* 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

@ -21,6 +21,7 @@ class ServerFeaturesDto {
required this.map,
required this.oauth,
required this.oauthAutoLaunch,
required this.ocr,
required this.passwordLogin,
required this.reverseGeocoding,
required this.search,
@ -45,6 +46,8 @@ class ServerFeaturesDto {
bool oauthAutoLaunch;
bool ocr;
bool passwordLogin;
bool reverseGeocoding;
@ -67,6 +70,7 @@ class ServerFeaturesDto {
other.map == map &&
other.oauth == oauth &&
other.oauthAutoLaunch == oauthAutoLaunch &&
other.ocr == ocr &&
other.passwordLogin == passwordLogin &&
other.reverseGeocoding == reverseGeocoding &&
other.search == search &&
@ -85,6 +89,7 @@ class ServerFeaturesDto {
(map.hashCode) +
(oauth.hashCode) +
(oauthAutoLaunch.hashCode) +
(ocr.hashCode) +
(passwordLogin.hashCode) +
(reverseGeocoding.hashCode) +
(search.hashCode) +
@ -93,7 +98,7 @@ class ServerFeaturesDto {
(trash.hashCode);
@override
String toString() => 'ServerFeaturesDto[configFile=$configFile, duplicateDetection=$duplicateDetection, email=$email, facialRecognition=$facialRecognition, importFaces=$importFaces, map=$map, oauth=$oauth, oauthAutoLaunch=$oauthAutoLaunch, passwordLogin=$passwordLogin, reverseGeocoding=$reverseGeocoding, search=$search, sidecar=$sidecar, smartSearch=$smartSearch, trash=$trash]';
String toString() => 'ServerFeaturesDto[configFile=$configFile, duplicateDetection=$duplicateDetection, email=$email, facialRecognition=$facialRecognition, importFaces=$importFaces, map=$map, oauth=$oauth, oauthAutoLaunch=$oauthAutoLaunch, ocr=$ocr, passwordLogin=$passwordLogin, reverseGeocoding=$reverseGeocoding, search=$search, sidecar=$sidecar, smartSearch=$smartSearch, trash=$trash]';
Map<String, dynamic> toJson() {
final json = <String, dynamic>{};
@ -105,6 +110,7 @@ class ServerFeaturesDto {
json[r'map'] = this.map;
json[r'oauth'] = this.oauth;
json[r'oauthAutoLaunch'] = this.oauthAutoLaunch;
json[r'ocr'] = this.ocr;
json[r'passwordLogin'] = this.passwordLogin;
json[r'reverseGeocoding'] = this.reverseGeocoding;
json[r'search'] = this.search;
@ -131,6 +137,7 @@ class ServerFeaturesDto {
map: mapValueOfType<bool>(json, r'map')!,
oauth: mapValueOfType<bool>(json, r'oauth')!,
oauthAutoLaunch: mapValueOfType<bool>(json, r'oauthAutoLaunch')!,
ocr: mapValueOfType<bool>(json, r'ocr')!,
passwordLogin: mapValueOfType<bool>(json, r'passwordLogin')!,
reverseGeocoding: mapValueOfType<bool>(json, r'reverseGeocoding')!,
search: mapValueOfType<bool>(json, r'search')!,
@ -192,6 +199,7 @@ class ServerFeaturesDto {
'map',
'oauth',
'oauthAutoLaunch',
'ocr',
'passwordLogin',
'reverseGeocoding',
'search',