Akiba So
72428dc075
Bug fixes (Flutter): - Wrap multi-statement DB writes (insert/update/delete note, deleteDocument, deletePageData, OCR FTS merge, migrations) in transactions to prevent data loss on interruption and a read-modify-write FTS race. - Fix PdfDocument leaks on exception (try/finally dispose) and preserve image aspect ratio when stamping images onto PDF pages. - Guard file-picker against empty selection (was .single -> crash). - Fix eraser ConcurrentModificationError and unmodifiable-list crash on PDF pages; capture page synchronously on save to stop wrong-page data loss. - Fix Riverpod DB-not-ready races, broken pull-to-refresh, settings load race, and search N+1; transform stored annotations on PDF page rotation. - Normalize pen pressure for devices without a pressure range. - PPT: single source of truth for slide strokes so ink displays and exports. UI/UX: - Material 3 typography, theme-aware colors (dark-mode fixes), hover cursors and right-click/visible actions on desktop, keyboard shortcuts (undo/redo/ save/find), toolbar overflow handling, friendlier empty states, semantic OCR status badges, relative timestamps, 1-based page indicators, large-deck PPT navigation, and a scratchpad-scope label in split view. Server (optional backend): - Persist JWT secret (was per-process random), block path traversal in storage, fix CORS '*'+credentials, add OCR job ownership checks, last-writer-wins sync guard, constant-time login, and split out heavy OCR deps so the API/tests run without them. CI: Gitea workflows for format+analyze+test (Linux, system sqlite) and a Windows release build; pristine `flutter analyze`, all Flutter and server tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
100 lines
3.0 KiB
Python
100 lines
3.0 KiB
Python
"""OCR router for BadNote."""
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, status
|
|
|
|
from ..auth import get_current_user
|
|
from ..database import get_db
|
|
from ..models import OcrJobRequest, OcrJobStatus, OcrResult
|
|
from ..ocr import queue as job_queue
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
@router.post("/process", status_code=status.HTTP_201_CREATED)
|
|
async def submit_ocr_job(
|
|
body: OcrJobRequest,
|
|
user_id: str = Depends(get_current_user),
|
|
) -> dict:
|
|
"""Enqueue an OCR job."""
|
|
job_data: dict = {
|
|
"user_id": user_id,
|
|
"note_id": body.note_id,
|
|
"document_id": body.document_id,
|
|
"page_number": body.page_number,
|
|
}
|
|
job_id = job_queue.enqueue(job_data)
|
|
return {"job_id": job_id}
|
|
|
|
|
|
@router.get("/status/{job_id}", response_model=OcrJobStatus)
|
|
async def get_job_status(
|
|
job_id: str,
|
|
user_id: str = Depends(get_current_user),
|
|
) -> OcrJobStatus:
|
|
"""Get OCR job status and result."""
|
|
job = job_queue.get_status(job_id)
|
|
# Treat jobs owned by another user as not found to avoid leaking their data.
|
|
if job is None or job.get("user_id") != user_id:
|
|
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Job not found")
|
|
|
|
return OcrJobStatus(
|
|
id=job["id"],
|
|
status=job["status"],
|
|
result_text=job.get("result_text"),
|
|
error_message=job.get("error_message"),
|
|
created_at=job["created_at"],
|
|
completed_at=job.get("completed_at"),
|
|
)
|
|
|
|
|
|
@router.get("/results/{note_id}", response_model=list[OcrResult])
|
|
async def get_ocr_results(
|
|
note_id: str,
|
|
user_id: str = Depends(get_current_user),
|
|
) -> list[OcrResult]:
|
|
"""Get all OCR results for a note."""
|
|
jobs = [
|
|
j for j in job_queue.get_jobs_for_note(note_id) if j.get("user_id") == user_id
|
|
]
|
|
return [
|
|
OcrResult(
|
|
id=j["id"],
|
|
note_id=j.get("note_id"),
|
|
document_id=j.get("document_id"),
|
|
page_number=j.get("page_number"),
|
|
status=j["status"],
|
|
result_text=j.get("result_text"),
|
|
error_message=j.get("error_message"),
|
|
created_at=j["created_at"],
|
|
completed_at=j.get("completed_at"),
|
|
)
|
|
for j in jobs
|
|
]
|
|
|
|
|
|
@router.get("/results/document/{document_id}", response_model=list[OcrResult])
|
|
async def get_document_ocr_results(
|
|
document_id: str,
|
|
user_id: str = Depends(get_current_user),
|
|
) -> list[OcrResult]:
|
|
"""Get all OCR results for a document."""
|
|
jobs = [
|
|
j
|
|
for j in job_queue.get_jobs_for_document(document_id)
|
|
if j.get("user_id") == user_id
|
|
]
|
|
return [
|
|
OcrResult(
|
|
id=j["id"],
|
|
note_id=j.get("note_id"),
|
|
document_id=j.get("document_id"),
|
|
page_number=j.get("page_number"),
|
|
status=j["status"],
|
|
result_text=j.get("result_text"),
|
|
error_message=j.get("error_message"),
|
|
created_at=j["created_at"],
|
|
completed_at=j.get("completed_at"),
|
|
)
|
|
for j in jobs
|
|
]
|