bvandeusen
e05e0b9f37
The gallery cursored on COALESCE(post.post_date, image_record.created_at) across the Post outer join — an expression spanning two tables that no index can serve, so every /scroll sorted a large slice of the library (and the old frontend fired ten serially). Materialize it: - image_record.effective_date column + ix_image_record_effective_date (effective_date DESC, id DESC); alembic 0035 backfills COALESCE(primary post's post_date, created_at) for existing rows. - gallery_service._effective_date_col() now returns the column, so scroll / timeline / jump / neighbors all order off the index instead of re-deriving the COALESCE. _neighbors reads record.effective_date directly (drops an extra Post lookup). - importer._apply_sidecar maintains it: when a primary post with a date is linked, effective_date = post.post_date; plain inserts keep the created_at-equivalent server default. Tests: sidecar import asserts effective_date == post.post_date; gallery ordering/timeline/jump test seeds set effective_date alongside created_at. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
94 lines
3.9 KiB
Python
94 lines
3.9 KiB
Python
"""ImageRecord — the gallery's primary entity, ported from ImageRepo.
|
||
|
||
ML fields and thumbnails are declared now (in FC-1) so FC-2 can populate them
|
||
without a schema migration. The SigLIP embedding column uses pgvector's Vector
|
||
type — pgvector extension is enabled in the initial migration.
|
||
"""
|
||
|
||
from datetime import datetime
|
||
|
||
from pgvector.sqlalchemy import Vector
|
||
from sqlalchemy import (
|
||
JSON,
|
||
BigInteger,
|
||
DateTime,
|
||
Enum,
|
||
ForeignKey,
|
||
Integer,
|
||
String,
|
||
Text,
|
||
func,
|
||
)
|
||
from sqlalchemy.orm import Mapped, mapped_column
|
||
|
||
from .base import Base
|
||
|
||
ORIGIN_CHOICES = ("downloaded", "imported_filesystem", "uploaded")
|
||
|
||
|
||
class ImageRecord(Base):
|
||
__tablename__ = "image_record"
|
||
|
||
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
||
|
||
# On-disk identity
|
||
path: Mapped[str] = mapped_column(Text, nullable=False, unique=True)
|
||
sha256: Mapped[str] = mapped_column(String(64), nullable=False, unique=True, index=True)
|
||
phash: Mapped[str | None] = mapped_column(String(32), nullable=True, index=True)
|
||
size_bytes: Mapped[int] = mapped_column(BigInteger, nullable=False)
|
||
mime: Mapped[str] = mapped_column(String(64), nullable=False)
|
||
width: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||
height: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||
|
||
# Integrity verification status. FC-2e populates this; FC-2a leaves rows at 'unknown'.
|
||
# Values: 'unknown' (default), 'ok', 'corrupt', 'failed_verification'.
|
||
integrity_status: Mapped[str] = mapped_column(
|
||
String(24), nullable=False, default="unknown", index=True
|
||
)
|
||
|
||
# Thumbnail (populated by FC-2)
|
||
thumbnail_path: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||
|
||
# Origin / provenance pointers
|
||
origin: Mapped[str] = mapped_column(Enum(*ORIGIN_CHOICES, name="origin_enum"), nullable=False)
|
||
primary_post_id: Mapped[int | None] = mapped_column(
|
||
ForeignKey("post.id", ondelete="SET NULL"), nullable=True, index=True
|
||
)
|
||
# FC-2d-vii-c: canonical per-image artist (the single source of truth
|
||
# for attribution; provenance posts remain lineage detail).
|
||
artist_id: Mapped[int | None] = mapped_column(
|
||
ForeignKey("artist.id", ondelete="SET NULL"), nullable=True, index=True
|
||
)
|
||
|
||
# ML fields (populated by FC-2's ml-worker)
|
||
tagger_predictions: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
||
tagger_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
|
||
# 1152 = SigLIP-so400m embedding dim. Swapping models in FC-2 may require
|
||
# a column-width migration.
|
||
siglip_embedding: Mapped[list[float] | None] = mapped_column(Vector(1152), nullable=True)
|
||
siglip_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
|
||
|
||
# Centroid score cache (populated post-tagging)
|
||
centroid_scores: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
||
|
||
created_at: Mapped[datetime] = mapped_column(
|
||
DateTime(timezone=True), nullable=False, server_default=func.now()
|
||
)
|
||
# Denormalized gallery sort key = COALESCE(primary post's post_date,
|
||
# created_at) (alembic 0035). The gallery used to compute this as a
|
||
# COALESCE across the Post outer join on every /scroll, which can't use
|
||
# an index and re-sorted a large slice of the library per page (×10 with
|
||
# the old serial batching). Materializing it lets the cursor scroll read
|
||
# ix_image_record_effective_date directly. Maintained by the importer
|
||
# (services/importer.py _apply_sidecar) when a primary post with a date
|
||
# is linked; plain inserts keep the created_at-equivalent server default.
|
||
effective_date: Mapped[datetime] = mapped_column(
|
||
DateTime(timezone=True), nullable=False, server_default=func.now()
|
||
)
|
||
updated_at: Mapped[datetime] = mapped_column(
|
||
DateTime(timezone=True),
|
||
nullable=False,
|
||
server_default=func.now(),
|
||
onupdate=func.now(),
|
||
)
|