app/models/document.py

"""Document ORM model for uploaded source files and processing status."""

from datetime import datetime
from uuid import uuid4

from sqlalchemy import DateTime, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column

from app.database import Base


class Document(Base):
    """ORM model representing an ingested document."""

    __tablename__ = "documents"

    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid4()))
    filename: Mapped[str] = mapped_column(String(255), nullable=False)
    original_filename: Mapped[str] = mapped_column(String(255), nullable=False)
    file_type: Mapped[str] = mapped_column(String(50), nullable=False)
    file_size_bytes: Mapped[int | None] = mapped_column(Integer)
    file_path: Mapped[str] = mapped_column(String(500), nullable=False)
    status: Mapped[str] = mapped_column(String(50), default="pending")
    total_chunks: Mapped[int] = mapped_column(Integer, default=0)
    error_message: Mapped[str | None] = mapped_column(Text)
    uploaded_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.utcnow)
    processed_at: Mapped[datetime | None] = mapped_column(DateTime)

    def __repr__(self) -> str:
        """Return a concise string representation for debugging."""

        return f"Document(id={self.id!r}, filename={self.filename!r}, status={self.status!r})"