Files
immich/server/src/repositories/ocr.repository.ts
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

69 lines
2.4 KiB
TypeScript

import { Injectable } from '@nestjs/common';
import { Insertable, Kysely, sql } from 'kysely';
import { InjectKysely } from 'nestjs-kysely';
import { DummyValue, GenerateSql } from 'src/decorators';
import { DB } from 'src/schema';
import { AssetOcrTable } from 'src/schema/tables/asset-ocr.table';
@Injectable()
export class OcrRepository {
constructor(@InjectKysely() private db: Kysely<DB>) {}
@GenerateSql({ params: [DummyValue.UUID] })
getById(id: string) {
return this.db.selectFrom('asset_ocr').selectAll('asset_ocr').where('asset_ocr.id', '=', id).executeTakeFirst();
}
@GenerateSql({ params: [DummyValue.UUID] })
getByAssetId(id: string) {
return this.db.selectFrom('asset_ocr').selectAll('asset_ocr').where('asset_ocr.assetId', '=', id).execute();
}
deleteAll() {
return this.db.transaction().execute(async (trx: Kysely<DB>) => {
await sql`truncate ${sql.table('asset_ocr')}`.execute(trx);
await sql`truncate ${sql.table('ocr_search')}`.execute(trx);
});
}
@GenerateSql({
params: [
DummyValue.UUID,
[
{
assetId: DummyValue.UUID,
x1: DummyValue.NUMBER,
y1: DummyValue.NUMBER,
x2: DummyValue.NUMBER,
y2: DummyValue.NUMBER,
x3: DummyValue.NUMBER,
y3: DummyValue.NUMBER,
x4: DummyValue.NUMBER,
y4: DummyValue.NUMBER,
text: DummyValue.STRING,
boxScore: DummyValue.NUMBER,
textScore: DummyValue.NUMBER,
},
],
],
})
upsert(assetId: string, ocrDataList: Insertable<AssetOcrTable>[]) {
let query = this.db.with('deleted_ocr', (db) => db.deleteFrom('asset_ocr').where('assetId', '=', assetId));
if (ocrDataList.length > 0) {
const searchText = ocrDataList.map((item) => item.text.trim()).join(' ');
(query as any) = query
.with('inserted_ocr', (db) => db.insertInto('asset_ocr').values(ocrDataList))
.with('inserted_search', (db) =>
db
.insertInto('ocr_search')
.values({ assetId, text: searchText })
.onConflict((oc) => oc.column('assetId').doUpdateSet((eb) => ({ text: eb.ref('excluded.text') }))),
);
} else {
(query as any) = query.with('deleted_search', (db) => db.deleteFrom('ocr_search').where('assetId', '=', assetId));
}
return query.selectNoFrom(sql`1`.as('dummy')).execute();
}
}