brainy/tests/unit/db/db-backup.test.ts
David Snelling 7aad80395e feat(8.0): validateBackup() dry-run + includeContent blob round-trip test + clone test
- validateBackup(data) → { valid, errors, warnings }: structural check, supported
  formatVersion, entity-id uniqueness + required fields, relation-endpoint coverage.
  Lets consumers (e.g. a serializer checking a .wbench graph) validate before import()
  without mutating the brain. Exported from the package root.
- Tests: validateBackup cases, remapIds clone (copy-not-move), and the includeContent
  VFS-blob filesystem round-trip (export captures bytes → import writes them).

Completes the #196 export/import surface for the showcase bar (deferred to 8.0.x:
since(prior).export() delta convenience, exportStream/importStream NDJSON).
2026-06-17 11:44:29 -07:00

295 lines
12 KiB
TypeScript

/**
* Unit tests for the 8.0 portable graph backup/restore surface:
* db.export() / brain.export() (read, at a pinned generation)
* brain.import(backup) (write, one atomic transaction; polymorphic)
*
* Real round-trips against in-memory storage (no mocks of the API under test),
* including the 8.0-specific compositions (asOf/with export) and the polymorphic
* import() dispatch. Entities carry subtypes so the suite passes under 8.0's
* subtype-required default.
*/
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
import { randomUUID } from 'node:crypto'
import * as fs from 'node:fs/promises'
import * as os from 'node:os'
import * as path from 'node:path'
import { Brainy } from '../../../src/brainy'
import { createTestConfig } from '../../helpers/test-factory'
import { NounType, VerbType } from '../../../src/types/graphTypes'
import { validateBackup } from '../../../src/db/backup'
import type { BackupData } from '../../../src/db/backup'
describe('8.0 portable graph export/import (BackupData v1)', () => {
let brain: Brainy
beforeEach(async () => {
brain = new Brainy(createTestConfig())
await brain.init()
})
afterEach(async () => {
await brain.close()
})
describe('format + round-trip', () => {
it('brain.export() produces a versioned BackupData document', async () => {
const a = await brain.add({ data: 'Alice', type: NounType.Person, subtype: 'employee' })
const b = await brain.add({ data: 'Acme', type: NounType.Organization, subtype: 'vendor' })
await brain.relate({ from: a, to: b, type: VerbType.WorksWith, subtype: 'full-time' })
const backup = await brain.export()
expect(backup.format).toBe('brainy-backup')
expect(backup.formatVersion).toBe(1)
expect(backup.entities.map((e) => e.id).sort()).toEqual([a, b].sort())
expect(backup.relations).toHaveLength(1)
expect(backup.entities.find((e) => e.id === a)?.subtype).toBe('employee')
expect(backup.relations[0].subtype).toBe('full-time')
})
it('round-trips into a second brain via polymorphic brain.import()', async () => {
const a = await brain.add({ data: 'Alice', type: NounType.Person, subtype: 'employee' })
const b = await brain.add({ data: 'Bob', type: NounType.Person, subtype: 'employee' })
await brain.relate({ from: a, to: b, type: VerbType.FriendOf, subtype: 'close' })
const backup = await brain.export({}, { includeVectors: true })
const target = new Brainy(createTestConfig())
await target.init()
try {
const result = await target.import(backup)
expect(result.imported).toBe(2)
expect(result.errors).toHaveLength(0)
expect((await target.get(a))?.id).toBe(a)
const rels = await target.related({ from: a })
expect(rels.some((r) => r.to === b && r.type === VerbType.FriendOf)).toBe(true)
} finally {
await target.close()
}
})
})
describe('selectors', () => {
it('ids — exactly the requested entities', async () => {
const a = await brain.add({ data: 'A', type: NounType.Thing, subtype: 'x' })
const b = await brain.add({ data: 'B', type: NounType.Thing, subtype: 'x' })
await brain.add({ data: 'C', type: NounType.Thing, subtype: 'x' })
const backup = await brain.export({ ids: [a, b] })
expect(backup.entities.map((e) => e.id).sort()).toEqual([a, b].sort())
})
it('collection — collection + transitive Contains members', async () => {
const root = await brain.add({ data: 'Folder', type: NounType.Collection, subtype: 'dir' })
const c1 = await brain.add({ data: 'C1', type: NounType.Document, subtype: 'doc' })
const c2 = await brain.add({ data: 'C2', type: NounType.Document, subtype: 'doc' })
await brain.add({ data: 'Outside', type: NounType.Document, subtype: 'doc' })
await brain.relate({ from: root, to: c1, type: VerbType.Contains, subtype: 'has' })
await brain.relate({ from: c1, to: c2, type: VerbType.Contains, subtype: 'has' })
const backup = await brain.export({ collection: root })
expect(backup.entities.map((e) => e.id).sort()).toEqual([root, c1, c2].sort())
})
it('induced edges only by default', async () => {
const a = await brain.add({ data: 'A', type: NounType.Thing, subtype: 'x' })
const b = await brain.add({ data: 'B', type: NounType.Thing, subtype: 'x' })
const c = await brain.add({ data: 'C', type: NounType.Thing, subtype: 'x' })
await brain.relate({ from: a, to: b, type: VerbType.RelatedTo, subtype: 'r' })
await brain.relate({ from: b, to: c, type: VerbType.RelatedTo, subtype: 'r' })
const backup = await brain.export({ ids: [a, b] })
expect(backup.relations).toHaveLength(1)
expect(backup.relations[0].from).toBe(a)
})
})
describe('vectors + conflict', () => {
it('omits vectors by default and re-embeds on import', async () => {
const a = await brain.add({ data: 'Re-embed me', type: NounType.Thing, subtype: 'x' })
const backup = await brain.export({ ids: [a] })
expect(backup.entities[0].vector).toBeUndefined()
const target = new Brainy(createTestConfig())
await target.init()
try {
const result = await target.import(backup)
expect(result.reembedded).toBe(1)
expect((await target.get(a, { includeVectors: true }))?.vector?.length).toBeGreaterThan(0)
} finally {
await target.close()
}
})
it('onConflict:merge updates an existing entity in place', async () => {
const a = await brain.add({ data: 'V1', type: NounType.Thing, subtype: 'x', metadata: { n: 1 } })
const backup = await brain.export({ ids: [a] }, { includeVectors: true })
await brain.update({ id: a, metadata: { n: 99 }, merge: false })
const result = await brain.import(backup, { onConflict: 'merge' })
expect(result.merged).toBe(1)
expect((await brain.get(a))?.metadata?.n).toBe(1)
})
})
describe('8.0 composition — export on the immutable Db', () => {
it('asOf(generation).export() is a time-travel export', async () => {
// Only transact() advances the committed generation (add() does not), so
// distinct generations are created via transact for a true time-travel pin.
const a = '22222222-2222-4222-8222-222222222222'
const b = '33333333-3333-4333-8333-333333333333'
await brain.transact([{ op: 'add', id: a, data: 'First', type: NounType.Thing, subtype: 'x' }])
const g1 = brain.generation()
await brain.transact([{ op: 'add', id: b, data: 'Second', type: NounType.Thing, subtype: 'x' }])
const past = await brain.asOf(g1)
try {
// Whole-brain export at g1 enumerates via the generation-correct find() path.
const backup = await past.export()
const ids = backup.entities.map((e) => e.id)
expect(ids).toContain(a)
expect(ids).not.toContain(b) // b was committed in a later generation
} finally {
await past.release()
}
})
it('now().with(ops).export() is a what-if export', async () => {
const a = await brain.add({ data: 'Real', type: NounType.Thing, subtype: 'x' })
const speculativeId = '11111111-1111-4111-8111-111111111111'
const view = await brain.now().with([
{ op: 'add', id: speculativeId, data: 'Speculative', type: NounType.Thing, subtype: 'x' }
])
try {
const backup = await view.export({ ids: [a, speculativeId] })
expect(backup.entities.map((e) => e.id).sort()).toEqual([a, speculativeId].sort())
} finally {
await view.release()
}
// The speculative entity never touched the durable brain.
expect(await brain.get(speculativeId)).toBeNull()
})
})
describe('import validation', () => {
it('rejects a newer formatVersion', async () => {
const future: BackupData = {
format: 'brainy-backup',
formatVersion: 999,
brainyVersion: 'x',
createdAt: new Date().toISOString(),
embedding: { model: 'm', dimensions: 384 },
entities: [],
relations: [],
stats: { entityCount: 0, relationCount: 0, blobCount: 0 }
}
await expect(brain.import(future)).rejects.toThrow(/formatVersion/)
})
})
describe('id remapping (clone)', () => {
it('imports a subgraph under fresh ids (a copy, not a move)', async () => {
const a = await brain.add({ data: 'A', type: NounType.Thing, subtype: 'x' })
const b = await brain.add({ data: 'B', type: NounType.Thing, subtype: 'x' })
await brain.relate({ from: a, to: b, type: VerbType.RelatedTo, subtype: 'r' })
const backup = await brain.export({ ids: [a, b] }, { includeVectors: true })
const remap = new Map<string, string>([
[a, randomUUID()],
[b, randomUUID()]
])
const result = await brain.import(backup, { remapIds: (id) => remap.get(id) ?? id })
expect(result.imported).toBe(2)
expect((await brain.get(remap.get(a)!))?.id).toBe(remap.get(a))
expect((await brain.get(a))?.id).toBe(a) // original still present
const rels = await brain.related({ from: remap.get(a)! })
expect(rels.some((r) => r.to === remap.get(b))).toBe(true)
})
})
describe('validateBackup() — dry-run check', () => {
const valid = (): BackupData => ({
format: 'brainy-backup',
formatVersion: 1,
brainyVersion: 'x',
createdAt: new Date().toISOString(),
embedding: { model: 'all-MiniLM-L6-v2', dimensions: 384 },
entities: [{ id: 'a', type: NounType.Thing }],
relations: [],
stats: { entityCount: 1, relationCount: 0, blobCount: 0, vectorDimensions: 384 }
})
it('accepts a well-formed backup', () => {
const r = validateBackup(valid())
expect(r.valid).toBe(true)
expect(r.errors).toHaveLength(0)
})
it('rejects a non-BackupData value', () => {
const r = validateBackup({ entities: [] })
expect(r.valid).toBe(false)
expect(r.errors[0]).toMatch(/BackupData/)
})
it('rejects a newer formatVersion', () => {
const r = validateBackup({ ...valid(), formatVersion: 999 })
expect(r.valid).toBe(false)
expect(r.errors.some((e) => /formatVersion/.test(e))).toBe(true)
})
it('flags duplicate entity ids as an error', () => {
const b = valid()
b.entities = [
{ id: 'dup', type: NounType.Thing },
{ id: 'dup', type: NounType.Thing }
]
const r = validateBackup(b)
expect(r.valid).toBe(false)
expect(r.errors.some((e) => /duplicate/.test(e))).toBe(true)
})
it('warns (not errors) on a relation endpoint missing from entities', () => {
const b = valid()
b.relations = [{ id: 'r1', from: 'a', to: 'missing', type: VerbType.RelatedTo }]
const r = validateBackup(b)
expect(r.valid).toBe(true) // a dangling endpoint is a warning, not a hard error
expect(r.warnings.some((w) => /missing/.test(w))).toBe(true)
})
})
})
describe('8.0 export includeContent (VFS blobs, filesystem)', () => {
let dir: string
let brain: Brainy
beforeEach(async () => {
dir = await fs.mkdtemp(path.join(os.tmpdir(), 'brainy-blob-'))
brain = new Brainy({ storage: { type: 'filesystem', rootDirectory: dir } })
await brain.init()
})
afterEach(async () => {
await brain.close()
await fs.rm(dir, { recursive: true, force: true })
})
it('captures VFS file bytes in blobs and writes them on import', async () => {
await brain.vfs.writeFile('/hello.txt', 'Hello blobs')
const backup = await brain.export(
{ vfsPath: '/hello.txt' },
{ includeVectors: true, includeContent: true }
)
expect(backup.stats.blobCount).toBeGreaterThanOrEqual(1)
const b64 = Object.values(backup.blobs ?? {})[0]
expect(Buffer.from(b64, 'base64').toString()).toBe('Hello blobs')
const dir2 = await fs.mkdtemp(path.join(os.tmpdir(), 'brainy-blob2-'))
const target = new Brainy({ storage: { type: 'filesystem', rootDirectory: dir2 } })
await target.init()
try {
const result = await target.import(backup)
expect(result.blobsWritten).toBeGreaterThanOrEqual(1)
expect(result.imported).toBeGreaterThanOrEqual(1)
} finally {
await target.close()
await fs.rm(dir2, { recursive: true, force: true })
}
})
})