bvandeusen
f154603811
Videos deduped on sha256 only (pHash is images-only), so a different encode/remux of the same clip imported as a distinct record — the "same video from multiple sources" clutter surfaced by #859. Tier-1 metadata fingerprint: identity = container duration (±1.0s) + matching aspect ratio, scoped to the same artist; quality axis = pixel dimensions (mirrors image pHash: larger_exists→skip+link, smaller_exists→supersede). Codec/bitrate are deliberately NOT part of identity (the point is matching across re-encodes). Tight tolerances because a wrong video merge is destructive. - image_record.duration_seconds (Float, nullable; migration 0052). NULL for images. - safe_probe.probe_video also reads format=duration (one extra ffprobe field on the call that already runs); ProbeResult.duration. - _find_similar_video(duration,w,h,artist) shared by both import pipelines. - _import_media (filesystem/archive path): captures duration, video near-dup branch, persists duration. - attach_in_place (download path — handles #859's videos, previously didn't probe video at all): best-effort probe for dims+duration (LENIENT — never newly rejects a downloaded video on probe failure), video near-dup branch, persists duration. - _supersede carries duration onto the kept row. Reuses SkipReason.duplicate_phash so the existing download/external dup-cleanup (path-safe unlink, #859) applies unchanged. Tests: skip-smaller, supersede-larger (+ duration adopted), and distinct-durations-not-merged (false-merge guard). Follow-up (Phase 2, #871): a backfill to re-probe NULL-duration existing videos so the current library participates in dedup; retroactive merge of existing dups is a separate destructive maintenance action. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
113 lines
5.1 KiB
Python
113 lines
5.1 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,
|
||
Float,
|
||
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)
|
||
# Video container duration (seconds); NULL for images. The Tier-1 video
|
||
# near-dup key (#871): two videos of the same artist with matching duration
|
||
# (+ aspect) are the same content across re-encodes — dedup like image pHash.
|
||
duration_seconds: Mapped[float | None] = mapped_column(Float, 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)
|
||
|
||
# Source provenance for downloaded media (#830 Phase 2). `source_url` is the
|
||
# CDN/origin URL the file was fetched from (debugging + future re-fetch).
|
||
# `source_filehash` is the URL's 32-hex CDN identity segment
|
||
# (utils.paths.filehash_from_url) — the JOIN KEY that maps a post body's
|
||
# inline `<img src=CDN>` back to this local copy so the rendered body serves
|
||
# our stored image instead of hotlinking the public source. Indexed for the
|
||
# render-time lookup. NULL for filesystem-imported / pre-Phase-2 rows.
|
||
source_url: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||
source_filehash: Mapped[str | None] = mapped_column(
|
||
String(32), nullable=True, index=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). Per-tag predictions live in the
|
||
# normalized image_prediction table (#768) — the tagger_predictions JSON
|
||
# column was dropped in migration 0046. tagger_model_version stays as the
|
||
# "has this been tagged / is it current?" signal the backfill sweep reads.
|
||
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(),
|
||
)
|