Files
BadNote/server/badnote_server/routers/v1_ocr_router.py
Akiba So 198da00ecd
All checks were successful
CI / Windows build (push) Successful in 7m47s
feat: vault-aligned server v1 + UX polish
Redesign the optional FastAPI companion around vault files (manifest /
PUT/GET/DELETE + OCR jobs) instead of legacy strokes_json notes. Wire a
client Server settings panel for health/login. Polish shell UX: l10n for
settings/home/board, sticky-board empty state, and a narrow-screen
diagnostics FAB.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-05 19:04:48 +08:00

75 lines
2.3 KiB
Python

"""v1 OCR job API — upload ink raster, poll status, fetch text."""
from __future__ import annotations
import os
import uuid
from datetime import datetime, timezone
from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile, status
from ..auth import get_current_user
from ..config import settings
from ..ocr import queue as ocr_queue
router = APIRouter()
@router.post("/jobs", status_code=status.HTTP_202_ACCEPTED)
async def create_ocr_job(
image: UploadFile = File(...),
source_path: str = Form(""),
page_index: int = Form(0),
user_id: str = Depends(get_current_user),
) -> dict:
"""Enqueue an OCR job from an uploaded PNG/JPEG of handwriting."""
job_id = str(uuid.uuid4())
blob_dir = os.path.join(settings.storage_path, "ocr_blobs", user_id)
os.makedirs(blob_dir, exist_ok=True)
ext = os.path.splitext(image.filename or "ink.png")[1] or ".png"
blob_path = os.path.join(blob_dir, f"{job_id}{ext}")
data = await image.read()
if not data:
raise HTTPException(status.HTTP_400_BAD_REQUEST, detail="empty image")
with open(blob_path, "wb") as f:
f.write(data)
ocr_queue.enqueue(
{
"id": job_id,
"user_id": user_id,
"source_path": source_path,
"note_id": source_path or job_id,
"page_index": page_index,
"image_path": blob_path,
"created_at": datetime.now(timezone.utc).isoformat(),
}
)
return {
"job_id": job_id,
"status": "pending",
"source_path": source_path,
"page_index": page_index,
}
@router.get("/jobs/{job_id}")
async def get_ocr_job(
job_id: str,
user_id: str = Depends(get_current_user),
) -> dict:
job = ocr_queue.get_status(job_id)
if job is None:
raise HTTPException(status.HTTP_404_NOT_FOUND, detail="job not found")
if job.get("user_id") not in (None, user_id):
raise HTTPException(status.HTTP_403_FORBIDDEN, detail="forbidden")
return {
"job_id": job_id,
"status": job.get("status"),
"result": job.get("result_text") or job.get("result") or job.get("text"),
"error": job.get("error_message") or job.get("error"),
"source_path": job.get("source_path"),
"page_index": job.get("page_index"),
}