fc3k: cleanup_service mutations — unlink primitive, artist cascade, bulk image delete, tag delete, prune unused

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

backend/app/services/cleanup_service.py

@@ -12,6 +12,8 @@ re-exports from this module and then delete the wrapper.
 """
 from __future__ import annotations
 
+from pathlib import Path
+
 from sqlalchemy import func, select
 from sqlalchemy.orm import Session
 
@@ -154,3 +156,212 @@ def find_unused_tags(
     if limit is not None:
         stmt = stmt.limit(limit)
     return list(session.execute(stmt).scalars().all())
+
+
+def unlink_image_files(
+    image: ImageRecord, images_root: Path,
+) -> dict:
+    """Best-effort unlink of all on-disk files for an ImageRecord.
+
+    Targets: image.path (original), image.thumbnail_path (cached
+    thumbnail), and the computed thumbs path at
+    /images/thumbs/<sha256[:3]>/<sha256>.(jpg|png|webp) (tries all
+    three extensions; missing extension is silently OK).
+
+    Returns {"original": bool, "thumbnail": bool}. Missing files
+    count as success (missing_ok semantics). OSErrors are swallowed
+    and reported as False so the calling DB delete still proceeds.
+    """
+    out = {"original": False, "thumbnail": False}
+    if image.path:
+        try:
+            Path(image.path).unlink(missing_ok=True)
+            out["original"] = True
+        except OSError:
+            out["original"] = False
+    # Custom thumbnail_path (when set) — try it first.
+    if image.thumbnail_path:
+        try:
+            Path(image.thumbnail_path).unlink(missing_ok=True)
+            out["thumbnail"] = True
+        except OSError:
+            out["thumbnail"] = False
+    # Convention thumbs dir — try all extensions; missing OK.
+    if image.sha256:
+        bucket = image.sha256[:3]
+        for ext in ("jpg", "png", "webp"):
+            try:
+                (images_root / "thumbs" / bucket / f"{image.sha256}.{ext}").unlink(
+                    missing_ok=True,
+                )
+            except OSError:
+                pass
+    return out
+
+
+def delete_artist_cascade(
+    session: Session, *, artist_id: int, images_root: Path,
+) -> dict:
+    """Batched delete of an artist's images + the artist row.
+
+    Mirrors the cleanup_artist_async pattern: 500-row batches,
+    commit between batches so partial progress survives a worker
+    kill. Idempotent on missing artist (returns zeroed counts).
+    Postgres cascades handle image_tag / image_provenance /
+    series_page / tag_suggestion_rejection from ImageRecord delete,
+    and source / post / download_event / etc. from Artist delete
+    (via Artist.sources cascade="all, delete-orphan").
+    """
+    artist = session.get(Artist, artist_id)
+    if artist is None:
+        return {
+            "artist": None,
+            "summary": {
+                "images_deleted": 0,
+                "files_deleted": 0,
+                "thumbs_deleted": 0,
+                "import_tasks_nulled": 0,
+                "files_failed": 0,
+            },
+        }
+    artist_info = {"id": artist.id, "name": artist.name, "slug": artist.slug}
+
+    images_deleted = 0
+    files_deleted = 0
+    thumbs_deleted = 0
+    files_failed = 0
+
+    while True:
+        rows = session.execute(
+            select(ImageRecord)
+            .where(ImageRecord.artist_id == artist.id)
+            .limit(500)
+        ).scalars().all()
+        if not rows:
+            break
+        for img in rows:
+            unlinked = unlink_image_files(img, images_root)
+            if unlinked["original"]:
+                files_deleted += 1
+            else:
+                files_failed += 1
+            if unlinked["thumbnail"]:
+                thumbs_deleted += 1
+            session.delete(img)
+            images_deleted += 1
+        session.commit()
+
+    # ImportTask.result_image_id FK is SET NULL on image delete (Postgres
+    # handles this in the cascade above). We don't separately count those
+    # in FC-3k — the legacy cleanup_artist_async did it via
+    # source_path_prefix matching that's out of scope here.
+    import_tasks_nulled = 0
+
+    session.delete(artist)
+    session.commit()
+
+    return {
+        "artist": artist_info,
+        "summary": {
+            "images_deleted": images_deleted,
+            "files_deleted": files_deleted,
+            "thumbs_deleted": thumbs_deleted,
+            "import_tasks_nulled": import_tasks_nulled,
+            "files_failed": files_failed,
+        },
+    }
+
+
+def delete_images(
+    session: Session, *, image_ids: list[int], images_root: Path,
+) -> dict:
+    """Delete a list of images in 500-row batches with commit between.
+
+    Postgres CASCADE on image_tag / image_provenance / series_page /
+    tag_suggestion_rejection / post_attachment(FK SET NULL) handles
+    the DB side; this function handles file unlinks first then row
+    deletes. Idempotent on missing IDs (returned as missing_ids;
+    no error). On partial OSError, the row is still deleted and
+    files_failed is incremented.
+    """
+    if not image_ids:
+        return {
+            "images_deleted": 0,
+            "files_deleted": 0,
+            "thumbs_deleted": 0,
+            "files_failed": 0,
+            "missing_ids": [],
+        }
+
+    seen_ids: set[int] = set()
+    images_deleted = 0
+    files_deleted = 0
+    thumbs_deleted = 0
+    files_failed = 0
+
+    pending = list(image_ids)
+    while pending:
+        batch_ids = pending[:500]
+        pending = pending[500:]
+        rows = session.execute(
+            select(ImageRecord).where(ImageRecord.id.in_(batch_ids))
+        ).scalars().all()
+        for img in rows:
+            seen_ids.add(img.id)
+            unlinked = unlink_image_files(img, images_root)
+            if unlinked["original"]:
+                files_deleted += 1
+            else:
+                files_failed += 1
+            if unlinked["thumbnail"]:
+                thumbs_deleted += 1
+            session.delete(img)
+            images_deleted += 1
+        session.commit()
+
+    missing = sorted(set(image_ids) - seen_ids)
+    return {
+        "images_deleted": images_deleted,
+        "files_deleted": files_deleted,
+        "thumbs_deleted": thumbs_deleted,
+        "files_failed": files_failed,
+        "missing_ids": missing,
+    }
+
+
+def delete_tag(session: Session, *, tag_id: int) -> dict:
+    """Simple DELETE FROM tag WHERE id=?.
+
+    Postgres cascades the rest (image_tag, tag_alias, tag_allowlist,
+    tag_reference_embedding, tag_suggestion_rejection, series_page).
+    Returns counts BEFORE delete so the caller can surface them.
+    Raises LookupError if tag_id not found.
+    """
+    tag = session.get(Tag, tag_id)
+    if tag is None:
+        raise LookupError(f"tag id not found: {tag_id}")
+    associations_count = count_tag_associations(session, tag_id=tag_id)
+    info = {"id": tag.id, "name": tag.name, "kind": tag.kind.value}
+    session.delete(tag)
+    session.commit()
+    return {"deleted": info, "associations_removed": associations_count}
+
+
+def prune_unused_tags(session: Session, *, dry_run: bool = False) -> dict:
+    """Find tags with zero references and (unless dry_run) delete them.
+
+    Returns:
+      dry_run=True:  {"count": N, "sample_names": [first 50]}
+      dry_run=False: {"deleted": N, "sample_names": [first 50]}
+    """
+    unused = find_unused_tags(session)
+    sample = [t.name for t in unused[:50]]
+    if dry_run:
+        return {"count": len(unused), "sample_names": sample}
+    ids = [t.id for t in unused]
+    if ids:
+        session.execute(
+            Tag.__table__.delete().where(Tag.id.in_(ids))
+        )
+        session.commit()
+    return {"deleted": len(ids), "sample_names": sample}