"""ImageProvenance — links an ImageRecord to a Post. One image can have many provenance rows — different posts each contribute metadata (enrich-on-duplicate rule, spec §3: a downloaded image that is a pHash dupe of an existing record gets a NEW provenance row for the new post appended, rather than the metadata being dropped). But the (image, post) pair is unique — alembic 0021 enforces uq_image_provenance_image_post after operator-flagged 2026-05-26 saw _apply_sidecar's existence-check + INSERT race plant duplicates that then broke .scalar_one_or_none() on every later deep-scan rederive (MultipleResultsFound). """ from datetime import datetime from sqlalchemy import JSON, DateTime, ForeignKey, Integer, UniqueConstraint, func from sqlalchemy.orm import Mapped, mapped_column from .base import Base class ImageProvenance(Base): __tablename__ = "image_provenance" __table_args__ = ( UniqueConstraint( "image_record_id", "post_id", name="uq_image_provenance_image_post", ), ) id: Mapped[int] = mapped_column(Integer, primary_key=True) image_record_id: Mapped[int] = mapped_column( ForeignKey("image_record.id", ondelete="CASCADE"), nullable=False, index=True ) post_id: Mapped[int] = mapped_column( ForeignKey("post.id", ondelete="CASCADE"), nullable=False, index=True ) # Nullable since alembic 0030 — provenance rows for filesystem-imported # content with no subscription have NULL source_id. FK ondelete SET # NULL so deleting a Source detaches its provenance rows instead of # destroying the linkage between image and post. source_id: Mapped[int | None] = mapped_column( ForeignKey("source.id", ondelete="SET NULL"), nullable=True, index=True ) # The archive PostAttachment this image was extracted FROM, when it came # out of a .zip/.rar rather than as a loose file (milestone #87). Lets the # provenance UI show the exact archive a file lives inside instead of every # attachment on the post. NULL for loose downloads and pre-backfill rows. # SET NULL so deleting the archive attachment never destroys the (image, # post) edge — it just forgets which archive it came from. from_attachment_id: Mapped[int | None] = mapped_column( ForeignKey("post_attachment.id", ondelete="SET NULL"), nullable=True, index=True, ) captured_metadata: Mapped[dict | None] = mapped_column(JSON, nullable=True) captured_at: Mapped[datetime] = mapped_column( DateTime(timezone=True), nullable=False, server_default=func.now() )