* 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>
This commit is contained in:
Kang 2025-10-27 22:09:55 +08:00 committed by GitHub
parent c666dc6c67
commit 02b29046b3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
90 changed files with 3610 additions and 1722 deletions

View file

@ -27,8 +27,10 @@ import { EmailRepository } from 'src/repositories/email.repository';
import { EventRepository } from 'src/repositories/event.repository';
import { JobRepository } from 'src/repositories/job.repository';
import { LoggingRepository } from 'src/repositories/logging.repository';
import { MachineLearningRepository } from 'src/repositories/machine-learning.repository';
import { MemoryRepository } from 'src/repositories/memory.repository';
import { NotificationRepository } from 'src/repositories/notification.repository';
import { OcrRepository } from 'src/repositories/ocr.repository';
import { PartnerRepository } from 'src/repositories/partner.repository';
import { PersonRepository } from 'src/repositories/person.repository';
import { SearchRepository } from 'src/repositories/search.repository';
@ -47,6 +49,7 @@ import { VersionHistoryRepository } from 'src/repositories/version-history.repos
import { DB } from 'src/schema';
import { AlbumTable } from 'src/schema/tables/album.table';
import { AssetExifTable } from 'src/schema/tables/asset-exif.table';
import { AssetFileTable } from 'src/schema/tables/asset-file.table';
import { AssetJobStatusTable } from 'src/schema/tables/asset-job-status.table';
import { AssetTable } from 'src/schema/tables/asset.table';
import { FaceSearchTable } from 'src/schema/tables/face-search.table';
@ -169,6 +172,11 @@ export class MediumTestContext<S extends BaseService = BaseService> {
return { asset, result };
}
async newAssetFile(dto: Insertable<AssetFileTable>) {
const result = await this.get(AssetRepository).upsertFile(dto);
return { result };
}
async newAssetFace(dto: Partial<Insertable<AssetFace>> & { assetId: string }) {
const assetFace = mediumFactory.assetFaceInsert(dto);
const result = await this.get(PersonRepository).createAssetFace(assetFace);
@ -307,6 +315,7 @@ const newRealRepository = <T>(key: ClassConstructor<T>, db: Kysely<DB>): T => {
case AssetJobRepository:
case MemoryRepository:
case NotificationRepository:
case OcrRepository:
case PartnerRepository:
case PersonRepository:
case SearchRepository:
@ -359,6 +368,7 @@ const newMockRepository = <T>(key: ClassConstructor<T>) => {
case CryptoRepository:
case MemoryRepository:
case NotificationRepository:
case OcrRepository:
case PartnerRepository:
case PersonRepository:
case SessionRepository:
@ -407,6 +417,10 @@ const newMockRepository = <T>(key: ClassConstructor<T>) => {
return automock(LoggingRepository, { args: [undefined, configMock], strict: false });
}
case MachineLearningRepository: {
return automock(MachineLearningRepository, { args: [{ setContext: () => {} }] });
}
case StorageRepository: {
return automock(StorageRepository, { args: [{ setContext: () => {} }] });
}