40 lines
1.7 KiB
Python
40 lines
1.7 KiB
Python
|
"""Reference and duplicate group models."""
|
||
|
|
from sqlalchemy import Float, ForeignKey, JSON, String
|
||
|
|
from sqlalchemy.orm import Mapped, mapped_column, relationship
|
||
|
|
|
||
|
|
from app.models.base import Base, TimestampMixin, UUIDMixin
|
||
|
|
|
||
|
|
|
||
|
|
class ArticleReference(Base, UUIDMixin, TimestampMixin):
|
||
|
|
"""Reference from a cleaned article to another related article."""
|
||
|
|
|
||
|
|
__tablename__ = "article_references"
|
||
|
|
|
||
|
|
source_article_id: Mapped[str] = mapped_column(
|
||
|
|
ForeignKey("cleaned_articles.id", ondelete="CASCADE"), nullable=False, index=True
|
||
|
|
)
|
||
|
|
referenced_article_id: Mapped[str | None] = mapped_column(
|
||
|
|
ForeignKey("cleaned_articles.id", ondelete="SET NULL"), nullable=True, index=True
|
||
|
|
)
|
||
|
|
reference_type: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
|
||
|
|
reference_link: Mapped[str | None] = mapped_column(String(2048), default="")
|
||
|
|
reference_title: Mapped[str | None] = mapped_column(String(1024), default="")
|
||
|
|
similarity: Mapped[float | None] = mapped_column(Float, nullable=True)
|
||
|
|
|
||
|
|
|
||
|
|
class DuplicateGroup(Base, UUIDMixin, TimestampMixin):
|
||
|
|
"""Group of duplicate articles."""
|
||
|
|
|
||
|
|
__tablename__ = "duplicate_groups"
|
||
|
|
|
||
|
|
representative_article_id: Mapped[str | None] = mapped_column(
|
||
|
|
ForeignKey("cleaned_articles.id", ondelete="SET NULL"), nullable=True, index=True
|
||
|
|
)
|
||
|
|
member_article_ids: Mapped[list] = mapped_column(JSON, default=list, nullable=False)
|
||
|
|
similarity_matrix: Mapped[dict] = mapped_column(JSON, default=dict, nullable=False)
|
||
|
|
brief_date: Mapped[str | None] = mapped_column(String(10), default="", index=True)
|
||
|
|
|
||
|
|
articles: Mapped[list["CleanedArticle"]] = relationship(
|
||
|
|
"CleanedArticle", back_populates="duplicate_group"
|
||
|
|
)
|