feat: add ImageHandler with EXIF extraction and comprehensive MIME detection (v5.2.0)

Implements Phase 1.5 (Comprehensive MIME Type Detection) and adds built-in image processing support to IntelligentImportAugmentation.

**New Features:**
- ImageHandler: Extracts image metadata (dimensions, format, color space) using sharp
- EXIF extraction: Camera data, GPS, timestamps using exifr library
- Support for JPEG, PNG, WebP, GIF, TIFF, BMP, SVG, HEIC, AVIF formats
- MimeTypeDetector: Unified MIME type detection with magic byte support
- FormatDetector: Enhanced with image format detection via MIME + magic bytes

**Architecture Fixes:**
- Fixed brain.import() augmentation pipeline integration (src/brainy.ts:3140-3154)
- Added parameter spreading for ImportSource objects to enable augmentation access
- Fixed metadata propagation through ImportCoordinator to final results
- Added augmentation data check in ImportCoordinator.extract()

**Integration:**
- ImageHandler registered as built-in handler alongside CSV, Excel, PDF
- Images import as 'media' entities with 'image' subtype
- Full metadata preserved in knowledge graph entities
- Configuration options: enableImage, extractEXIF, imageDefaults

**Test Coverage:**
- 15 integration tests (image-import.test.ts) - 100% passing
- 27 unit tests (image-handler.test.ts) - 100% passing
- Format detection tests for all supported image types
- Error handling and resilience tests

**Breaking Changes:** None - backward compatible

Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
David Snelling 2025-11-03 14:06:17 -08:00
parent 6345f87eb2
commit 1874b77896
26 changed files with 5079 additions and 434 deletions

View file

@ -0,0 +1,187 @@
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
import { Brainy } from '../../../src/brainy.js'
import { VirtualFileSystem } from '../../../src/vfs/VirtualFileSystem.js'
import * as fs from 'fs/promises'
import * as path from 'path'
/**
* v5.2.0: Test unified BlobStorage integration with VFS
*
* This test verifies that:
* 1. All files (small, medium, large) use BlobStorage
* 2. No size-based branching occurs
* 3. Content is stored and retrieved correctly
* 4. Deduplication works automatically
*
* Note: Uses FileSystemStorage because BlobStorage is only available
* in COW-enabled storage adapters (not MemoryStorage)
*/
describe('VFS Unified BlobStorage (v5.2.0)', () => {
let brain: Brainy
let vfs: VirtualFileSystem
let testDir: string
beforeEach(async () => {
// Create temporary directory for test storage
testDir = path.join('/tmp', `brainy-test-blob-${Date.now()}-${Math.random().toString(36).slice(2)}`)
await fs.mkdir(testDir, { recursive: true })
brain = new Brainy({
storage: {
type: 'filesystem',
options: { path: testDir }
},
silent: true
})
await brain.init()
vfs = brain.vfs
})
afterEach(async () => {
await brain.close()
// Clean up temporary directory
try {
await fs.rm(testDir, { recursive: true, force: true })
} catch (error) {
// Ignore cleanup errors
}
})
describe('Unified Storage Path', () => {
it('should store small files (<100KB) in BlobStorage', async () => {
const content = 'Small file content'
await vfs.writeFile('/small.txt', content)
// Get entity directly using VFS API
const entity = await vfs.getEntity('/small.txt')
expect(entity.metadata.vfsType).toBe('file')
expect(entity.metadata.storage?.type).toBe('blob')
expect(entity.metadata.storage?.hash).toBeDefined()
const readContent = await vfs.readFile('/small.txt')
expect(readContent.toString()).toBe(content)
})
it('should store medium files (100KB-10MB) in BlobStorage', async () => {
const content = Buffer.alloc(200_000, 'M') // 200KB
await vfs.writeFile('/medium.bin', content)
const entity = await vfs.getEntity('/medium.bin')
expect(entity.metadata.vfsType).toBe('file')
expect(entity.metadata.storage?.type).toBe('blob')
expect(entity.metadata.storage?.hash).toBeDefined()
const readContent = await vfs.readFile('/medium.bin')
expect(Buffer.compare(readContent, content)).toBe(0)
})
it('should store large files (>10MB) in BlobStorage', async () => {
const content = Buffer.alloc(11_000_000, 'L') // 11MB
await vfs.writeFile('/large.bin', content)
const entity = await vfs.getEntity('/large.bin')
expect(entity.metadata.vfsType).toBe('file')
expect(entity.metadata.storage?.type).toBe('blob')
expect(entity.metadata.storage?.hash).toBeDefined()
const readContent = await vfs.readFile('/large.bin')
expect(Buffer.compare(readContent, content)).toBe(0)
})
})
describe('Deduplication', () => {
it('should deduplicate identical files', async () => {
const content = 'Duplicate content test'
// Write same content to two different paths
await vfs.writeFile('/file1.txt', content)
await vfs.writeFile('/file2.txt', content)
// Get entities directly
const entity1 = await vfs.getEntity('/file1.txt')
const entity2 = await vfs.getEntity('/file2.txt')
// Both should have blob storage
expect(entity1.metadata.storage?.type).toBe('blob')
expect(entity2.metadata.storage?.type).toBe('blob')
// But same blob hash (deduplicated)
const hash1 = entity1.metadata.storage?.hash
const hash2 = entity2.metadata.storage?.hash
expect(hash1).toBeDefined()
expect(hash2).toBeDefined()
expect(hash1).toBe(hash2) // Same content = same hash
})
})
describe('File Operations', () => {
it('should update files correctly', async () => {
await vfs.writeFile('/update.txt', 'Original content')
await vfs.writeFile('/update.txt', 'Updated content')
const content = await vfs.readFile('/update.txt')
expect(content.toString()).toBe('Updated content')
})
it('should delete files and decrement blob refs', async () => {
await vfs.writeFile('/delete.txt', 'Delete me')
await vfs.unlink('/delete.txt')
await expect(vfs.readFile('/delete.txt')).rejects.toThrow()
})
it('should append to files', async () => {
await vfs.writeFile('/append.txt', 'First part')
await vfs.appendFile('/append.txt', ' Second part')
const content = await vfs.readFile('/append.txt')
expect(content.toString()).toBe('First part Second part')
})
})
describe('Binary Files', () => {
it('should handle binary files correctly', async () => {
const binary = Buffer.from([0x00, 0xFF, 0xAB, 0xCD, 0xEF])
await vfs.writeFile('/binary.dat', binary)
const read = await vfs.readFile('/binary.dat')
expect(Buffer.compare(read, binary)).toBe(0)
})
it('should preserve binary file integrity', async () => {
// Create a buffer with various byte patterns
const buffer = Buffer.alloc(1000)
for (let i = 0; i < 1000; i++) {
buffer[i] = i % 256
}
await vfs.writeFile('/integrity.bin', buffer)
const read = await vfs.readFile('/integrity.bin')
expect(Buffer.compare(read, buffer)).toBe(0)
expect(read.length).toBe(buffer.length)
})
})
describe('Metadata', () => {
it('should store correct metadata', async () => {
const content = 'Test file'
await vfs.writeFile('/meta.txt', content)
const entity = await vfs.getEntity('/meta.txt')
expect(entity.metadata.size).toBe(content.length)
expect(entity.metadata.vfsType).toBe('file')
expect(entity.metadata.storage?.type).toBe('blob')
expect(entity.metadata.storage?.size).toBe(content.length)
expect(entity.metadata.mimeType).toBeDefined()
})
})
})

View file

@ -0,0 +1,230 @@
/**
* Comprehensive MIME Type Detection Tests (v5.2.0)
*
* Verifies that MimeTypeDetector correctly identifies:
* - Standard types (via mime library)
* - Custom developer types (shell, configs, modern languages)
* - Office formats (Microsoft, OpenDocument)
* - Special files (Dockerfile, Makefile, dotfiles)
*/
import { describe, it, expect } from 'vitest'
import { mimeDetector } from '../../../src/vfs/MimeTypeDetector.js'
describe('MimeTypeDetector (v5.2.0)', () => {
describe('Code Files - Programming Languages', () => {
it('should detect TypeScript files', () => {
expect(mimeDetector.detectMimeType('file.ts')).toBe('text/typescript')
expect(mimeDetector.detectMimeType('component.tsx')).toBe('text/typescript')
})
it('should detect JavaScript files', () => {
// mime library returns text/javascript for .js (IANA standard)
expect(mimeDetector.detectMimeType('file.js')).toBe('text/javascript')
expect(mimeDetector.detectMimeType('component.jsx')).toBe('text/javascript')
expect(mimeDetector.detectMimeType('module.mjs')).toBe('text/javascript')
})
it('should detect modern languages', () => {
expect(mimeDetector.detectMimeType('file.kt')).toBe('text/x-kotlin')
expect(mimeDetector.detectMimeType('file.swift')).toBe('text/x-swift')
expect(mimeDetector.detectMimeType('file.dart')).toBe('text/x-dart')
expect(mimeDetector.detectMimeType('script.lua')).toBe('text/x-lua')
expect(mimeDetector.detectMimeType('app.scala')).toBe('text/x-scala')
})
it('should detect traditional languages', () => {
expect(mimeDetector.detectMimeType('script.py')).toBe('text/x-python')
expect(mimeDetector.detectMimeType('main.go')).toBe('text/x-go')
expect(mimeDetector.detectMimeType('lib.rs')).toBe('text/x-rust')
expect(mimeDetector.detectMimeType('App.java')).toBe('text/x-java')
expect(mimeDetector.detectMimeType('main.c')).toBe('text/x-c')
expect(mimeDetector.detectMimeType('main.cpp')).toBe('text/x-c++')
})
it('should detect functional languages', () => {
expect(mimeDetector.detectMimeType('main.hs')).toBe('text/x-haskell')
expect(mimeDetector.detectMimeType('core.clj')).toBe('text/x-clojure')
expect(mimeDetector.detectMimeType('server.erl')).toBe('text/x-erlang')
expect(mimeDetector.detectMimeType('lib.ex')).toBe('text/x-elixir')
})
})
describe('Shell Scripts', () => {
it('should detect various shell script types', () => {
expect(mimeDetector.detectMimeType('script.sh')).toBe('application/x-sh')
expect(mimeDetector.detectMimeType('setup.bash')).toBe('text/x-shellscript')
expect(mimeDetector.detectMimeType('config.zsh')).toBe('text/x-shellscript')
expect(mimeDetector.detectMimeType('functions.fish')).toBe('text/x-shellscript')
})
})
describe('Configuration Files', () => {
it('should detect config file formats', () => {
expect(mimeDetector.detectMimeType('.env')).toBe('text/x-env')
expect(mimeDetector.detectMimeType('config.ini')).toBe('text/x-ini')
expect(mimeDetector.detectMimeType('app.properties')).toBe('text/x-java-properties')
expect(mimeDetector.detectMimeType('settings.conf')).toBe('text/plain')
})
it('should detect dotfiles', () => {
expect(mimeDetector.detectMimeType('.gitignore')).toBe('text/plain')
expect(mimeDetector.detectMimeType('.dockerignore')).toBe('text/plain')
expect(mimeDetector.detectMimeType('.npmignore')).toBe('text/plain')
expect(mimeDetector.detectMimeType('.editorconfig')).toBe('text/plain')
})
})
describe('Build & Project Files', () => {
it('should detect special build files', () => {
expect(mimeDetector.detectMimeType('Dockerfile')).toBe('text/x-dockerfile')
expect(mimeDetector.detectMimeType('Makefile')).toBe('text/x-makefile')
expect(mimeDetector.detectMimeType('build.gradle')).toBe('text/x-gradle')
expect(mimeDetector.detectMimeType('CMakeLists.txt.cmake')).toBe('text/x-cmake')
})
})
describe('Web Framework Components', () => {
it('should detect modern web frameworks', () => {
expect(mimeDetector.detectMimeType('Component.vue')).toBe('text/x-vue')
expect(mimeDetector.detectMimeType('Page.svelte')).toBe('text/x-svelte')
expect(mimeDetector.detectMimeType('layout.astro')).toBe('text/x-astro')
})
it('should detect style preprocessors', () => {
expect(mimeDetector.detectMimeType('styles.scss')).toBe('text/x-scss')
expect(mimeDetector.detectMimeType('theme.sass')).toBe('text/x-sass')
expect(mimeDetector.detectMimeType('main.less')).toBe('text/x-less')
})
})
describe('Data Formats', () => {
it('should detect standard data formats', () => {
expect(mimeDetector.detectMimeType('data.json')).toBe('application/json')
expect(mimeDetector.detectMimeType('config.yaml')).toBe('text/yaml')
expect(mimeDetector.detectMimeType('config.yml')).toBe('text/yaml')
expect(mimeDetector.detectMimeType('data.xml')).toBe('text/xml')
expect(mimeDetector.detectMimeType('data.csv')).toBe('text/csv')
})
it('should detect big data formats', () => {
expect(mimeDetector.detectMimeType('data.parquet')).toBe('application/vnd.apache.parquet')
expect(mimeDetector.detectMimeType('schema.avro')).toBe('application/avro')
expect(mimeDetector.detectMimeType('api.proto')).toBe('text/x-protobuf')
})
})
describe('Office Formats - Microsoft Office', () => {
it('should detect Word documents', () => {
expect(mimeDetector.detectMimeType('document.docx'))
.toBe('application/vnd.openxmlformats-officedocument.wordprocessingml.document')
expect(mimeDetector.detectMimeType('template.dotx'))
.toBe('application/vnd.openxmlformats-officedocument.wordprocessingml.template')
})
it('should detect Excel spreadsheets', () => {
expect(mimeDetector.detectMimeType('spreadsheet.xlsx'))
.toBe('application/vnd.openxmlformats-officedocument.spreadsheetml.sheet')
expect(mimeDetector.detectMimeType('template.xltx'))
.toBe('application/vnd.openxmlformats-officedocument.spreadsheetml.template')
})
it('should detect PowerPoint presentations', () => {
expect(mimeDetector.detectMimeType('presentation.pptx'))
.toBe('application/vnd.openxmlformats-officedocument.presentationml.presentation')
})
})
describe('Office Formats - OpenDocument', () => {
it('should detect OpenDocument formats', () => {
expect(mimeDetector.detectMimeType('document.odt')).toBe('application/vnd.oasis.opendocument.text')
expect(mimeDetector.detectMimeType('spreadsheet.ods')).toBe('application/vnd.oasis.opendocument.spreadsheet')
expect(mimeDetector.detectMimeType('presentation.odp')).toBe('application/vnd.oasis.opendocument.presentation')
})
})
describe('Media Files', () => {
it('should detect image formats', () => {
expect(mimeDetector.detectMimeType('photo.jpg')).toBe('image/jpeg')
expect(mimeDetector.detectMimeType('logo.png')).toBe('image/png')
expect(mimeDetector.detectMimeType('icon.svg')).toBe('image/svg+xml')
expect(mimeDetector.detectMimeType('graphic.webp')).toBe('image/webp')
})
it('should detect video formats', () => {
expect(mimeDetector.detectMimeType('video.mp4')).toBe('video/mp4')
expect(mimeDetector.detectMimeType('movie.mov')).toBe('video/quicktime')
expect(mimeDetector.detectMimeType('clip.webm')).toBe('video/webm')
})
it('should detect audio formats', () => {
expect(mimeDetector.detectMimeType('song.mp3')).toBe('audio/mpeg')
expect(mimeDetector.detectMimeType('sound.wav')).toBe('audio/wav')
expect(mimeDetector.detectMimeType('podcast.ogg')).toBe('audio/ogg')
})
})
describe('Text File Detection', () => {
it('should identify text files correctly', () => {
// Code files
expect(mimeDetector.isTextFile('text/typescript')).toBe(true)
expect(mimeDetector.isTextFile('text/x-python')).toBe(true)
expect(mimeDetector.isTextFile('application/javascript')).toBe(true)
// Data formats
expect(mimeDetector.isTextFile('application/json')).toBe(true)
expect(mimeDetector.isTextFile('text/yaml')).toBe(true)
expect(mimeDetector.isTextFile('text/xml')).toBe(true)
// Binary files
expect(mimeDetector.isTextFile('image/png')).toBe(false)
expect(mimeDetector.isTextFile('video/mp4')).toBe(false)
expect(mimeDetector.isTextFile('application/pdf')).toBe(false)
})
})
describe('Edge Cases', () => {
it('should handle files without extensions', () => {
expect(mimeDetector.detectMimeType('Dockerfile')).toBe('text/x-dockerfile')
expect(mimeDetector.detectMimeType('Makefile')).toBe('text/x-makefile')
})
it('should handle unknown extensions', () => {
expect(mimeDetector.detectMimeType('file.unknown')).toBe('application/octet-stream')
expect(mimeDetector.detectMimeType('random.foobar123')).toBe('application/octet-stream')
})
it('should handle case variations', () => {
expect(mimeDetector.detectMimeType('FILE.TS')).toBe('text/typescript')
expect(mimeDetector.detectMimeType('DoCtUmEnT.JSON')).toBe('application/json')
})
})
describe('Coverage Verification', () => {
it('should handle 40+ file types from mime library', () => {
// Standard web types (from mime library)
expect(mimeDetector.detectMimeType('page.html')).toBe('text/html')
expect(mimeDetector.detectMimeType('style.css')).toBe('text/css')
expect(mimeDetector.detectMimeType('doc.pdf')).toBe('application/pdf')
expect(mimeDetector.detectMimeType('archive.zip')).toBe('application/zip')
expect(mimeDetector.detectMimeType('data.tar')).toBe('application/x-tar')
})
it('should handle 50+ custom types', () => {
// All custom types should be defined
const customTypes = [
['.bash', 'text/x-shellscript'],
['.kt', 'text/x-kotlin'],
['.swift', 'text/x-swift'],
['.dart', 'text/x-dart'],
['.env', 'text/x-env'],
['.vue', 'text/x-vue'],
['.parquet', 'application/vnd.apache.parquet']
]
customTypes.forEach(([ext, expected]) => {
expect(mimeDetector.detectMimeType(`file${ext}`)).toBe(expected)
})
})
})
})