bvandeusen/FabledCurator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 33 Wiki Activity

feat(tags): legacy-tag purge also catches source:* general tags

Browse Source 
Operator-confirmed 2026-05-28: the BlenderKnight:* tags are `archive`
kind (caught by the kind purge), but the `source:patreon`-style tags
are IR's old `source` kind that fell back to `general` during migration
(FC's enum has no `source` kind) — so they can't be matched by kind.

Broadened the purge to a two-rule match and renamed it for accuracy
(all dev-only, unreleased):
- cleanup_service.purge_tags_by_kind → purge_legacy_tags. Predicate is
  now `kind IN (archive, post, artist) OR name LIKE 'source:%'`
  (LEGACY_NAME_PREFIXES). Preview classifies each row into by_kind OR
  by_prefix (source:* counts once under the prefix bucket regardless of
  its general kind).
- endpoint /tags/purge-retired-kinds → /tags/purge-legacy. dry-run
  returns by_kind + by_prefix + count + sample.
- store purgeRetiredKindTags → purgeLegacyTags.
- Tag Maintenance card copy + breakdown updated to show both buckets;
  button reads "Preview/Delete legacy tags".

Tests updated + extended: dry-run reports by_kind {archive,post,artist}
AND by_prefix {source:*}, plain general/character tags survive; commit
deletes both the kind-matched and source:*-matched rows and leaves the
rest.
This commit is contained in:
Bryan Van Deusen
2026-05-28 01:20:41 -04:00
parent e1fc65bd1b
commit bf8eb4468f
5 changed files with 104 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/api/admin.py
+11 -9
View File
@@ -6,6 +6,7 @@ Five action surfaces:
DELETE /api/admin/tags/<int:tag_id> (Tier B)
POST /api/admin/tags/<int:dest_id>/merge (Tier B)
POST /api/admin/tags/prune-unused (Tier A)
POST /api/admin/tags/purge-legacy (Tier A)
GET /api/admin/tags/<int:tag_id>/usage-count (helper)
Tier-C ops take a dry_run body flag (returns projection inline,
@@ -208,20 +209,21 @@ async def tags_prune_unused():
return jsonify(result)
@admin_bp.route("/tags/purge-retired-kinds", methods=["POST"])
async def tags_purge_retired_kinds():
"""Tier-A: delete tags whose kind is a system/legacy kind FC no
longer creates (archive / post / artist — the IR-migration leftovers
like `BlenderKnight:Hannah_BJ_Loops`). dry-run preview returns
per-kind counts + a sample so the UI can show exactly what'll go
before the operator confirms with dry_run=false."""
from ..services.cleanup_service import purge_tags_by_kind
@admin_bp.route("/tags/purge-legacy", methods=["POST"])
async def tags_purge_legacy():
"""Tier-A: delete legacy IR-migration tags — archive/post/artist
kinds (e.g. `BlenderKnight:Hannah_BJ_Loops`) PLUS general tags with
a legacy name prefix (`source:*`, from IR's source kind that fell
back to general). dry-run preview returns per-kind + per-prefix
counts + a sample so the UI shows exactly what'll go before the
operator confirms with dry_run=false."""
from ..services.cleanup_service import purge_legacy_tags
body = await request.get_json(silent=True) or {}
dry_run = bool(body.get("dry_run", False))
async with get_session() as session:
result = await session.run_sync(
lambda sync_sess: purge_tags_by_kind(sync_sess, dry_run=dry_run)
lambda sync_sess: purge_legacy_tags(sync_sess, dry_run=dry_run)
)
return jsonify(result)
backend/app/services/cleanup_service.py
+49 -25
View File
@@ -16,7 +16,7 @@ from datetime import UTC, datetime
from pathlib import Path
from typing import Any
from sqlalchemy import func, select, update
from sqlalchemy import func, or_, select, update
from sqlalchemy.orm import Session
from ..models import Artist, ImageRecord, LibraryAuditRun, Tag
@@ -369,46 +369,70 @@ def prune_unused_tags(session: Session, *, dry_run: bool = False) -> dict:
return {"deleted": len(ids), "sample_names": sample}
# System/legacy tag kinds that FC no longer creates: the tag input only
# makes character/fandom/series/general; provenance (post grouping) and
# archive membership are their own systems now, and artists are
# first-class Artist/Source rows. These linger only on IR-migrated rows.
# meta/rating were hard-deleted by alembic 0023, so they're not listed.
# Legacy tags FC no longer uses, in two shapes:
# (1) kinds the tag input never produces — archive/post/artist.
# provenance (post grouping) + archive membership are their own
# systems now, and artists are first-class Artist/Source rows.
# meta/rating were already hard-deleted by alembic 0023.
# (2) name prefixes from IR kinds FC never adopted — `source:*`.
# ImageRepo had a `source` kind; FC's enum doesn't, so ir_ingest
# fell those back to `general` (kind=general, name="source:patreon"
# etc.). They can't be caught by kind, so we match the name prefix.
PURGEABLE_TAG_KINDS = ("archive", "post", "artist")
LEGACY_NAME_PREFIXES = ("source:",)
def purge_tags_by_kind(
session: Session, *, kinds: tuple[str, ...] = PURGEABLE_TAG_KINDS,
dry_run: bool = False,
) -> dict:
"""Count (dry_run) or delete all tags whose kind is in `kinds`.
def _legacy_tag_predicate():
name_clauses = [Tag.name.like(f"{p}%") for p in LEGACY_NAME_PREFIXES]
return or_(Tag.kind.in_(PURGEABLE_TAG_KINDS), *name_clauses)
def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
"""Count (dry_run) or delete legacy IR-migration tags: archive/post/
artist-kind tags PLUS general tags whose name matches a legacy
prefix (source:*).
CASCADE on image_tag / tag_alias / tag_allowlist /
tag_reference_embedding / tag_suggestion_rejection / series_page
clears the related rows on the parent DELETE.
Returns:
{"by_kind": {kind: count, ...}, "count": total,
"sample_names": [first 50], and on live runs "deleted": total}
{"by_kind": {kind: count, ...}, # kind-matched rows
"by_prefix": {"source:*": count}, # name-prefix-matched rows
"count": total, "sample_names": [first 50],
and on live runs "deleted": total}
"""
predicate = _legacy_tag_predicate()
rows = session.execute(
select(Tag.id, Tag.name, Tag.kind).where(Tag.kind.in_(kinds))
select(Tag.id, Tag.name, Tag.kind).where(predicate)
).all()
by_kind: dict[str, int] = {}
for _id, _name, kind in rows:
key = kind.value if hasattr(kind, "value") else str(kind)
by_kind[key] = by_kind.get(key, 0) + 1
by_prefix: dict[str, int] = {}
for _id, name, kind in rows:
# Classify by name-prefix first so a source:* row counts once,
# under the prefix bucket, regardless of its (general) kind.
matched_prefix = next(
(p for p in LEGACY_NAME_PREFIXES if name.startswith(p)), None,
)
if matched_prefix is not None:
label = f"{matched_prefix}*"
by_prefix[label] = by_prefix.get(label, 0) + 1
else:
key = kind.value if hasattr(kind, "value") else str(kind)
by_kind[key] = by_kind.get(key, 0) + 1
sample = [name for _id, name, _kind in rows[:50]]
total = len(rows)
if dry_run:
return {"by_kind": by_kind, "count": total, "sample_names": sample}
if total:
session.execute(Tag.__table__.delete().where(Tag.kind.in_(kinds)))
session.commit()
return {
"by_kind": by_kind, "count": total, "deleted": total,
"sample_names": sample,
result = {
"by_kind": by_kind, "by_prefix": by_prefix,
"count": total, "sample_names": sample,
}
if dry_run:
return result
if total:
session.execute(Tag.__table__.delete().where(predicate))
session.commit()
result["deleted"] = total
return result
# ---------------------------------------------------------------------------
frontend/src/components/settings/TagMaintenanceCard.vue
+17 -12
View File
@@ -48,12 +48,14 @@
<v-divider class="my-5" />
<p class="fc-muted text-body-2 mb-4">
Purge tags with retired/system kinds FC no longer uses
(<code>archive</code>, <code>post</code>, <code>artist</code>) —
IR-migration leftovers like
<code>BlenderKnight:Hannah_BJ_Loops</code>. Provenance and
artists are their own systems now, so these tag rows are pure
noise. Removes them from every image.
Purge legacy IR-migration tags FC no longer uses: retired/system
kinds (<code>archive</code>, <code>post</code>,
<code>artist</code> — e.g.
<code>BlenderKnight:Hannah_BJ_Loops</code>) plus
<code>source:*</code> tags (ImageRepo's old <code>source</code>
kind, which migrated to <code>general</code>). Provenance and
artists are their own systems now, so these are pure noise.
Removes them from every image.
</p>
<v-btn
@@ -62,14 +64,17 @@
:loading="loadingKindPreview"
class="mb-3"
@click="onKindPreview"
>Preview retired-kind tags</v-btn>
>Preview legacy tags</v-btn>
<div v-if="kindPreview">
<p class="text-body-2 mb-2">
<strong>{{ kindPreview.count }}</strong> tag(s) of retired kinds.
<strong>{{ kindPreview.count }}</strong> legacy tag(s).
<span v-for="(n, k) in kindPreview.by_kind" :key="k" class="fc-muted">
{{ k }}: {{ n }}&nbsp;&nbsp;
</span>
<span v-for="(n, p) in kindPreview.by_prefix" :key="p" class="fc-muted">
{{ p }}: {{ n }}&nbsp;&nbsp;
</span>
</p>
<div v-if="kindPreview.sample_names?.length" class="fc-name-grid mb-3">
<span v-for="n in kindPreview.sample_names" :key="n" class="fc-name">
@@ -82,7 +87,7 @@
:disabled="!kindPreview.count"
:loading="kindCommitting"
@click="onKindCommit"
>Delete {{ kindPreview.count }} retired-kind tag(s)</v-btn>
>Delete {{ kindPreview.count }} legacy tag(s)</v-btn>
</div>
</v-card-text>
</v-card>
@@ -123,7 +128,7 @@ async function onCommit() {
async function onKindPreview() {
loadingKindPreview.value = true
try {
kindPreview.value = await store.purgeRetiredKindTags({ dryRun: true })
kindPreview.value = await store.purgeLegacyTags({ dryRun: true })
} finally {
loadingKindPreview.value = false
}
@@ -132,8 +137,8 @@ async function onKindPreview() {
async function onKindCommit() {
kindCommitting.value = true
try {
await store.purgeRetiredKindTags({ dryRun: false })
kindPreview.value = { count: 0, by_kind: {}, sample_names: [] }
await store.purgeLegacyTags({ dryRun: false })
kindPreview.value = { count: 0, by_kind: {}, by_prefix: {}, sample_names: [] }
} finally {
kindCommitting.value = false
}
frontend/src/stores/admin.js
+3 -3
View File
@@ -114,11 +114,11 @@ export const useAdminStore = defineStore('admin', () => {
}
}
async function purgeRetiredKindTags({ dryRun = true } = {}) {
async function purgeLegacyTags({ dryRun = true } = {}) {
lastError.value = null
try {
return await api.post(
'/api/admin/tags/purge-retired-kinds',
'/api/admin/tags/purge-legacy',
{ body: { dry_run: dryRun } },
)
} catch (e) {
@@ -161,7 +161,7 @@ export const useAdminStore = defineStore('admin', () => {
mergeTags,
tagUsageCount,
pruneUnusedTags,
purgeRetiredKindTags,
purgeLegacyTags,
pollTaskUntilDone,
}
})
tests/test_api_admin.py
+24 -17
View File
@@ -367,50 +367,57 @@ async def test_prune_unused_commit_deletes_and_returns_count(client, db):
@pytest.mark.asyncio
async def test_purge_retired_kinds_dry_run_counts_by_kind(client, db):
async def test_purge_legacy_dry_run_counts_by_kind_and_prefix(client, db):
db.add_all([
Tag(name="BlenderKnight:Hannah_BJ_Loops", kind=TagKind.archive),
Tag(name="BlenderKnight:May Animation", kind=TagKind.post),
Tag(name="SomeArtist", kind=TagKind.artist),
# IR `source` kind fell back to general during migration —
# caught by the source:* name prefix, not by kind.
Tag(name="source:patreon", kind=TagKind.general),
Tag(name="blonde hair", kind=TagKind.general), # must survive
])
await db.commit()
resp = await client.post(
"/api/admin/tags/purge-retired-kinds", json={"dry_run": True},
"/api/admin/tags/purge-legacy", json={"dry_run": True},
)
body = await resp.get_json()
assert body["count"] == 3
assert body["count"] == 4
assert body["by_kind"] == {"archive": 1, "post": 1, "artist": 1}
assert body["by_prefix"] == {"source:*": 1}
assert "blonde hair" not in body["sample_names"]
assert "source:patreon" in body["sample_names"]
@pytest.mark.asyncio
async def test_purge_retired_kinds_commit_deletes_only_retired(client, db):
async def test_purge_legacy_commit_deletes_only_legacy(client, db):
from sqlalchemy import func, select
db.add_all([
Tag(name="arch1", kind=TagKind.archive),
Tag(name="post1", kind=TagKind.post),
Tag(name="source:fanbox", kind=TagKind.general),
Tag(name="keepme", kind=TagKind.general),
Tag(name="char1", kind=TagKind.character),
])
await db.commit()
resp = await client.post(
"/api/admin/tags/purge-retired-kinds", json={"dry_run": False},
"/api/admin/tags/purge-legacy", json={"dry_run": False},
)
body = await resp.get_json()
assert body["deleted"] == 2
assert body["deleted"] == 2 # arch1 + source:fanbox
# general + character tags survive.
surviving = (await db.execute(
select(func.count()).select_from(Tag)
.where(Tag.kind.in_([TagKind.general, TagKind.character]))
# The plain general + character tags survive.
keep = (await db.execute(
select(Tag.name).where(Tag.name.in_(["keepme", "char1"]))
)).scalars().all()
assert set(keep) == {"keepme", "char1"}
# No archive/post/artist or source:* left.
gone = (await db.execute(
select(func.count()).select_from(Tag).where(
(Tag.kind.in_([TagKind.archive, TagKind.post, TagKind.artist]))
| (Tag.name.like("source:%"))
)
)).scalar_one()
assert surviving >= 2
retired_left = (await db.execute(
select(func.count()).select_from(Tag)
.where(Tag.kind.in_([TagKind.archive, TagKind.post, TagKind.artist]))
)).scalar_one()
assert retired_left == 0
assert gone == 0