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/queries/asset.job.repository.sql

@@ -285,6 +285,23 @@ from
 where
   "asset"."id" = $2
 
+-- AssetJobRepository.getForOcr
+select
+  "asset"."visibility",
+  (
+    select
+      "asset_file"."path"
+    from
+      "asset_file"
+    where
+      "asset_file"."assetId" = "asset"."id"
+      and "asset_file"."type" = $1
+  ) as "previewFile"
+from
+  "asset"
+where
+  "asset"."id" = $2
+
 -- AssetJobRepository.getForSyncAssets
 select
   "asset"."id",
@@ -483,6 +500,17 @@ where
 order by
   "asset"."fileCreatedAt" desc
 
+-- AssetJobRepository.streamForOcrJob
+select
+  "asset"."id"
+from
+  "asset"
+  inner join "asset_job_status" on "asset_job_status"."assetId" = "asset"."id"
+where
+  "asset_job_status"."ocrAt" is null
+  and "asset"."deletedAt" is null
+  and "asset"."visibility" != $1
+
 -- AssetJobRepository.streamForMigrationJob
 select
   "id"

server/src/queries/ocr.repository.sql

@@ -0,0 +1,68 @@
+-- NOTE: This file is auto generated by ./sql-generator
+
+-- OcrRepository.getById
+select
+  "asset_ocr".*
+from
+  "asset_ocr"
+where
+  "asset_ocr"."id" = $1
+
+-- OcrRepository.getByAssetId
+select
+  "asset_ocr".*
+from
+  "asset_ocr"
+where
+  "asset_ocr"."assetId" = $1
+
+-- OcrRepository.upsert
+with
+  "deleted_ocr" as (
+    delete from "asset_ocr"
+    where
+      "assetId" = $1
+  ),
+  "inserted_ocr" as (
+    insert into
+      "asset_ocr" (
+        "assetId",
+        "x1",
+        "y1",
+        "x2",
+        "y2",
+        "x3",
+        "y3",
+        "x4",
+        "y4",
+        "text",
+        "boxScore",
+        "textScore"
+      )
+    values
+      (
+        $2,
+        $3,
+        $4,
+        $5,
+        $6,
+        $7,
+        $8,
+        $9,
+        $10,
+        $11,
+        $12,
+        $13
+      )
+  ),
+  "inserted_search" as (
+    insert into
+      "ocr_search" ("assetId", "text")
+    values
+      ($14, $15)
+    on conflict ("assetId") do update
+    set
+      "text" = "excluded"."text"
+  )
+select
+  1 as "dummy"