import os import urllib.parse from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary, Enum as SqlEnum from sqlalchemy.dialects.postgresql import JSONB from sqlalchemy.ext.declarative import declarative_base from sqlalchemy.orm import sessionmaker, relationship from dotenv import load_dotenv # Load environment variables load_dotenv() DB_USER = os.getenv("DB_USER", "postgres") DB_PASSWORD = os.getenv("DB_PASSWORD", "password") DB_HOST = os.getenv("DB_HOST", "localhost") DB_PORT = os.getenv("DB_PORT", "5432") DB_NAME = os.getenv("DB_NAME", "ocr_db") 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 Vendor(Base): __tablename__ = "vendors" id = Column(Integer, primary_key=True, index=True) name = Column(String, unique=True, index=True) default_model = Column(String) # 'text' or 'vision' created_at = Column(DateTime) 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) status = Column(String) # 'pending', 'verified' processed_data = Column(JSONB) # Store the verified extraction results vendor = relationship("Vendor") 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_content = Column(LargeBinary) email = relationship("Email", back_populates="attachments") def get_db(): db = SessionLocal() try: yield db finally: db.close()