app/models/document.py

from __future__ import annotations

from datetime import datetime
from typing import TYPE_CHECKING

from sqlalchemy import DateTime, ForeignKey, Integer, JSON, String, Text, func
from sqlalchemy.orm import Mapped, mapped_column, relationship

from app.core.database import Base
from app.utils.ids import prefixed_id

if TYPE_CHECKING:
    from app.models.document_chunk import DocumentChunk


class Document(Base):
    __tablename__ = "documents"

    id: Mapped[str] = mapped_column(
        String(40),
        primary_key=True,
        default=lambda: prefixed_id("doc"),
    )
    user_id: Mapped[str] = mapped_column(
        String(40),
        ForeignKey("users.id"),
        index=True,
        nullable=False,
    )
    title: Mapped[str] = mapped_column(String(255), nullable=False)
    file_name: Mapped[str] = mapped_column(String(255), nullable=False)
    file_type: Mapped[str] = mapped_column(String(80), nullable=False)
    file_path: Mapped[str] = mapped_column(String(500), nullable=False)
    subject: Mapped[str | None] = mapped_column(String(120), nullable=True)
    chapter: Mapped[str | None] = mapped_column(String(160), nullable=True)
    syllabus: Mapped[str | None] = mapped_column(String(120), nullable=True)
    status: Mapped[str] = mapped_column(String(30), default="uploaded", nullable=False)
    extracted_text: Mapped[str | None] = mapped_column(Text, nullable=True)
    extraction_error: Mapped[str | None] = mapped_column(Text, nullable=True)
    chunk_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
    source_type: Mapped[str] = mapped_column(
        String(40),
        default="pdf",
        nullable=False,
    )
    # Semantic material type set by the source classifier on upload.
    # Possible values: notes | chapter | textbook | question_paper |
    #                  handwritten_notes | syllabus | resume_or_personal_doc | unknown
    material_type: Mapped[str] = mapped_column(
        String(40),
        default="unknown",
        nullable=False,
    )
    education_extraction_status: Mapped[str] = mapped_column(
        String(30),
        default="uploaded",
        nullable=False,
    )
    education_extraction_error: Mapped[str | None] = mapped_column(Text, nullable=True)
    education_warnings_json: Mapped[list[str]] = mapped_column(
        JSON,
        default=list,
        nullable=False,
    )
    syllabus_items_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
    pyq_questions_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
    pyq_years_json: Mapped[list[int]] = mapped_column(JSON, default=list, nullable=False)
    extracted_text_length: Mapped[int | None] = mapped_column(Integer, nullable=True)
    processing_started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
    processing_completed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True),
        server_default=func.now(),
        nullable=False,
    )
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True),
        server_default=func.now(),
        onupdate=func.now(),
        nullable=False,
    )
    chunks: Mapped[list["DocumentChunk"]] = relationship(
        "DocumentChunk",
        back_populates="document",
        cascade="all, delete-orphan",
        order_by="DocumentChunk.chunk_index",
    )