Files
OCR/backend/database.py

82 lines
2.7 KiB
Python

import os
import urllib.parse
from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker, relationship
from sqlalchemy.dialects.postgresql import JSONB
from sqlalchemy.sql import func
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
DB_USER = os.getenv("DB_USER")
DB_PASSWORD = os.getenv("DB_PASSWORD")
DB_HOST = os.getenv("DB_HOST")
DB_PORT = os.getenv("DB_PORT")
DB_NAME = os.getenv("DB_NAME")
encoded_user = urllib.parse.quote_plus(DB_USER)
encoded_password = urllib.parse.quote_plus(DB_PASSWORD)
# SQLAlchemy Database URL
DATABASE_URL = f"postgresql://{encoded_user}:{encoded_password}@{DB_HOST}:{DB_PORT}/{DB_NAME}"
engine = create_engine(DATABASE_URL)
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
Base = declarative_base()
class Email(Base):
__tablename__ = "emails"
id = Column(Integer, primary_key=True, index=True)
subject = Column(String, index=True)
sender = Column(String, index=True)
body = Column(Text)
received_date = Column(DateTime)
is_read = Column(Boolean, default=False)
attachments = relationship("Attachment", back_populates="email")
class Attachment(Base):
__tablename__ = "attachments"
id = Column(Integer, primary_key=True, index=True)
email_id = Column(Integer, ForeignKey("emails.id"))
filename = Column(String)
content_type = Column(String)
file_path = Column(String, nullable=True) # Path to file on disk
file_content = Column(LargeBinary, nullable=True) # Stored in DB (for small files)
email = relationship("Email", back_populates="attachments")
class Vendor(Base):
__tablename__ = "vendors"
id = Column(Integer, primary_key=True, index=True)
name = Column(String, unique=True, index=True)
default_model = Column(String, default="text") # 'text' (Gemma) or 'vision' (Qwen)
created_at = Column(DateTime(timezone=True), server_default=func.now())
documents = relationship("Document", back_populates="vendor")
class Document(Base):
__tablename__ = "documents"
id = Column(Integer, primary_key=True, index=True)
vendor_id = Column(Integer, ForeignKey("vendors.id"), nullable=True)
filename = Column(String)
upload_date = Column(DateTime(timezone=True), server_default=func.now())
status = Column(String, default="pending") # pending, verified
processed_data = Column(JSONB) # The final verified JSON
vendor = relationship("Vendor", back_populates="documents")
def get_db():
db = SessionLocal()
try:
yield db
finally:
db.close()