marcel/familienarchiv
1
0
Fork 0
Code Issues 125 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(c4): fix 3d OCR — route transcription/annotation through domain services

Browse Source 
OcrAsyncRunner injects TranscriptionService and AnnotationService; it only
accesses the DB directly for OcrJob state (OcrJobRepository). The previous
Rel arrow incorrectly showed direct JDBC access for transcription blocks and
annotations, contradicting the component description.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-06 11:25:14 +02:00
parent 83c3d85b00
commit 35d82814a6
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/architecture/c4-diagrams.md
View File

@@ -277,6 +277,9 @@ C4Component
Component(ocrTraining, "OcrTrainingService", "Spring Service", "Orchestrates model training: exports training data as ZIP, calls Python /train or /segtrain, persists training metrics in OcrTrainingRunRepository.") Component(ocrTraining, "OcrTrainingService", "Spring Service", "Orchestrates model training: exports training data as ZIP, calls Python /train or /segtrain, persists training metrics in OcrTrainingRunRepository.")
} }
Component(transcriptionSvc, "TranscriptionService", "Spring Service", "See diagram 3b.2. Called by OcrAsyncRunner to persist transcription blocks per page.")
Component(annotationSvc, "AnnotationService", "Spring Service", "See diagram 3b.2. Called by OcrAsyncRunner to persist OCR-generated annotation regions per page.")
Rel(frontend, ocrCtrl, "OCR trigger, status, and progress requests", "HTTP / JSON / SSE") Rel(frontend, ocrCtrl, "OCR trigger, status, and progress requests", "HTTP / JSON / SSE")
Rel(ocrCtrl, ocrSvc, "Single-document jobs", "") Rel(ocrCtrl, ocrSvc, "Single-document jobs", "")
Rel(ocrCtrl, ocrBatch, "Batch jobs", "") Rel(ocrCtrl, ocrBatch, "Batch jobs", "")
@@ -286,7 +289,9 @@ C4Component
Rel(ocrAsync, ocrClient, "Streams OCR results page by page", "HTTP / NDJSON") Rel(ocrAsync, ocrClient, "Streams OCR results page by page", "HTTP / NDJSON")
Rel(ocrTraining, ocrClient, "Sends training data ZIP", "HTTP / multipart") Rel(ocrTraining, ocrClient, "Sends training data ZIP", "HTTP / multipart")
Rel(ocrClient, ocrPy, "POST /ocr/stream, /train, /segtrain, /train-sender", "HTTP / REST") Rel(ocrClient, ocrPy, "POST /ocr/stream, /train, /segtrain, /train-sender", "HTTP / REST")
Rel(ocrAsync, db, "Reads / writes job state, transcription blocks, annotations", "JDBC") Rel(ocrAsync, transcriptionSvc, "Saves transcription blocks per page", "")
Rel(ocrAsync, annotationSvc, "Saves annotation regions per page", "")
Rel(ocrAsync, db, "Reads / writes OCR job state", "JDBC")
Rel(ocrAsync, minio, "Generates presigned URLs for PDF fetch", "S3 API") Rel(ocrAsync, minio, "Generates presigned URLs for PDF fetch", "S3 API")
Rel(ocrPy, minio, "Fetches PDF via presigned URL", "HTTP / S3 presigned") Rel(ocrPy, minio, "Fetches PDF via presigned URL", "HTTP / S3 presigned")
Rel(ocrTraining, db, "Persists training run metrics", "JDBC") Rel(ocrTraining, db, "Persists training run metrics", "JDBC")