Files
immich/server/src/services/ocr.service.spec.ts
T
Kang 02b29046b3 feat: ocr (#18836)
* feat: add OCR functionality and related configurations

* chore: update labeler configuration for machine learning files

* feat(i18n): enhance OCR model descriptions and add orientation classification and unwarping features

* chore: update Dockerfile to include ccache for improved build performance

* feat(ocr): enhance OCR model configuration with orientation classification and unwarping options, update PaddleOCR integration, and improve response structure

* refactor(ocr): remove OCR_CLEANUP job from enum and type definitions

* refactor(ocr): remove obsolete OCR entity and migration files, and update asset job status and schema to accommodate new OCR table structure

* refactor(ocr): update OCR schema and response structure to use individual coordinates instead of bounding box, and adjust related service and repository files

* feat: enhance OCR configuration and functionality

- Updated OCR settings to include minimum detection box score, minimum detection score, and minimum recognition score.
- Refactored PaddleOCRecognizer to utilize new scoring parameters.
- Introduced new database tables for asset OCR data and search functionality.
- Modified related services and repositories to support the new OCR features.
- Updated translations for improved clarity in settings UI.

* sql changes

* use rapidocr

* change dto

* update web

* update lock

* update api

* store positions as normalized floats

* match column order in db

* update admin ui settings descriptions

fix max resolution key

set min threshold to 0.1

fix bind

* apply config correctly, adjust defaults

* unnecessary model type

* unnecessary sources

* fix(ocr): switch RapidOCR lang type from LangDet to LangRec

* fix(ocr): expose lang_type (LangRec.CH) and font_path on OcrOptions for RapidOCR

* fix(ocr): make OCR text search case- and accent-insensitive using ILIKE + unaccent

* fix(ocr): add OCR search fields

* fix: Add OCR database migration and update ML prediction logic.

* trigrams are already case insensitive

* add tests

* format

* update migrations

* wrong uuid function

* linting

* maybe fix medium tests

* formatting

* fix weblate check

* openapi

* sql

* minor fixes

* maybe fix medium tests part 2

* passing medium tests

* format web

* readd sql

* format dart

* disabled in e2e

* chore: translation ordering

---------

Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
2025-10-27 14:09:55 +00:00

178 lines
5.9 KiB
TypeScript

import { AssetVisibility, ImmichWorker, JobName, JobStatus } from 'src/enum';
import { OcrService } from 'src/services/ocr.service';
import { assetStub } from 'test/fixtures/asset.stub';
import { systemConfigStub } from 'test/fixtures/system-config.stub';
import { makeStream, newTestService, ServiceMocks } from 'test/utils';
describe(OcrService.name, () => {
let sut: OcrService;
let mocks: ServiceMocks;
beforeEach(() => {
({ sut, mocks } = newTestService(OcrService));
mocks.config.getWorker.mockReturnValue(ImmichWorker.Microservices);
});
it('should work', () => {
expect(sut).toBeDefined();
});
describe('handleQueueOcr', () => {
it('should do nothing if machine learning is disabled', async () => {
mocks.systemMetadata.get.mockResolvedValue(systemConfigStub.machineLearningDisabled);
await sut.handleQueueOcr({ force: false });
expect(mocks.database.setDimensionSize).not.toHaveBeenCalled();
});
it('should queue the assets without ocr', async () => {
mocks.assetJob.streamForOcrJob.mockReturnValue(makeStream([assetStub.image]));
await sut.handleQueueOcr({ force: false });
expect(mocks.job.queueAll).toHaveBeenCalledWith([{ name: JobName.Ocr, data: { id: assetStub.image.id } }]);
expect(mocks.assetJob.streamForOcrJob).toHaveBeenCalledWith(false);
});
it('should queue all the assets', async () => {
mocks.assetJob.streamForOcrJob.mockReturnValue(makeStream([assetStub.image]));
await sut.handleQueueOcr({ force: true });
expect(mocks.job.queueAll).toHaveBeenCalledWith([{ name: JobName.Ocr, data: { id: assetStub.image.id } }]);
expect(mocks.assetJob.streamForOcrJob).toHaveBeenCalledWith(true);
});
});
describe('handleOcr', () => {
it('should do nothing if machine learning is disabled', async () => {
mocks.systemMetadata.get.mockResolvedValue(systemConfigStub.machineLearningDisabled);
expect(await sut.handleOcr({ id: '123' })).toEqual(JobStatus.Skipped);
expect(mocks.asset.getByIds).not.toHaveBeenCalled();
expect(mocks.machineLearning.encodeImage).not.toHaveBeenCalled();
});
it('should skip assets without a resize path', async () => {
mocks.assetJob.getForOcr.mockResolvedValue({ visibility: AssetVisibility.Timeline, previewFile: null });
expect(await sut.handleOcr({ id: assetStub.noResizePath.id })).toEqual(JobStatus.Failed);
expect(mocks.ocr.upsert).not.toHaveBeenCalled();
expect(mocks.machineLearning.ocr).not.toHaveBeenCalled();
});
it('should save the returned objects', async () => {
mocks.machineLearning.ocr.mockResolvedValue({
box: [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160],
boxScore: [0.9, 0.8],
text: ['One Two Three', 'Four Five'],
textScore: [0.95, 0.85],
});
mocks.assetJob.getForOcr.mockResolvedValue({
visibility: AssetVisibility.Timeline,
previewFile: assetStub.image.files[1].path,
});
expect(await sut.handleOcr({ id: assetStub.image.id })).toEqual(JobStatus.Success);
expect(mocks.machineLearning.ocr).toHaveBeenCalledWith(
'/uploads/user-id/thumbs/path.jpg',
expect.objectContaining({
modelName: 'PP-OCRv5_mobile',
minDetectionScore: 0.5,
minRecognitionScore: 0.8,
maxResolution: 736,
}),
);
expect(mocks.ocr.upsert).toHaveBeenCalledWith(assetStub.image.id, [
{
assetId: assetStub.image.id,
boxScore: 0.9,
text: 'One Two Three',
textScore: 0.95,
x1: 10,
y1: 20,
x2: 30,
y2: 40,
x3: 50,
y3: 60,
x4: 70,
y4: 80,
},
{
assetId: assetStub.image.id,
boxScore: 0.8,
text: 'Four Five',
textScore: 0.85,
x1: 90,
y1: 100,
x2: 110,
y2: 120,
x3: 130,
y3: 140,
x4: 150,
y4: 160,
},
]);
});
it('should apply config settings', async () => {
mocks.systemMetadata.get.mockResolvedValue({
machineLearning: {
enabled: true,
ocr: {
modelName: 'PP-OCRv5_server',
enabled: true,
minDetectionScore: 0.8,
minRecognitionScore: 0.9,
maxResolution: 1500,
},
},
});
mocks.machineLearning.ocr.mockResolvedValue({ box: [], boxScore: [], text: [], textScore: [] });
mocks.assetJob.getForOcr.mockResolvedValue({
visibility: AssetVisibility.Timeline,
previewFile: assetStub.image.files[1].path,
});
expect(await sut.handleOcr({ id: assetStub.image.id })).toEqual(JobStatus.Success);
expect(mocks.machineLearning.ocr).toHaveBeenCalledWith(
'/uploads/user-id/thumbs/path.jpg',
expect.objectContaining({
modelName: 'PP-OCRv5_server',
minDetectionScore: 0.8,
minRecognitionScore: 0.9,
maxResolution: 1500,
}),
);
expect(mocks.ocr.upsert).toHaveBeenCalledWith(assetStub.image.id, []);
});
it('should skip invisible assets', async () => {
mocks.assetJob.getForOcr.mockResolvedValue({
visibility: AssetVisibility.Hidden,
previewFile: assetStub.image.files[1].path,
});
expect(await sut.handleOcr({ id: assetStub.livePhotoMotionAsset.id })).toEqual(JobStatus.Skipped);
expect(mocks.machineLearning.ocr).not.toHaveBeenCalled();
expect(mocks.ocr.upsert).not.toHaveBeenCalled();
});
it('should fail if asset could not be found', async () => {
mocks.assetJob.getForOcr.mockResolvedValue(void 0);
expect(await sut.handleOcr({ id: assetStub.image.id })).toEqual(JobStatus.Failed);
expect(mocks.machineLearning.ocr).not.toHaveBeenCalled();
expect(mocks.ocr.upsert).not.toHaveBeenCalled();
});
});
});