fc3k: cleanup_service projections — artist cascade, bulk delete, tag usage, unused tags

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/app/services/cleanup_service.py

@@ -0,0 +1,156 @@
+"""FC-3k: first-class admin destructive operations.
+
+Projections are pure SELECTs used by both dry-run preview endpoints
+and Tier-B count prompts. Mutations (Task 2) are called from sync
+HTTP handlers (small ops) and from Celery tasks in
+backend.app.tasks.admin (long ops).
+
+This module is the PERMANENT home of artist-cascade + image-unlink
+logic. The legacy copy at backend/app/services/migrators/cleanup.py
+stays in place until FC-3j; FC-3j will replace its body with thin
+re-exports from this module and then delete the wrapper.
+"""
+from __future__ import annotations
+
+from sqlalchemy import func, select
+from sqlalchemy.orm import Session
+
+from ..models import Artist, ImageRecord, Tag
+from ..models.series_page import SeriesPage
+from ..models.tag import image_tag
+
+
+def project_artist_cascade(session: Session, *, slug: str) -> dict:
+    """Read-only projection of what delete_artist_cascade would touch.
+
+    Returns:
+        {
+          "artist": {"id": int, "name": str, "slug": str},
+          "projected": {
+            "images": int,
+            "sources": int,
+            "thumbs": int,        # images with a thumbnail_path set
+            "import_tasks": int,  # ImportTask rows referencing the artist's images
+            "bytes_on_disk": int, # SUM(image_record.size_bytes) — column is NOT NULL
+          },
+        }
+    Raises LookupError if slug not found. No mutations.
+    """
+    from ..models.import_task import ImportTask
+    from ..models.source import Source
+
+    artist = session.execute(
+        select(Artist).where(Artist.slug == slug)
+    ).scalar_one_or_none()
+    if artist is None:
+        raise LookupError(f"artist slug not found: {slug!r}")
+
+    images_count = session.execute(
+        select(func.count(ImageRecord.id))
+        .where(ImageRecord.artist_id == artist.id)
+    ).scalar_one()
+    sources_count = session.execute(
+        select(func.count(Source.id))
+        .where(Source.artist_id == artist.id)
+    ).scalar_one()
+    thumbs_count = session.execute(
+        select(func.count(ImageRecord.id))
+        .where(ImageRecord.artist_id == artist.id)
+        .where(ImageRecord.thumbnail_path.is_not(None))
+    ).scalar_one()
+    import_tasks_count = session.execute(
+        select(func.count(ImportTask.id))
+        .where(
+            ImportTask.result_image_id.in_(
+                select(ImageRecord.id).where(ImageRecord.artist_id == artist.id)
+            )
+        )
+    ).scalar_one()
+    bytes_on_disk = session.execute(
+        select(func.coalesce(func.sum(ImageRecord.size_bytes), 0))
+        .where(ImageRecord.artist_id == artist.id)
+    ).scalar_one()
+
+    return {
+        "artist": {"id": artist.id, "name": artist.name, "slug": artist.slug},
+        "projected": {
+            "images": images_count,
+            "sources": sources_count,
+            "thumbs": thumbs_count,
+            "import_tasks": import_tasks_count,
+            "bytes_on_disk": int(bytes_on_disk),
+        },
+    }
+
+
+def project_bulk_image_delete(
+    session: Session, *, image_ids: list[int],
+) -> dict:
+    """Read-only projection of what delete_images would touch.
+
+    Returns:
+        {
+          "images_found": int,
+          "thumbs_to_unlink": int,
+          "bytes_on_disk": int,
+          "missing_ids": list[int],   # ids passed in that don't exist
+        }
+    No mutations.
+    """
+    if not image_ids:
+        return {
+            "images_found": 0,
+            "thumbs_to_unlink": 0,
+            "bytes_on_disk": 0,
+            "missing_ids": [],
+        }
+
+    rows = session.execute(
+        select(
+            ImageRecord.id,
+            ImageRecord.thumbnail_path,
+            ImageRecord.size_bytes,
+        ).where(ImageRecord.id.in_(image_ids))
+    ).all()
+    found_ids = {r.id for r in rows}
+    missing = sorted(set(image_ids) - found_ids)
+    return {
+        "images_found": len(rows),
+        "thumbs_to_unlink": sum(1 for r in rows if r.thumbnail_path),
+        "bytes_on_disk": sum(r.size_bytes for r in rows),
+        "missing_ids": missing,
+    }
+
+
+def count_tag_associations(session: Session, *, tag_id: int) -> int:
+    """COUNT(*) FROM image_tag WHERE tag_id=?. For Tier-B prompt."""
+    return session.execute(
+        select(func.count())
+        .select_from(image_tag)
+        .where(image_tag.c.tag_id == tag_id)
+    ).scalar_one()
+
+
+def find_unused_tags(
+    session: Session, *, limit: int | None = None,
+) -> list[Tag]:
+    """Tags with no image_tag rows AND no series_page rows.
+
+    Sorted by name. Used by both dry-run preview and the live prune.
+    A tag is "unused" iff it has zero rows in image_tag AND zero rows
+    in series_page (so we don't accidentally prune a series tag that
+    happens to have no images yet).
+    """
+    used_via_image_tag = select(image_tag.c.tag_id).distinct()
+    used_via_series = select(SeriesPage.series_tag_id).where(
+        SeriesPage.series_tag_id.is_not(None)
+    ).distinct()
+    stmt = (
+        select(Tag)
+        .where(Tag.id.not_in(used_via_image_tag))
+        .where(Tag.id.not_in(used_via_series))
+        .order_by(Tag.name)
+    )
+    if limit is not None:
+        stmt = stmt.limit(limit)
+    return list(session.execute(stmt).scalars().all())