feat(translation): add model, config, task, API, and UI for default document language translation

- Add detected_language, default_language_text, default_language_code columns to FileRecord
- Add default_document_language column to UserProfile
- Add DEFAULT_DOCUMENT_LANGUAGE config setting (defaults to "en")
- Create translate_to_default_language Celery task
- Integrate translation trigger into embed_metadata_into_pdf pipeline
- Add /api/files/{id}/translate and /api/files/{id}/translation/default API endpoints
- Add /files/{id}/text/default-language view endpoint
- Update file_view.html with translation sections (default language, on-the-fly)
- Add translation keys to en.json
- Create Alembic migration 036
- Update .env.demo

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-16 11:54:13 +00:00
parent ff1fde5e48
commit 3a221a62cd
11 changed files with 697 additions and 1 deletions
+28
View File
@@ -832,6 +832,34 @@ def get_processed_text(request: Request, file_id: int, db: Session = Depends(get
)
@router.get("/files/{file_id}/text/default-language")
@require_login
def get_default_language_text(request: Request, file_id: int, db: Session = Depends(get_db)):
"""Return the persisted default-language translation for the file view."""
from fastapi import status
from fastapi.responses import JSONResponse
from app.models import FileRecord
file_record = db.query(FileRecord).filter(FileRecord.id == file_id).first()
if not file_record:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=_FILE_NOT_FOUND)
if not file_record.default_language_text:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="No default-language translation available",
)
return JSONResponse(
content={
"text": file_record.default_language_text,
"language_code": file_record.default_language_code,
"detected_language": file_record.detected_language,
}
)
@router.get("/duplicates")
@require_login
def duplicates_page(