Sheetly / app /models.py
nvikou's picture
initial commit
da6ee5e verified
Raw History Blame Contribute Delete
3.09 kB
"""SQLAlchemy models for Sheetly."""
from __future__ import annotations
from datetime import datetime
from typing import Any, Optional
from sqlalchemy import (
JSON,
Boolean,
DateTime,
Float,
ForeignKey,
Integer,
String,
Text,
)
from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
from app.timeutil import utc_now
class Base(DeclarativeBase):
"""Declarative base."""
class Batch(Base):
"""Upload batch job."""
__tablename__ = "batches"
id: Mapped[str] = mapped_column(String(36), primary_key=True)
status: Mapped[str] = mapped_column(
String(32), default="pending"
)
total: Mapped[int] = mapped_column(Integer, default=0)
processed: Mapped[int] = mapped_column(Integer, default=0)
failed: Mapped[int] = mapped_column(Integer, default=0)
created_at: Mapped[datetime] = mapped_column(
DateTime, default=utc_now
)
finished_at: Mapped[Optional[datetime]] = mapped_column(
DateTime, nullable=True
)
class Document(Base):
"""Processed document record."""
__tablename__ = "documents"
id: Mapped[str] = mapped_column(String(36), primary_key=True)
batch_id: Mapped[Optional[str]] = mapped_column(
String(36), ForeignKey("batches.id"), nullable=True
)
filename: Mapped[str] = mapped_column(String(512))
file_path: Mapped[str] = mapped_column(String(1024))
mime_type: Mapped[str] = mapped_column(String(128), default="")
doc_type: Mapped[str] = mapped_column(
String(64), default="other"
)
status: Mapped[str] = mapped_column(
String(32), default="queued"
)
language: Mapped[str] = mapped_column(String(8), default="")
extracted: Mapped[Optional[dict[str, Any]]] = mapped_column(
JSON, nullable=True
)
confidence: Mapped[Optional[dict[str, Any]]] = mapped_column(
JSON, nullable=True
)
issues: Mapped[Optional[list[Any]]] = mapped_column(
JSON, nullable=True
)
is_duplicate: Mapped[bool] = mapped_column(
Boolean, default=False
)
duplicate_of: Mapped[Optional[str]] = mapped_column(
String(36), nullable=True
)
error: Mapped[Optional[str]] = mapped_column(
Text, nullable=True
)
avg_confidence: Mapped[Optional[float]] = mapped_column(
Float, nullable=True
)
created_at: Mapped[datetime] = mapped_column(
DateTime, default=utc_now
)
updated_at: Mapped[datetime] = mapped_column(
DateTime, default=utc_now, onupdate=utc_now
)
class DuplicateIndex(Base):
"""Index for invoice duplicate detection."""
__tablename__ = "duplicate_index"
id: Mapped[int] = mapped_column(
Integer, primary_key=True, autoincrement=True
)
supplier: Mapped[str] = mapped_column(String(256), index=True)
invoice_number: Mapped[str] = mapped_column(
String(128), index=True
)
document_id: Mapped[str] = mapped_column(String(36))
created_at: Mapped[datetime] = mapped_column(
DateTime, default=utc_now
)