* 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

@ -19,6 +19,7 @@ class SystemConfigJobDto {
required this.metadataExtraction,
required this.migration,
required this.notifications,
required this.ocr,
required this.search,
required this.sidecar,
required this.smartSearch,
@ -38,6 +39,8 @@ class SystemConfigJobDto {
JobSettingsDto notifications;
JobSettingsDto ocr;
JobSettingsDto search;
JobSettingsDto sidecar;
@ -56,6 +59,7 @@ class SystemConfigJobDto {
other.metadataExtraction == metadataExtraction &&
other.migration == migration &&
other.notifications == notifications &&
other.ocr == ocr &&
other.search == search &&
other.sidecar == sidecar &&
other.smartSearch == smartSearch &&
@ -71,6 +75,7 @@ class SystemConfigJobDto {
(metadataExtraction.hashCode) +
(migration.hashCode) +
(notifications.hashCode) +
(ocr.hashCode) +
(search.hashCode) +
(sidecar.hashCode) +
(smartSearch.hashCode) +
@ -78,7 +83,7 @@ class SystemConfigJobDto {
(videoConversion.hashCode);
@override
String toString() => 'SystemConfigJobDto[backgroundTask=$backgroundTask, faceDetection=$faceDetection, library_=$library_, metadataExtraction=$metadataExtraction, migration=$migration, notifications=$notifications, search=$search, sidecar=$sidecar, smartSearch=$smartSearch, thumbnailGeneration=$thumbnailGeneration, videoConversion=$videoConversion]';
String toString() => 'SystemConfigJobDto[backgroundTask=$backgroundTask, faceDetection=$faceDetection, library_=$library_, metadataExtraction=$metadataExtraction, migration=$migration, notifications=$notifications, ocr=$ocr, search=$search, sidecar=$sidecar, smartSearch=$smartSearch, thumbnailGeneration=$thumbnailGeneration, videoConversion=$videoConversion]';
Map<String, dynamic> toJson() {
final json = <String, dynamic>{};
@ -88,6 +93,7 @@ class SystemConfigJobDto {
json[r'metadataExtraction'] = this.metadataExtraction;
json[r'migration'] = this.migration;
json[r'notifications'] = this.notifications;
json[r'ocr'] = this.ocr;
json[r'search'] = this.search;
json[r'sidecar'] = this.sidecar;
json[r'smartSearch'] = this.smartSearch;
@ -111,6 +117,7 @@ class SystemConfigJobDto {
metadataExtraction: JobSettingsDto.fromJson(json[r'metadataExtraction'])!,
migration: JobSettingsDto.fromJson(json[r'migration'])!,
notifications: JobSettingsDto.fromJson(json[r'notifications'])!,
ocr: JobSettingsDto.fromJson(json[r'ocr'])!,
search: JobSettingsDto.fromJson(json[r'search'])!,
sidecar: JobSettingsDto.fromJson(json[r'sidecar'])!,
smartSearch: JobSettingsDto.fromJson(json[r'smartSearch'])!,
@ -169,6 +176,7 @@ class SystemConfigJobDto {
'metadataExtraction',
'migration',
'notifications',
'ocr',
'search',
'sidecar',
'smartSearch',