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>

server/src/schema/tables/asset-job-status.table.ts

@@ -20,4 +20,7 @@ export class AssetJobStatusTable {
 
   @Column({ type: 'timestamp with time zone', nullable: true })
   thumbnailAt!: Timestamp | null;
+
+  @Column({ type: 'timestamp with time zone', nullable: true })
+  ocrAt!: Timestamp | null;
 }

server/src/schema/tables/asset-ocr.table.ts

@@ -0,0 +1,45 @@
+import { AssetTable } from 'src/schema/tables/asset.table';
+import { Column, ForeignKeyColumn, Generated, PrimaryGeneratedColumn, Table } from 'src/sql-tools';
+
+@Table('asset_ocr')
+export class AssetOcrTable {
+  @PrimaryGeneratedColumn()
+  id!: Generated<string>;
+
+  @ForeignKeyColumn(() => AssetTable, { onDelete: 'CASCADE', onUpdate: 'CASCADE' })
+  assetId!: string;
+
+  // box positions are normalized, with values between 0 and 1
+  @Column({ type: 'real' })
+  x1!: number;
+
+  @Column({ type: 'real' })
+  y1!: number;
+
+  @Column({ type: 'real' })
+  x2!: number;
+
+  @Column({ type: 'real' })
+  y2!: number;
+
+  @Column({ type: 'real' })
+  x3!: number;
+
+  @Column({ type: 'real' })
+  y3!: number;
+
+  @Column({ type: 'real' })
+  x4!: number;
+
+  @Column({ type: 'real' })
+  y4!: number;
+
+  @Column({ type: 'real' })
+  boxScore!: number;
+
+  @Column({ type: 'real' })
+  textScore!: number;
+
+  @Column({ type: 'text' })
+  text!: string;
+}

server/src/schema/tables/ocr-search.table.ts

@@ -0,0 +1,20 @@
+import { AssetTable } from 'src/schema/tables/asset.table';
+import { Column, ForeignKeyColumn, Index, Table } from 'src/sql-tools';
+
+@Table('ocr_search')
+@Index({
+  name: 'idx_ocr_search_text',
+  using: 'gin',
+  expression: 'f_unaccent("text") gin_trgm_ops',
+})
+export class OcrSearchTable {
+  @ForeignKeyColumn(() => AssetTable, {
+    onDelete: 'CASCADE',
+    onUpdate: 'CASCADE',
+    primary: true,
+  })
+  assetId!: string;
+
+  @Column({ type: 'text' })
+  text!: string;
+}