feat(provenance): image_record.artist_id + 0008 backfill/drop-artist-tags

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 21:33:11 -04:00
parent 8fe1994d8e
commit 63e7185811
4 changed files with 238 additions and 0 deletions
@@ -0,0 +1,52 @@
+"""fc2d-vii-c: image_record.artist_id + backfill + drop artist tags
+
+Revision ID: 0008
+Revises: 0007
+Create Date: 2026-05-18
+
+Internal forward-correctness migration (the big legacy-import migration
+stays deferred). downgrade() does NOT recreate deleted artist tags;
+downgrade is dev-only and the data is reconstructable by re-import.
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+from backend.app.utils.artist_backfill import (
+    BACKFILL_PRIMARY_SQL,
+    BACKFILL_PROVENANCE_SQL,
+    BACKFILL_TAG_SQL,
+    DELETE_ARTIST_TAGS_SQL,
+)
+
+revision: str = "0008"
+down_revision: Union[str, None] = "0007"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "image_record",
+        sa.Column("artist_id", sa.Integer(), nullable=True),
+    )
+    op.create_foreign_key(
+        "fk_image_record_artist_id", "image_record", "artist",
+        ["artist_id"], ["id"], ondelete="SET NULL",
+    )
+    op.create_index(
+        "ix_image_record_artist_id", "image_record", ["artist_id"],
+    )
+    op.execute(BACKFILL_PRIMARY_SQL)
+    op.execute(BACKFILL_PROVENANCE_SQL)
+    op.execute(BACKFILL_TAG_SQL)
+    op.execute(DELETE_ARTIST_TAGS_SQL)
+
+
+def downgrade() -> None:
+    op.drop_index("ix_image_record_artist_id", table_name="image_record")
+    op.drop_constraint(
+        "fk_image_record_artist_id", "image_record", type_="foreignkey"
+    )
+    op.drop_column("image_record", "artist_id")
@@ -54,6 +54,11 @@ class ImageRecord(Base):
    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)
@@ -0,0 +1,44 @@
+"""Literal SQL for the FC-2d-vii-c artist backfill / artist-tag delete.
+
+Intentionally pure string constants — NO model/slug imports, NO logic —
+so migration 0008 and its test share one drift-proof source of truth.
+Backfill steps are ordered primary -> provenance -> artist-tag and each
+only touches rows still NULL (idempotent, first match wins). The
+artist-tag step matches Artist.name = Tag.name: the importer always
+created both from the same artist_name string.
+"""
+
+BACKFILL_PRIMARY_SQL = """
+UPDATE image_record AS ir
+SET artist_id = s.artist_id
+FROM post p
+JOIN source s ON s.id = p.source_id
+WHERE ir.primary_post_id = p.id
+  AND ir.artist_id IS NULL
+"""
+
+BACKFILL_PROVENANCE_SQL = """
+UPDATE image_record AS ir
+SET artist_id = s.artist_id
+FROM (
+    SELECT DISTINCT ON (ip.image_record_id)
+           ip.image_record_id, src.artist_id
+    FROM image_provenance ip
+    JOIN source src ON src.id = ip.source_id
+    ORDER BY ip.image_record_id, ip.id
+) AS s
+WHERE ir.id = s.image_record_id
+  AND ir.artist_id IS NULL
+"""
+
+BACKFILL_TAG_SQL = """
+UPDATE image_record AS ir
+SET artist_id = a.id
+FROM image_tag it
+JOIN tag t ON t.id = it.tag_id AND t.kind = 'artist'
+JOIN artist a ON a.name = t.name
+WHERE it.image_record_id = ir.id
+  AND ir.artist_id IS NULL
+"""
+
+DELETE_ARTIST_TAGS_SQL = "DELETE FROM tag WHERE kind = 'artist'"
@@ -0,0 +1,137 @@
+"""FC-2d-vii-c: image_record.artist_id + backfill + artist-tag delete."""
+
+from datetime import UTC, datetime, timedelta
+
+import pytest
+from sqlalchemy import func, select, text
+
+from backend.app.models import (
+    Artist,
+    ImageProvenance,
+    ImageRecord,
+    Post,
+    Source,
+    Tag,
+    TagKind,
+)
+from backend.app.models.tag import image_tag
+from backend.app.utils.artist_backfill import (
+    BACKFILL_PRIMARY_SQL,
+    BACKFILL_PROVENANCE_SQL,
+    BACKFILL_TAG_SQL,
+    DELETE_ARTIST_TAGS_SQL,
+)
+
+pytestmark = pytest.mark.integration
+
+
+def test_image_record_has_artist_id_column():
+    assert "artist_id" in {c.name for c in ImageRecord.__table__.columns}
+
+
+async def _img(db, n):
+    rec = ImageRecord(
+        path=f"/images/bf/{n}.jpg", sha256=f"bf{n:062d}",
+        size_bytes=1, mime="image/jpeg", width=1, height=1,
+        origin="imported_filesystem", integrity_status="unknown",
+    )
+    rec.created_at = datetime.now(UTC) - timedelta(minutes=n)
+    db.add(rec)
+    await db.flush()
+    return rec
+
+
+async def _artist_source(db, name, slug):
+    a = Artist(name=name, slug=slug)
+    db.add(a)
+    await db.flush()
+    s = Source(artist_id=a.id, platform="patreon",
+               url=f"https://p.test/{slug}")
+    db.add(s)
+    await db.flush()
+    return a, s
+
+
+async def _run_backfill(db):
+    await db.execute(text(BACKFILL_PRIMARY_SQL))
+    await db.execute(text(BACKFILL_PROVENANCE_SQL))
+    await db.execute(text(BACKFILL_TAG_SQL))
+
+
+@pytest.mark.asyncio
+async def test_backfill_primary_post(db):
+    rec = await _img(db, 1)
+    a, s = await _artist_source(db, "Alice", "alice")
+    post = Post(source_id=s.id, external_post_id="1")
+    db.add(post)
+    await db.flush()
+    rec.primary_post_id = post.id
+    await db.flush()
+    await _run_backfill(db)
+    got = await db.scalar(
+        select(ImageRecord.artist_id).where(ImageRecord.id == rec.id)
+    )
+    assert got == a.id
+
+
+@pytest.mark.asyncio
+async def test_backfill_provenance_fallback(db):
+    rec = await _img(db, 1)
+    a, s = await _artist_source(db, "Bob", "bob")
+    post = Post(source_id=s.id, external_post_id="2")
+    db.add(post)
+    await db.flush()
+    db.add(ImageProvenance(image_record_id=rec.id, post_id=post.id,
+                           source_id=s.id))
+    await db.flush()
+    await _run_backfill(db)
+    got = await db.scalar(
+        select(ImageRecord.artist_id).where(ImageRecord.id == rec.id)
+    )
+    assert got == a.id
+
+
+@pytest.mark.asyncio
+async def test_backfill_artist_tag_by_name(db):
+    rec = await _img(db, 1)
+    a = Artist(name="Carol", slug="carol")
+    db.add(a)
+    await db.flush()
+    tag = Tag(name="Carol", kind=TagKind.artist)
+    db.add(tag)
+    await db.flush()
+    await db.execute(image_tag.insert().values(
+        image_record_id=rec.id, tag_id=tag.id, source="auto"))
+    await db.flush()
+    await _run_backfill(db)
+    got = await db.scalar(
+        select(ImageRecord.artist_id).where(ImageRecord.id == rec.id)
+    )
+    assert got == a.id
+
+
+@pytest.mark.asyncio
+async def test_no_signal_stays_null(db):
+    rec = await _img(db, 1)
+    await _run_backfill(db)
+    got = await db.scalar(
+        select(ImageRecord.artist_id).where(ImageRecord.id == rec.id)
+    )
+    assert got is None
+
+
+@pytest.mark.asyncio
+async def test_delete_removes_only_artist_tags(db):
+    artist_tag = Tag(name="Dave", kind=TagKind.artist)
+    general_tag = Tag(name="forest", kind=TagKind.general)
+    db.add_all([artist_tag, general_tag])
+    await db.flush()
+    await db.execute(text(DELETE_ARTIST_TAGS_SQL))
+    remaining = await db.scalar(
+        select(func.count()).select_from(Tag).where(Tag.kind == TagKind.artist)
+    )
+    assert remaining == 0
+    survived = await db.scalar(
+        select(func.count()).select_from(Tag).where(Tag.kind == TagKind.general)
+    )
+    assert survived >= 1