],
toolDefs: [],
ormQueries: [],
constructorBindings: [],
fileScopeBindings: [],
parsedFiles: [],
skippedLanguages: {},
fileCount: 0,
...overrides,
});
describe('computeChunkHash', () => {
it('produces a stable hex hash for a fixed set of (filePath, contentHash) entries', () => {
const entries = [
{ filePath: 'a.ts', contentHash: 'h-a' },
{ filePath: 'b.ts', contentHash: 'h-b' },
{ filePath: 'c.ts', contentHash: 'h-c' },
];
const h1 = computeChunkHash(entries);
const h2 = computeChunkHash(entries);
expect(h1).toBe(h2);
expect(h1).toMatch(/^[a-f0-9]{64}$/);
});
it('is order-independent (same files in different order → same hash)', () => {
const order1 = [
{ filePath: 'a.ts', contentHash: 'h-a' },
{ filePath: 'b.ts', contentHash: 'h-b' },
];
const order2 = [
{ filePath: 'b.ts', contentHash: 'h-b' },
{ filePath: 'a.ts', contentHash: 'h-a' },
];
expect(computeChunkHash(order1)).toBe(computeChunkHash(order2));
});
it('changes when any file content changes', () => {
const before = [
{ filePath: 'a.ts', contentHash: 'h-a' },
{ filePath: 'b.ts', contentHash: 'h-b' },
];
const after = [
{ filePath: 'a.ts', contentHash: 'h-a' },
{ filePath: 'b.ts', contentHash: 'h-b-NEW' }, // b.ts content changed
];
expect(computeChunkHash(before)).not.toBe(computeChunkHash(after));
});
it('changes when chunk membership changes (file added or removed)', () => {
const small = [
{ filePath: 'a.ts', contentHash: 'h-a' },
{ filePath: 'b.ts', contentHash: 'h-b' },
];
const bigger = [...small, { filePath: 'c.ts', contentHash: 'h-c' }];
expect(computeChunkHash(small)).not.toBe(computeChunkHash(bigger));
});
});
describe('fileContentHash', () => {
it('hashes a string deterministically', () => {
expect(fileContentHash('hello')).toBe(fileContentHash('hello'));
expect(fileContentHash('hello')).not.toBe(fileContentHash('hello!'));
expect(fileContentHash('hello')).toMatch(/^[a-f0-9]{64}$/);
});
it('handles Buffer input identical to its string form', () => {
const s = 'sentinel';
expect(fileContentHash(Buffer.from(s))).toBe(fileContentHash(s));
});
});
describe('PARSE_CACHE_VERSION', () => {
// 35 -> 36 for the bound-callable start-line join (#2735), 36 -> 37 for
// Java/Kotlin Spring AOP capture side-channels (#2416), 37 -> 38 for the Swift
// conditional-directive parse-semantics change (#2771), 38 -> 39 for
// receiver-chain wire format v2: every persisted chain string changed prefix
// and a v2 decoder refuses v1 by design, so a stale cache replays chains this
// build silently discards. 39 -> 40 for inference-typed field captures in six
// languages (#2807) — all parse-time emission, so a warm cache replays the
// pre-fix capture set for byte-unchanged files and the new receiver edges
// never appear.
//
// This pin has now earned its keep EIGHT times, and twice it caught an EXACT
// clash rather than a near-miss: main took 37 for #2416 while this branch
// already used 37, and then took 38 for #2771 after this branch had moved to
// 38. Both times two incompatible schemas claimed one number. Note when the
// second clash was caught — after review, while the branch sat waiting to
// merge — which is precisely the window in which `main` allocates. Re-check
// against origin/main immediately before merge, not at review time.
// Moved 42 -> 43 for #2813's `@reference.embedded-pointer` capture, which is
// parse-time emission and so cannot be served from a v42 warm cache.
// Moved 43 -> 44 for #2842's TypeScript heritage capture (interface and
// abstract-class `@reference.inherits`), which is parse-time emission and so
// cannot be served from a v43 warm cache.
// Moved 44 -> 45 for #2837 (Go struct/interface captures re-anchored from
// `type_declaration` to `type_spec`). This branch first took 44 and COLLIDED
// with #2842 above, which merged first — the ninth entry in the ledger and the
// third EXACT clash. Note what this pin could and could not do: it cannot
// detect the tie (both branches asserted `toBe(44)`, which passes when main is
// already 44); only the merge-time diff against origin/main surfaced it. What
// the pin DOES do is fail loudly the moment the constant and this expectation
// drift apart, which is what forces the re-check to happen at all.
// Moved 45 -> 46 for the JavaScript bare-identifier read captures, the
// object-literal `@definition.property` rule and the TypeScript shape-member
// captures (A1/A2/A4/A5) — all parse-time, so a v45 warm cache serves entries
// carrying neither the new reference sites nor the new Property nodes.
//
// This branch first took 45 and COLLIDED with #2837 above, which merged
// first: the TENTH ledger entry and the FOURTH exact clash, and the second in
// a row. Same lesson as the note above — the pin cannot detect the tie, since
// both sides asserted `toBe(45)` and that passes while main is already 45.
// Only the merge-time diff against origin/main surfaces it.
//
// Moved 46 -> 47 for method-level Spring `@RequestMapping` routes (#2857):
// cached ParseWorkerResults otherwise replay the pre-fix empty route set.
// That PR read this branch's claim on 46 and took 47 rather than colliding —
// the FIFTH clash, and the first the ledger's convention actually prevented.
// It only moved the collision up one step, though: this branch's own 47 and
// everything above it had to be renumbered +1 at merge time. Capture sets
// unchanged; only the numbers moved.
//
// Moved 51 -> 52 for dispatch-guard routes (R3-7): the JS/TS providers now
// implement `extractDecoratorRoutes`, and decorator routes are worker output
// carried in the cache. A v50 warm cache replays a worker result whose
// `decoratorRoutes` predates the extractor, so `route_map` keeps answering
// empty — the exact symptom the change fixes, disguised as "it does not work".
// Moved 52 -> 53 for the same-file constant folding that followed, because a
// build stamped 50 (now 52) had already been used to analyze without it.
//
//
// Moved 47 -> 48 for #2833's three parse-time changes: C++
// `field_declaration` captures for `template_type` and qualified generic
// member types (those members had NO type binding before), a Python interpret
// change that reduces `Repo[User]` to `Repo` in `TypeRef.rawName`, and the new
// `SymbolDefinition.typeParameters` field read from a
// `@declaration.type-parameters` capture in six languages. All three are
// serialized into the cached ParsedFile, so an older warm cache replays
// pre-fix bindings and the fix is a silent no-op on incremental analyze while
// every cold-run test still passes.
//
// 48, not 46, because this branch collided TWICE: it staged 46 and then 47,
// both free when written, and by merge time #2856 claimed 46 and #2857 took 47
// and merged first. This assertion is exactly what CANNOT detect that — the
// branch asserted `toBe(47)` and so did #2857, and both passed. What this pin
// does do is fail loudly the moment the constant and this expectation drift
// apart, which is what forces the merge-time diff against origin/main to
// happen at all.
// Moved 53 -> 54 for W2-8: type parameters are captured on generic functions
// and aliases, not just class-likes, so the shadowing guard has data to read.
// Moved 54 -> 55 for W2-9: the dispatch-guard verb walk tracks boolean polarity,
// so a ternary can no longer report the verb it excludes. Routes are emitted at
// parse time, so a warm cache would replay the inverted verb indefinitely.
// Moved 55 -> 56 for R3-8 part 1: the verb walk returns every method a guard
// serves, so a multi-method guard emits several routes where it emitted one.
// Moved 56 -> 57 for R3-8 part 2: `.match()` dispatch, bound-match test sites,
// named regex consts, and capturing segment wildcards in `regexToRoutePath`.
// Moved 57 -> 58 for #2897: fetch sites are captured without a literal URL.
// Moved 58 -> 59 for the #2899 review follow-up: the dispatch-guard walk keys
// match bindings on (enclosing function, name) instead of the bare identifier,
// and a ternary conjunction INTERSECTS its operands instead of taking the first
// non-empty set. Both strictly remove routes, so a warm cache would keep
// serving a fabricated verbed route that evicts the true one.
// Moved 59 -> 60 for #2864's `ParsedImport.reexportsName` and the
// `@import.publishes` capture gating it — a serialized ParsedFile field AND a
// capture change, the first being the easy-to-miss half. 60 was staged while
// main was 53, chosen above every in-flight MAXIMUM rather than at main + 1;
// #2899 then cascaded main to 59, and 60 survived only because of that choice.
// Moved 60 -> 62 for the cycle-checker fix's two optional `ParsedImport`
// fields, `typeOnly` and `runsOnlyWhenCalled`. Neither is a capture, but
// `parsedfile-store.ts` serializes the whole ParsedFile generically, so both
// are part of the cached shape — the same half of #2864 that was easy to miss.
// A warm cache would replay untagged imports, the strict `=== true` reads
// would take the untagged path, and `check --cycles` would keep reporting the
// erased and deferred imports the branch exists to stop reporting: a silent
// no-op on incremental analyze while every cold-run test passes.
// Main subsequently advanced through 63. Values above it must remain distinct
// from both published branch heads and every active in-flight claim.
// Moved 63 -> 64 for Java enum and annotated heritage captures (#2918),
// then 64 -> 66 for the synthetic-declaration sidecar, both now on main.
// Moved 66 -> 67 for #2917's implicit Java record-component accessor
// definitions and scope declarations. This branch staged 65 before #2918's 66
// landed; 67 is the next free value above every in-flight claim (main 66,
// #2939's 64), re-checked against the claims rather than against main alone.
// Moved 67 -> 68 for #2912's `ReferenceSite.typeArguments` — heritage generic
// arguments derived at extraction time, so a warm cache replays `inherits`
// sites without them and instantiation-aware dispatch degrades silently to
// the pre-fix fan-out. This branch staged 64 above the claims live at the
// time (61, 62, 63); all three landed and cascaded main to 67, so 68 is the
// next free value above every claim at merge — the rule, re-applied.
// Version 69 added #2969's JS/TS data-route-table decoratorRoutes. Version 70
// adds Spring non-HTTP handler side-channel facts (#2417 / #2891), so it is
// the next free value after both cache payload changes.
// Moved 70 -> 71 for #2980's Java constant-route capture set (moduleConstants
// + routePathOperands). 72 -> 74 added import-proven Convex endpoint metadata,
// skipping 73 because open PR #3046 claims it.
// Version 75 adds #3009's NestJS decorator routes to the same JS/TS
// decoratorRoutes channel, so a warm pre-feature cache cannot replay the empty
// route set that change fixes. This branch originally claimed 71; origin/main
// cascaded past it (71 to #2980, 74 to Convex) while the PR was open, so 71
// would now be BELOW main and the reuse gate would never fire. 75 is the next
// free value above origin/main and above every in-flight claim (#3046 at 73,
// #1616 at a stale 2) — the rule, re-applied at merge, not at authoring time.
// Moved 75 -> 76 within this same branch for the NestJS array form, then
// 76 -> 77 because 76 turned out not to be free: origin/main reached 76 via
// #3046 while this branch was in review, and package.json is 1.6.9 on both
// sides, so the cache key was the byte-identical `76+1.6.9` on two branches
// with incompatible worker output. #3046 had skipped 75 precisely because
// this branch held it. Two PRs each doing the bookkeeping correctly still
// collided, because each re-checked once and neither re-checked after the
// other moved — which is why the rule is re-applied AT MERGE, not when the
// number is picked.
// Moved 89 -> 90 for #2865's decorator-route `handlerName` after #3128
// merged and took 89. origin/main is 89; 90 is the next free value and
// still unused by other open PRs' parse-cache.ts heads — the same
// collision the paragraph above describes, caught this time by re-checking
// at merge.
// Moved 90 -> 91 for #3130's Kotlin Spring decoratorRoutes and Kotlin
// ModuleConstants shadow metadata, both persisted worker output.
// Moved 91 -> 92 for #1432 (Zig): the shared callable-flow reader's member-call
// capture facts change for Kotlin / C++ / C# / TypeScript, and Zig is captured
// for the first time with rules that moved within the PR — a warm cache from
// an earlier head of that branch replayed the old facts across `--force`.
// Moved 92 -> 93 for #3161 (Zig static gating): call captures inside a
// comptime-false branch gain the `@reference.static-gated` marker, a
// parse-time fact a warm cache from an earlier head would replay without.
// Moved 94 -> 95 for #3179: Objective-C framework-import-only header
// classification changed parse-worker output for the same file content.
// Moved 95 -> 96 for #3179: Objective-C macro-marker preprocessing now
// recognizes form feed and vertical tab as C preprocessing whitespace.
// Moved 96 -> 97 for #3179: comment-prefixed directives and invalid numeric
// marker prefixes change the parse-time normalization result.
// Moved 97 -> 98 for #3219 (Zig callable-value references): `ZIG_SCOPE_QUERY`
// gained three `@reference.value-ref` rules, so a `.zig` file now yields
// `value-ref` entries in `ParsedFile.referenceSites` where it yielded none.
// A warm pre-v98 cache replays the old, empty site list for every unchanged
// file — `--force` included, since shards are content-addressed — so no USES
// edge is emitted, the boundary probe measures a real zero, and `impact` on a
// registered accessor goes back to `epistemic: "exact"`: the #3399 defect,
// silently un-fixed on exactly the incremental path most users are on.
// Moved 98 -> 99 for #3190: lexical import provenance and corrected export
// evidence. origin/main took 98 for #3219; 99 is the next free value.
it('pins SCHEMA_BUMP to 99 so concurrent bumps cannot silently collide (#2766, #3015, #3088, #2885, #3128, #2865, #3130, #1432, #3161, #3179, #3219, #3190)', () => {
expect(Number(PARSE_CACHE_VERSION.split('+', 1)[0])).toBe(99);
expect(PARSE_CACHE_BUCKET_COUNT).toBe(128);
// The PREVIOUS version must fail the reuse gate, not merely differ from the
// current one — a hardcoded number outside the conflict hunk rebases cleanly
// while being wrong, which is exactly how the 37/38 exact clashes landed.
// Every nearby historical or in-flight value is rejected.
for (const taken of [
59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81,
82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98,
]) {
expect(Number(PARSE_CACHE_VERSION.split('+', 1)[0])).not.toBe(taken);
}
});
it('embeds the gitnexus package version (so upgrades invalidate the cache)', () => {
// Looks like "1+1.6.4" — schema bump prefix + actual gitnexus version
expect(PARSE_CACHE_VERSION).toMatch(/^\d+\+\d+\.\d+\.\d+/);
});
});
describe('packParseCacheChunks (#3088)', () => {
const files = [
{ path: 'src/a.ts', size: 100, language: 'typescript' },
{ path: 'src/b.ts', size: 100, language: 'typescript' },
{ path: 'pkg/c.py', size: 100, language: 'python' },
];
const budget = 2 * 1024 * 1024;
const packKey = (chunk: string[]): string =>
`${files.find((f) => f.path === chunk[0])?.language ?? 'typescript'}\0${parseCacheBucketId(chunk[0])}`;
it('is independent of scan order', () => {
expect(packParseCacheChunks(files, budget)).toEqual(
packParseCacheChunks([...files].reverse(), budget),
);
});
it('add/delete only rewrites packs in the affected (language, bucket)', () => {
const a = packParseCacheChunks(files, budget);
const added = { path: 'AAA.ts', size: 150_000, language: 'typescript' };
const withNew = packParseCacheChunks([...files, added], budget);
const addedKey = packKey([added.path]);
const untouched = (packs: string[][]) =>
packs.filter((c) => packKey(c) !== addedKey).map((c) => c.join('|'));
expect(untouched(withNew).sort()).toEqual(untouched(a).sort());
expect(withNew.some((c) => c.includes(added.path))).toBe(true);
const withoutB = packParseCacheChunks(
files.filter((f) => f.path !== 'src/b.ts'),
budget,
);
const removedKey = packKey(['src/b.ts']);
const leftover = (packs: string[][]) =>
packs.filter((c) => packKey(c) !== removedKey).map((c) => c.join('|'));
expect(leftover(withoutB).sort()).toEqual(leftover(a).sort());
expect(withoutB.every((c) => !c.includes('src/b.ts'))).toBe(true);
});
it('parseCacheBucketId uses the full sha256 digest, not an IEEE-754 prefix', () => {
const path = 'src/foo.ts';
const hex = fileContentHash(path);
const full = Number(BigInt(`0x${hex}`) % BigInt(PARSE_CACHE_BUCKET_COUNT));
const truncated = Number.parseInt(hex.slice(0, 8), 16) % PARSE_CACHE_BUCKET_COUNT;
expect(parseCacheBucketId(path)).toBe(full);
expect(parseCacheBucketId(path)).toBeGreaterThanOrEqual(0);
expect(parseCacheBucketId(path)).toBeLessThan(PARSE_CACHE_BUCKET_COUNT);
expect(full).not.toBe(truncated);
});
});
describe('pruneCache', () => {
it('drops entries whose hashes are not in the used-set', () => {
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map<string, ParseWorkerResult[]>([
['hash-A', [minimalResult()]],
['hash-B', [minimalResult()]],
['hash-C', [minimalResult()]],
]),
usedKeys: new Set<string>(['hash-A']),
};
const removed = pruneCache(cache, cache.usedKeys);
expect(removed).toBe(2);
expect([...cache.entries.keys()].sort()).toEqual(['hash-A']);
});
it('returns 0 when every entry is in use', () => {
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map<string, ParseWorkerResult[]>([
['hash-A', [minimalResult()]],
['hash-B', [minimalResult()]],
]),
usedKeys: new Set<string>(['hash-A', 'hash-B']),
};
expect(pruneCache(cache, cache.usedKeys)).toBe(0);
expect(cache.entries.size).toBe(2);
});
it('drops onDiskKeys entries not in the used-set and counts them', () => {
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map<string, ParseWorkerResult[]>(),
usedKeys: new Set<string>(['disk-A']),
onDiskKeys: new Set<string>(['disk-A', 'disk-B', 'disk-C']),
};
const removed = pruneCache(cache, new Set(['disk-A']));
expect(removed).toBe(2);
expect([...(cache.onDiskKeys ?? [])].sort()).toEqual(['disk-A']);
});
});
describe('loadParseCache / saveParseCache (round-trip)', () => {
it('round-trips an empty cache', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set(),
};
await saveParseCache(dir, cache);
await expect(fs.access(path.join(dir, 'parse-cache', 'index.json'))).resolves.toBeUndefined();
await expect(fs.access(path.join(dir, 'parse-cache.json'))).rejects.toThrow();
const loaded = await loadParseCache(dir);
expect(loaded.version).toBe(PARSE_CACHE_VERSION);
expect(loaded.entries.size).toBe(0);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('returns an empty cache when the file is missing', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(0);
expect(loaded.usedKeys.size).toBe(0);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('returns an empty cache on version mismatch (next-run regen)', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
// Write a cache file with a different version directly
const fs = await import('fs/promises');
await fs.writeFile(
path.join(dir, 'parse-cache.json'),
JSON.stringify({ version: 'foreign-99', entries: { h: [] } }),
'utf-8',
);
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(0); // mismatch → empty
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('returns an empty cache on corrupt JSON', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
await fs.writeFile(path.join(dir, 'parse-cache.json'), '{not-json', 'utf-8');
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(0);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('loads a legacy single-file cache for backwards compatibility', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
await fs.writeFile(
path.join(dir, 'parse-cache.json'),
JSON.stringify({
version: PARSE_CACHE_VERSION,
entries: {
legacyChunk: [minimalResult({ fileCount: 7 })],
},
}),
'utf-8',
);
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(1);
expect(loaded.entries.get('legacyChunk')?.[0]?.fileCount).toBe(7);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('skips corrupt or missing shards while loading the sharded cache index', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const cacheDir = path.join(dir, 'parse-cache');
const goodKey = 'a'.repeat(64);
const missingKey = 'b'.repeat(64);
const badKey = 'c'.repeat(64);
await fs.mkdir(cacheDir, { recursive: true });
await fs.writeFile(
path.join(cacheDir, 'index.json'),
JSON.stringify({
version: PARSE_CACHE_VERSION,
keys: [goodKey, missingKey, badKey],
}),
'utf-8',
);
await writeV8CacheFile(path.join(cacheDir, `${goodKey}.v8`), [
minimalResult({ fileCount: 3 }),
]);
await fs.writeFile(path.join(cacheDir, `${badKey}.v8`), '{not-json', 'utf-8');
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(0);
expect(loaded.onDiskKeys?.size).toBe(3);
const chunk = await loadParseCacheChunk(loaded, goodKey);
expect(chunk?.[0]?.fileCount).toBe(3);
// A shard listed in the index but absent on disk, and a corrupt-JSON
// shard, both resolve to undefined (graceful cache miss) — not a throw.
expect(await loadParseCacheChunk(loaded, missingKey)).toBeUndefined();
expect(await loadParseCacheChunk(loaded, badKey)).toBeUndefined();
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('round-trips Map and Set values through the JSON replacer/reviver', async () => {
// ParsedFile.scopes[*].typeBindings is a ReadonlyMap<string, TypeRef>.
// Without the replacer/reviver pair, JSON.stringify collapses Maps to
// {} and downstream code that does .get() / iterates entries crashes
// with "is not iterable". This test pins the round-trip behaviour.
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const innerMap = new Map<string, string>([
['k1', 'v1'],
['k2', 'v2'],
]);
const innerSet = new Set<string>(['s1', 's2']);
// Stash the live Map/Set inside a synthetic ParseWorkerResult — we
// only need the serializer to traverse them. Casting to bypass the
// strict shape isn't a problem here: this test is about JSON
// round-tripping of arbitrary nested Map/Set values, not full
// ParseWorkerResult contents.
const fake = minimalResult({
parsedFiles: [
{
filePath: 't.ts',
// Cast through unknown to satisfy the readonly Scope shape
// while still smuggling a live Map into the serializer's
// traversal path — see comment block above.
scopes: [{ id: 's1', typeBindings: innerMap, extras: innerSet }],
} as unknown as ParseWorkerResult['parsedFiles'][number],
],
});
const chunkKey = 'd'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map<string, ParseWorkerResult[]>([[chunkKey, [fake]]]),
usedKeys: new Set([chunkKey]),
};
await saveParseCache(dir, cache);
const persisted = await fs.readdir(path.join(dir, 'parse-cache'));
expect(persisted).toContain('index.json');
expect(persisted).toContain(`${chunkKey}.v8`);
const loaded = await loadParseCache(dir);
const reloaded = (await loadParseCacheChunk(loaded, chunkKey))?.[0];
expect(reloaded).toBeDefined();
const scope = (reloaded as ParseWorkerResult).parsedFiles[0]?.scopes[0] as unknown as {
typeBindings?: unknown;
extras?: unknown;
};
expect(scope.typeBindings).toBeInstanceOf(Map);
expect((scope.typeBindings as Map<string, string>).get('k1')).toBe('v1');
expect((scope.typeBindings as Map<string, string>).size).toBe(2);
expect(scope.extras).toBeInstanceOf(Set);
expect((scope.extras as Set<string>).has('s2')).toBe(true);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('ignores traversal-like and non-hex keys in sharded index.json', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const cacheDir = path.join(dir, 'parse-cache');
await fs.mkdir(cacheDir, { recursive: true });
const safeKey = 'e'.repeat(64);
await fs.writeFile(
path.join(cacheDir, 'index.json'),
JSON.stringify({
version: PARSE_CACHE_VERSION,
keys: ['../evil', '/absolute', 'G'.repeat(64), safeKey],
}),
'utf-8',
);
await writeV8CacheFile(path.join(cacheDir, `${safeKey}.v8`), [
minimalResult({ fileCount: 9 }),
]);
const loaded = await loadParseCache(dir);
expect(loaded.onDiskKeys?.size).toBe(1);
const chunk = await loadParseCacheChunk(loaded, safeKey);
expect(chunk?.[0]?.fileCount).toBe(9);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('writes one shard file per cache entry (three distinct keys)', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const k1 = '1'.repeat(64);
const k2 = '2'.repeat(64);
const k3 = '3'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map<string, ParseWorkerResult[]>([
[k1, [minimalResult({ fileCount: 1 })]],
[k2, [minimalResult({ fileCount: 2 })]],
[k3, [minimalResult({ fileCount: 3 })]],
]),
usedKeys: new Set([k1, k2, k3]),
};
await saveParseCache(dir, cache);
const cacheDir = path.join(dir, 'parse-cache');
const names = await fs.readdir(cacheDir);
expect(names).toContain('index.json');
expect(names.filter((n) => n.endsWith('.v8')).length).toBe(3);
const loaded = await loadParseCache(dir);
expect(loaded.onDiskKeys?.size).toBe(3);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('returns empty when sharded index version mismatches even if legacy parse-cache.json is valid', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const cacheDir = path.join(dir, 'parse-cache');
await fs.mkdir(cacheDir, { recursive: true });
await fs.writeFile(
path.join(cacheDir, 'index.json'),
JSON.stringify({ version: 'foreign-sharded-1', keys: [] }),
'utf-8',
);
await fs.writeFile(
path.join(dir, 'parse-cache.json'),
JSON.stringify({
version: PARSE_CACHE_VERSION,
entries: { legacyChunk: [minimalResult({ fileCount: 42 })] },
}),
'utf-8',
);
const loaded = await loadParseCache(dir);
expect(loaded.entries.size).toBe(0);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('second saveParseCache replaces the first sharded cache', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
const k1 = '4'.repeat(64);
const k2 = '5'.repeat(64);
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[k1, [minimalResult()]]]),
usedKeys: new Set([k1]),
});
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[k2, [minimalResult({ fileCount: 99 })]]]),
usedKeys: new Set([k2]),
});
const names = await fs.readdir(path.join(dir, 'parse-cache'));
expect(names).not.toContain(`${k1}.v8`);
expect(names).toContain(`${k2}.v8`);
const loaded = await loadParseCache(dir);
expect(loaded.onDiskKeys?.size).toBe(1);
const chunk = await loadParseCacheChunk(loaded, k2);
expect(chunk?.[0]?.fileCount).toBe(99);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('removes legacy parse-cache.json after a successful sharded save', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const fs = await import('fs/promises');
await fs.writeFile(
path.join(dir, 'parse-cache.json'),
JSON.stringify({
version: PARSE_CACHE_VERSION,
entries: { oldLegacy: [minimalResult({ fileCount: 5 })] },
}),
'utf-8',
);
const k = '6'.repeat(64);
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[k, [minimalResult({ fileCount: 6 })]]]),
usedKeys: new Set([k]),
});
await expect(fs.access(path.join(dir, 'parse-cache.json'))).rejects.toThrow();
const loaded = await loadParseCache(dir);
const chunk = await loadParseCacheChunk(loaded, k);
expect(chunk?.[0]?.fileCount).toBe(6);
expect(loaded.onDiskKeys?.has(k)).toBe(true);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('slimParseWorkerResultsForCache drops legacy DAG fields', () => {
const raw = minimalResult({
calls: [{ filePath: 'a.c', calleeName: 'f', line: 1 } as never],
assignments: [
{ filePath: 'a.c', sourceId: 's', receiverText: 'x', propertyName: 'y', line: 1 },
],
constructorBindings: [{ filePath: 'a.c', bindings: [] }],
parsedFiles: [
{
filePath: 'a.c',
moduleScope: 'm',
scopes: [],
parsedImports: [],
localDefs: [],
referenceSites: [],
},
],
scopeExtractionFailures: ['a.c'],
});
const slim = slimParseWorkerResultsForCache([raw])[0];
expect(slim.calls).toEqual([]);
expect(slim.assignments).toEqual([]);
expect(slim.constructorBindings).toEqual([]);
expect(slim.parsedFiles).toEqual([]);
expect(slim.scopeExtractionFailures).toEqual(['a.c']);
expect(slim.fileCount).toBe(raw.fileCount);
});
it('slimParseWorkerResultsForCache preserves nodes (incremental exportedTypeMap depends on them)', () => {
const raw = minimalResult({
nodes: [
{
id: 'Function:a.ts:foo',
label: 'Function',
properties: { name: 'foo', filePath: 'a.ts', isExported: true },
},
] as ParseWorkerResult['nodes'],
});
const slim = slimParseWorkerResultsForCache([raw])[0];
// `nodes` (and `symbols`) must survive slimming — on a warm cache hit they
// are what mergeChunkResults replays to rebuild the ExportedTypeMap.
expect(slim.nodes).toEqual(raw.nodes);
expect(slim.nodes).toHaveLength(1);
});
it('round-trips scope extraction failures through a persisted cache shard', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const key = 'e'.repeat(64);
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[key, [minimalResult({ scopeExtractionFailures: ['src/broken.ts'] })]]]),
usedKeys: new Set([key]),
});
const loaded = await loadParseCache(dir);
const replayed = await loadParseCacheChunk(loaded, key);
expect(replayed?.[0]?.scopeExtractionFailures).toEqual(['src/broken.ts']);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('persistParseCacheChunk writes to disk without retaining in-memory entries', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const key = '7'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set(),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 11 })]);
expect(cache.entries.has(key)).toBe(false);
expect(cache.onDiskKeys?.has(key)).toBe(true);
const chunk = await loadParseCacheChunk(cache, key);
expect(chunk?.[0]?.fileCount).toBe(11);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('saveParseCache excludes a usedKeys hash whose shard was never persisted (no phantom index key)', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const realKey = 'a'.repeat(64);
const phantomKey = 'b'.repeat(64); // in usedKeys but has no entry and no on-disk shard
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map([[realKey, [minimalResult({ fileCount: 3 })]]]),
usedKeys: new Set([realKey, phantomKey]),
};
await saveParseCache(dir, cache);
const loaded = await loadParseCache(dir);
expect(loaded.onDiskKeys?.has(realKey)).toBe(true);
// The phantom key was never written, so it must not appear in the index.
expect(loaded.onDiskKeys?.has(phantomKey)).toBe(false);
expect((await loadParseCacheChunk(loaded, realKey))?.[0]?.fileCount).toBe(3);
expect(await loadParseCacheChunk(loaded, phantomKey)).toBeUndefined();
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('saveParseCache copies a persisted-but-evicted shard (copyFile branch) and round-trips', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const key = 'c'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: dir,
onDiskKeys: new Set(),
};
// persist writes the shard to the live dir and evicts it from `entries`,
// so saveParseCache must hit the copyFile branch to carry it forward.
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 42 })]);
expect(cache.entries.has(key)).toBe(false);
await saveParseCache(dir, cache);
const loaded = await loadParseCache(dir);
expect(loaded.onDiskKeys?.has(key)).toBe(true);
expect((await loadParseCacheChunk(loaded, key))?.[0]?.fileCount).toBe(42);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('recreates a memoized shard directory after a long-lived process replaces it', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-'));
try {
const firstKey = 'd'.repeat(64);
const secondKey = 'e'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([firstKey]),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, firstKey, [minimalResult({ fileCount: 1 })]);
await rm(path.join(dir, 'parse-cache'), { recursive: true, force: true });
cache.usedKeys = new Set([secondKey]);
await persistParseCacheChunk(cache, secondKey, [minimalResult({ fileCount: 2 })]);
await saveParseCache(dir, cache);
const loaded = await loadParseCache(dir);
expect((await loadParseCacheChunk(loaded, secondKey))?.[0]?.fileCount).toBe(2);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('writes a V8 shard and loads it with Map-preserving semantics', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-v8-'));
try {
const innerMap = new Map<string, string>([
['k1', 'v1'],
['k2', 'v2'],
]);
const innerSet = new Set<string>(['s1', 's2']);
const fake = minimalResult({
fileCount: 9,
imports: [
{
typeBindings: innerMap,
extras: innerSet,
} as unknown as ParseWorkerResult['imports'][number],
],
});
const key = 'f'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [fake]);
const names = await readdir(path.join(dir, 'parse-cache'));
expect(names).toEqual(expect.arrayContaining([`${key}.v8`]));
expect(names.some((n) => n.endsWith('.json') && n !== 'index.json')).toBe(false);
const loaded = await loadParseCacheChunk(cache, key);
expect(loaded?.[0]?.fileCount).toBe(9);
const smuggled = loaded?.[0]?.imports[0] as unknown as {
typeBindings?: unknown;
extras?: unknown;
};
expect(smuggled.typeBindings).toBeInstanceOf(Map);
expect([...(smuggled.typeBindings as Map<string, string>)]).toEqual([
['k1', 'v1'],
['k2', 'v2'],
]);
expect(smuggled.extras).toBeInstanceOf(Set);
expect([...(smuggled.extras as Set<string>)].sort()).toEqual(['s1', 's2']);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('treats a corrupt parse-cache V8 shard as a miss', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-v8-fb-'));
try {
const key = 'a'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 4 })]);
await writeFile(path.join(dir, 'parse-cache', `${key}.v8`), Buffer.from([1, 2, 3]));
const loaded = await loadParseCacheChunk(cache, key);
expect(loaded).toBeUndefined();
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('saveParseCache copies an existing V8 shard', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-v8-copy-'));
try {
const key = 'c'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 42 })]);
const liveV8 = await readFile(path.join(dir, 'parse-cache', `${key}.v8`));
await saveParseCache(dir, cache);
expect(await readdir(path.join(dir, 'parse-cache'))).toEqual(
expect.arrayContaining([`${key}.v8`, 'index.json']),
);
expect(await readFile(path.join(dir, 'parse-cache', `${key}.v8`))).toEqual(liveV8);
const loaded = await loadParseCache(dir);
expect((await loadParseCacheChunk(loaded, key))?.[0]?.fileCount).toBe(42);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('misses when the V8 shard is absent', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-v8-legacy-'));
try {
const key = 'b'.repeat(64);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: dir,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 7 })]);
await rm(path.join(dir, 'parse-cache', `${key}.v8`), { force: true });
const loaded = await loadParseCacheChunk(cache, key);
expect(loaded).toBeUndefined();
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('persists cold-rebuild shards under staging without touching the live parse-cache dir', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-stage-'));
try {
const liveKey = 'a'.repeat(64);
const stagedKey = 'b'.repeat(64);
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[liveKey, [minimalResult({ fileCount: 1 })]]]),
usedKeys: new Set([liveKey]),
});
const staging = getColdParseRebuildDir(dir);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([liveKey, stagedKey]),
storagePath: staging,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, stagedKey, [minimalResult({ fileCount: 99 })]);
const liveNames = await readdir(path.join(dir, 'parse-cache'));
expect(liveNames).toContain(`${liveKey}.v8`);
expect(liveNames).not.toContain(`${stagedKey}.v8`);
const stagedNames = await readdir(path.join(staging, 'parse-cache'));
expect(stagedNames).toContain(`${stagedKey}.v8`);
const saved = await saveParseCache(dir, cache);
expect(saved.sort()).toEqual([liveKey, stagedKey].sort());
const loaded = await loadParseCache(dir);
expect((await loadParseCacheChunk(loaded, liveKey))?.[0]?.fileCount).toBe(1);
expect((await loadParseCacheChunk(loaded, stagedKey))?.[0]?.fileCount).toBe(99);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('prefers a staged shard over a same-hash live shard when publishing', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-pref-'));
try {
const key = 'c'.repeat(64);
await saveParseCache(dir, {
version: PARSE_CACHE_VERSION,
entries: new Map([[key, [minimalResult({ fileCount: 1 })]]]),
usedKeys: new Set([key]),
});
const staging = getColdParseRebuildDir(dir);
const cache: ParseCache = {
version: PARSE_CACHE_VERSION,
entries: new Map(),
usedKeys: new Set([key]),
storagePath: staging,
onDiskKeys: new Set(),
};
await persistParseCacheChunk(cache, key, [minimalResult({ fileCount: 7 })]);
await saveParseCache(dir, cache);
const loaded = await loadParseCache(dir);
expect((await loadParseCacheChunk(loaded, key))?.[0]?.fileCount).toBe(7);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
it('createColdParseRebuildDir returns distinct directories under the same storage root', async () => {
const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-uniq-'));
try {
const a = await createColdParseRebuildDir(dir);
const b = await createColdParseRebuildDir(dir);
expect(a).not.toBe(b);
expect(a.startsWith(path.join(dir, 'parse-rebuild.'))).toBe(true);
expect(b.startsWith(path.join(dir, 'parse-rebuild.'))).toBe(true);
} finally {
await rm(dir, { recursive: true, force: true });
}
});
});