Marius Mutu
9f06482681
- Add adaptive 3-step OCR pipeline with early exit when all 5 fields found - Add pattern for "C. I. F." with spaces (OCR artifact from PaddleOCR) - Add pattern for YYYY. MM. DD date format with spaces (OMV/Petrom receipts) - Add pattern for "OTAL TAXE" with T cut off and reversed amount position - Make TVA rate pattern more flexible (code letter optional, handle "-21%") - Replace logger.info with print(flush=True) for better debugging visibility - Improve OCRPreview.vue to show extraction progress and raw OCR text 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
111 lines
2.9 KiB
Python
111 lines
2.9 KiB
Python
"""FastAPI application entry point for Data Entry App."""
|
|
|
|
import sys
|
|
import logging
|
|
import threading
|
|
from pathlib import Path
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI
|
|
|
|
# Configure logging to show INFO level messages
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
|
datefmt='%H:%M:%S'
|
|
)
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.staticfiles import StaticFiles
|
|
|
|
# Add shared modules to path
|
|
project_root = Path(__file__).parent.parent.parent.parent
|
|
sys.path.insert(0, str(project_root / "shared"))
|
|
|
|
from app.config import settings
|
|
from app.db.database import init_db
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
"""Application lifespan - startup and shutdown events."""
|
|
# Startup
|
|
print(f"Starting {settings.app_name} v{settings.app_version}")
|
|
|
|
# Initialize database
|
|
await init_db()
|
|
print("Database initialized")
|
|
|
|
# Ensure upload directory exists
|
|
settings.upload_path_resolved
|
|
print(f"Upload path: {settings.upload_path_resolved}")
|
|
|
|
# Pre-initialize OCR engine in background (PaddleOCR takes 15-20s)
|
|
def init_ocr_background():
|
|
try:
|
|
from app.services.ocr_service import ocr_service
|
|
ocr_service.ocr_engine._init_paddle_lazy()
|
|
print("OCR engine ready")
|
|
except Exception as e:
|
|
print(f"Warning: OCR engine pre-load failed: {e}")
|
|
|
|
print("Starting OCR engine pre-load (background)...")
|
|
threading.Thread(target=init_ocr_background, daemon=True).start()
|
|
|
|
yield
|
|
|
|
# Shutdown
|
|
print("Shutting down...")
|
|
|
|
|
|
# Create FastAPI app
|
|
app = FastAPI(
|
|
title=settings.app_name,
|
|
version=settings.app_version,
|
|
description="API pentru introducere bonuri fiscale cu workflow de aprobare",
|
|
lifespan=lifespan,
|
|
)
|
|
|
|
# CORS middleware
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=settings.cors_origins_list,
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
# Mount static files for uploads (optional - can serve through nginx in prod)
|
|
uploads_path = Path(settings.upload_path)
|
|
if uploads_path.exists():
|
|
app.mount("/uploads", StaticFiles(directory=str(uploads_path)), name="uploads")
|
|
|
|
|
|
# Health check endpoint
|
|
@app.get("/health")
|
|
async def health_check():
|
|
"""Health check endpoint."""
|
|
return {
|
|
"status": "healthy",
|
|
"app": settings.app_name,
|
|
"version": settings.app_version,
|
|
}
|
|
|
|
|
|
# Import and include routers
|
|
from app.routers import receipts, ocr
|
|
|
|
app.include_router(receipts.router, prefix="/api/receipts", tags=["receipts"])
|
|
app.include_router(ocr.router, prefix="/api/ocr", tags=["ocr"])
|
|
|
|
|
|
# Root endpoint
|
|
@app.get("/")
|
|
async def root():
|
|
"""Root endpoint - API information."""
|
|
return {
|
|
"name": settings.app_name,
|
|
"version": settings.app_version,
|
|
"docs": "/docs",
|
|
"health": "/health",
|
|
}
|