88 lines
3.5 KiB
Python
88 lines
3.5 KiB
Python
"""documents 테이블 ORM"""
|
|
|
|
from datetime import datetime
|
|
|
|
from pgvector.sqlalchemy import Vector
|
|
from sqlalchemy import BigInteger, DateTime, Enum, String, Text
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from core.database import Base
|
|
|
|
|
|
class Document(Base):
|
|
__tablename__ = "documents"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
|
|
|
|
# 1계층: 원본 파일
|
|
file_path: Mapped[str] = mapped_column(Text, unique=True, nullable=False)
|
|
file_hash: Mapped[str] = mapped_column(String(64), nullable=False)
|
|
file_format: Mapped[str] = mapped_column(String(20), nullable=False)
|
|
file_size: Mapped[int | None] = mapped_column(BigInteger)
|
|
file_type: Mapped[str] = mapped_column(
|
|
Enum("immutable", "editable", "note", name="doc_type"),
|
|
default="immutable"
|
|
)
|
|
import_source: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# 2계층: 텍스트 추출
|
|
extracted_text: Mapped[str | None] = mapped_column(Text)
|
|
extracted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
extractor_version: Mapped[str | None] = mapped_column(String(50))
|
|
|
|
# 2계층: AI 가공
|
|
ai_summary: Mapped[str | None] = mapped_column(Text)
|
|
ai_tags: Mapped[dict | None] = mapped_column(JSONB, default=[])
|
|
ai_domain: Mapped[str | None] = mapped_column(String(100))
|
|
ai_sub_group: Mapped[str | None] = mapped_column(String(100))
|
|
ai_model_version: Mapped[str | None] = mapped_column(String(50))
|
|
ai_processed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
document_type: Mapped[str | None] = mapped_column(String(50))
|
|
importance: Mapped[str | None] = mapped_column(String(20), default="medium")
|
|
ai_confidence: Mapped[float | None] = mapped_column()
|
|
|
|
# 3계층: 벡터 임베딩
|
|
embedding = mapped_column(Vector(1024), nullable=True)
|
|
embed_model_version: Mapped[str | None] = mapped_column(String(50))
|
|
embedded_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
# 사용자 메모
|
|
user_note: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# ODF 변환
|
|
derived_path: Mapped[str | None] = mapped_column(Text) # 변환본 경로 (.derived/)
|
|
original_format: Mapped[str | None] = mapped_column(String(20))
|
|
conversion_status: Mapped[str | None] = mapped_column(String(20), default="none")
|
|
|
|
# 승인/삭제
|
|
review_status: Mapped[str | None] = mapped_column(String(20), default="pending")
|
|
deleted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
# 외부 편집 URL
|
|
edit_url: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# 미리보기
|
|
preview_status: Mapped[str | None] = mapped_column(String(20), default="none")
|
|
preview_hash: Mapped[str | None] = mapped_column(String(64))
|
|
preview_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
# 메타데이터
|
|
source_channel: Mapped[str | None] = mapped_column(
|
|
Enum("law_monitor", "devonagent", "email", "web_clip",
|
|
"tksafety", "inbox_route", "manual", "drive_sync", "news",
|
|
name="source_channel")
|
|
)
|
|
data_origin: Mapped[str | None] = mapped_column(
|
|
Enum("work", "external", name="data_origin")
|
|
)
|
|
title: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# 타임스탬프
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now
|
|
)
|
|
updated_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now, onupdate=datetime.now
|
|
)
|