backend/app/models/document.py

"""
Document model — stores metadata for every uploaded file.
The actual binary is stored on the filesystem (uploads/).
Embeddings/chunks live in Qdrant.
"""
from __future__ import annotations

import uuid
from datetime import datetime
from sqlalchemy import Boolean, DateTime, ForeignKey, Integer, String, Text, func
from sqlalchemy.orm import Mapped, mapped_column

from app.core.database import Base


class Document(Base):
    __tablename__ = "documents"

    id: Mapped[str] = mapped_column(
        String(36), primary_key=True, default=lambda: str(uuid.uuid4())
    )
    # Ownership
    tenant_id: Mapped[str] = mapped_column(
        String(36), ForeignKey("tenants.id"), nullable=False, index=True
    )
    uploaded_by: Mapped[str] = mapped_column(
        String(36), ForeignKey("users.id"), nullable=False
    )

    # File metadata
    filename: Mapped[str] = mapped_column(String(512), nullable=False)
    original_name: Mapped[str] = mapped_column(String(512), nullable=False)
    file_path: Mapped[str] = mapped_column(String(1024), nullable=False)
    file_size_bytes: Mapped[int] = mapped_column(Integer, default=0)
    mime_type: Mapped[str] = mapped_column(String(100), default="application/pdf")

    # Classification
    doc_type: Mapped[str] = mapped_column(
        String(50), default="general"
    )  # general | hr | finance | legal | technical

    # Processing status
    status: Mapped[str] = mapped_column(
        String(30), default="pending"
    )  # pending | processing | ready | failed
    error_message: Mapped[str | None] = mapped_column(Text, nullable=True)
    chunk_count: Mapped[int] = mapped_column(Integer, default=0)
    page_count: Mapped[int] = mapped_column(Integer, default=0)

    # Timestamps
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), index=True
    )
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), onupdate=func.now()
    )

    def __repr__(self) -> str:
        return f"<Document {self.filename} [{self.status}]>"