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>
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
"""Background OCR worker for BadNote.
|
|
|
|
Polls the file-based queue and processes jobs using the OcrEngine.
|
|
"""
|
|
|
|
import asyncio
|
|
import logging
|
|
import os
|
|
|
|
from ..config import settings
|
|
from .engine import OcrEngine
|
|
from . import queue as job_queue
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
async def run_worker(poll_interval: int = 5) -> None:
|
|
"""Poll the queue and process OCR jobs.
|
|
|
|
Loads images from the job's image_path and runs them through EasyOCR.
|
|
"""
|
|
# Ensure queue dirs exist
|
|
for subdir in ("pending", "processing", "done", "failed"):
|
|
os.makedirs(os.path.join(settings.queue_path, subdir), exist_ok=True)
|
|
|
|
engine = OcrEngine()
|
|
logger.info("OCR worker started (poll_interval=%ds)", poll_interval)
|
|
|
|
while True:
|
|
job = job_queue.dequeue()
|
|
if job is not None:
|
|
job_id = job["id"]
|
|
logger.info("Processing OCR job %s", job_id)
|
|
try:
|
|
# Read image from the path specified in the job
|
|
image_path = job.get("image_path", "")
|
|
if image_path and os.path.exists(image_path):
|
|
result = await engine.recognize_file(image_path)
|
|
else:
|
|
# Fall back to image_bytes if provided inline
|
|
image_bytes = job.get("image_bytes", b"")
|
|
if isinstance(image_bytes, str):
|
|
import base64
|
|
image_bytes = base64.b64decode(image_bytes)
|
|
result = await engine.recognize(image_bytes)
|
|
|
|
job_queue.complete(job_id, result)
|
|
logger.info("OCR job %s completed: %d chars", job_id, len(result))
|
|
except Exception as exc:
|
|
logger.error("OCR job %s failed: %s", job_id, exc)
|
|
job_queue.fail(job_id, str(exc))
|
|
else:
|
|
await asyncio.sleep(poll_interval)
|
|
|
|
|
|
def main() -> None:
|
|
"""Entry point for `python -m badnote_server.ocr.worker`."""
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
|
)
|
|
try:
|
|
asyncio.run(run_worker())
|
|
except KeyboardInterrupt:
|
|
logger.info("OCR worker stopped")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|