* 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

@ -29,6 +29,7 @@ class StatisticsSearchDto {
this.libraryId,
this.make,
this.model,
this.ocr,
this.personIds = const [],
this.rating,
this.state,
@ -135,6 +136,14 @@ class StatisticsSearchDto {
String? model;
///
/// Please note: This property should have been non-nullable! Since the specification file
/// does not include a default value (using the "default:" property), however, the generated
/// source code must fall back to having a nullable type.
/// Consider adding a "default:" property in the specification file to hide this note.
///
String? ocr;
List<String> personIds;
/// Minimum value: -1
@ -233,6 +242,7 @@ class StatisticsSearchDto {
other.libraryId == libraryId &&
other.make == make &&
other.model == model &&
other.ocr == ocr &&
_deepEquality.equals(other.personIds, personIds) &&
other.rating == rating &&
other.state == state &&
@ -265,6 +275,7 @@ class StatisticsSearchDto {
(libraryId == null ? 0 : libraryId!.hashCode) +
(make == null ? 0 : make!.hashCode) +
(model == null ? 0 : model!.hashCode) +
(ocr == null ? 0 : ocr!.hashCode) +
(personIds.hashCode) +
(rating == null ? 0 : rating!.hashCode) +
(state == null ? 0 : state!.hashCode) +
@ -279,7 +290,7 @@ class StatisticsSearchDto {
(visibility == null ? 0 : visibility!.hashCode);
@override
String toString() => 'StatisticsSearchDto[albumIds=$albumIds, city=$city, country=$country, createdAfter=$createdAfter, createdBefore=$createdBefore, description=$description, deviceId=$deviceId, isEncoded=$isEncoded, isFavorite=$isFavorite, isMotion=$isMotion, isNotInAlbum=$isNotInAlbum, isOffline=$isOffline, lensModel=$lensModel, libraryId=$libraryId, make=$make, model=$model, personIds=$personIds, rating=$rating, state=$state, tagIds=$tagIds, takenAfter=$takenAfter, takenBefore=$takenBefore, trashedAfter=$trashedAfter, trashedBefore=$trashedBefore, type=$type, updatedAfter=$updatedAfter, updatedBefore=$updatedBefore, visibility=$visibility]';
String toString() => 'StatisticsSearchDto[albumIds=$albumIds, city=$city, country=$country, createdAfter=$createdAfter, createdBefore=$createdBefore, description=$description, deviceId=$deviceId, isEncoded=$isEncoded, isFavorite=$isFavorite, isMotion=$isMotion, isNotInAlbum=$isNotInAlbum, isOffline=$isOffline, lensModel=$lensModel, libraryId=$libraryId, make=$make, model=$model, ocr=$ocr, personIds=$personIds, rating=$rating, state=$state, tagIds=$tagIds, takenAfter=$takenAfter, takenBefore=$takenBefore, trashedAfter=$trashedAfter, trashedBefore=$trashedBefore, type=$type, updatedAfter=$updatedAfter, updatedBefore=$updatedBefore, visibility=$visibility]';
Map<String, dynamic> toJson() {
final json = <String, dynamic>{};
@ -358,6 +369,11 @@ class StatisticsSearchDto {
json[r'model'] = this.model;
} else {
// json[r'model'] = null;
}
if (this.ocr != null) {
json[r'ocr'] = this.ocr;
} else {
// json[r'ocr'] = null;
}
json[r'personIds'] = this.personIds;
if (this.rating != null) {
@ -445,6 +461,7 @@ class StatisticsSearchDto {
libraryId: mapValueOfType<String>(json, r'libraryId'),
make: mapValueOfType<String>(json, r'make'),
model: mapValueOfType<String>(json, r'model'),
ocr: mapValueOfType<String>(json, r'ocr'),
personIds: json[r'personIds'] is Iterable
? (json[r'personIds'] as Iterable).cast<String>().toList(growable: false)
: const [],