document-processor/app/models/document.py

53 lines
2.3 KiB
Python

from datetime import datetime
from sqlalchemy import String, Integer, DateTime, Text
from sqlalchemy.orm import Mapped, mapped_column, relationship
from app.db.base import Base
class Document(Base):
__tablename__ = "documents"
id: Mapped[int] = mapped_column(primary_key=True, index=True)
document_id: Mapped[str] = mapped_column(String(64), unique=True, index=True, nullable=False)
document_type: Mapped[str | None] = mapped_column(String(50), nullable=True)
source_path: Mapped[str] = mapped_column(Text, nullable=False)
original_path: Mapped[str | None] = mapped_column(Text, nullable=True)
current_path: Mapped[str | None] = mapped_column(Text, nullable=True)
share_path: Mapped[str | None] = mapped_column(Text, nullable=True)
original_filename: Mapped[str | None] = mapped_column(String(255), nullable=True)
canonical_filename: Mapped[str | None] = mapped_column(String(255), nullable=True)
mime_type: Mapped[str | None] = mapped_column(String(100), nullable=True)
file_size: Mapped[int | None] = mapped_column(Integer, nullable=True)
page_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
sha256_original: Mapped[str | None] = mapped_column(String(64), nullable=True)
sha256_current: Mapped[str | None] = mapped_column(String(64), nullable=True)
storage_status: Mapped[str] = mapped_column(String(50), default="ingested", nullable=False)
review_status: Mapped[str] = mapped_column(String(50), default="ingested", nullable=False)
created_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.utcnow, nullable=False)
updated_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow, nullable=False)
versions: Mapped[list["DocumentVersion"]] = relationship(
back_populates="document",
cascade="all, delete-orphan",
)
text_versions: Mapped[list["TextVersion"]] = relationship(
back_populates="document",
cascade="all, delete-orphan",
)
extracted_fields: Mapped[list["ExtractedField"]] = relationship(
back_populates="document",
cascade="all, delete-orphan",
)
layer1_candidates: Mapped[list["Layer1Candidate"]] = relationship(
back_populates="document",
cascade="all, delete-orphan",
)