feat(fc2b): add AliasService — (name, category) -> canonical tag

resolve() / resolve_many() (batch, used by the suggestion read path),
idempotent create, remove, list_all. Category-scoped so 'naruto' as
character vs copyright map to different canonicals. Tests marked
integration (real DB).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-15 07:37:13 -04:00
parent 696c17fe29
commit 03c6a61673
2 changed files with 189 additions and 0 deletions
+104
View File
@@ -0,0 +1,104 @@
"""Alias resolution + CRUD.
A tag_alias maps (model_name, model_category) -> canonical Tag. Resolution
happens at suggestion-read time so raw tagger_predictions stay unmolested.
"""
from collections.abc import Sequence
from dataclasses import dataclass
from sqlalchemy import delete, select
from sqlalchemy.dialects.postgresql import insert
from sqlalchemy.ext.asyncio import AsyncSession
from ...models import Tag, TagAlias
@dataclass(frozen=True)
class AliasRow:
alias_string: str
alias_category: str
canonical_tag_id: int
canonical_tag_name: str
class AliasService:
def __init__(self, session: AsyncSession):
self.session = session
async def resolve(self, name: str, category: str) -> Tag | None:
"""Return the canonical Tag for (name, category), or None if no alias."""
stmt = (
select(Tag)
.join(TagAlias, TagAlias.canonical_tag_id == Tag.id)
.where(TagAlias.alias_string == name)
.where(TagAlias.alias_category == category)
)
return (await self.session.execute(stmt)).scalar_one_or_none()
async def resolve_many(
self, pairs: list[tuple[str, str]]
) -> dict[tuple[str, str], Tag]:
"""Batch-resolve. Returns only the pairs that have an alias.
Used by SuggestionService so it does one query instead of N.
"""
if not pairs:
return {}
strings = {p[0] for p in pairs}
stmt = (
select(TagAlias, Tag)
.join(Tag, Tag.id == TagAlias.canonical_tag_id)
.where(TagAlias.alias_string.in_(strings))
)
rows = (await self.session.execute(stmt)).all()
wanted = set(pairs)
out: dict[tuple[str, str], Tag] = {}
for alias, tag in rows:
key = (alias.alias_string, alias.alias_category)
if key in wanted:
out[key] = tag
return out
async def create(
self, alias_string: str, alias_category: str, canonical_tag_id: int
) -> None:
"""Idempotent create (ON CONFLICT DO NOTHING)."""
stmt = insert(TagAlias).values(
alias_string=alias_string,
alias_category=alias_category,
canonical_tag_id=canonical_tag_id,
)
stmt = stmt.on_conflict_do_nothing(
index_elements=["alias_string", "alias_category"]
)
await self.session.execute(stmt)
async def remove(self, alias_string: str, alias_category: str) -> None:
await self.session.execute(
delete(TagAlias)
.where(TagAlias.alias_string == alias_string)
.where(TagAlias.alias_category == alias_category)
)
async def list_all(self) -> Sequence[AliasRow]:
stmt = (
select(
TagAlias.alias_string,
TagAlias.alias_category,
TagAlias.canonical_tag_id,
Tag.name,
)
.join(Tag, Tag.id == TagAlias.canonical_tag_id)
.order_by(TagAlias.alias_string.asc())
)
rows = (await self.session.execute(stmt)).all()
return [
AliasRow(
alias_string=r[0],
alias_category=r[1],
canonical_tag_id=r[2],
canonical_tag_name=r[3],
)
for r in rows
]
+85
View File
@@ -0,0 +1,85 @@
import pytest
from backend.app.models import TagKind
from backend.app.services.ml.aliases import AliasService
from backend.app.services.tag_service import TagService
pytestmark = pytest.mark.integration
@pytest.mark.asyncio
async def test_create_and_resolve(db):
tags = TagService(db)
canonical = await tags.find_or_create("Sasuke Uchiha", TagKind.character)
aliases = AliasService(db)
await aliases.create("uchiha_sasuke", "character", canonical.id)
resolved = await aliases.resolve("uchiha_sasuke", "character")
assert resolved is not None
assert resolved.id == canonical.id
@pytest.mark.asyncio
async def test_resolve_returns_none_when_no_alias(db):
aliases = AliasService(db)
assert await aliases.resolve("nonexistent", "general") is None
@pytest.mark.asyncio
async def test_category_scoped(db):
tags = TagService(db)
char = await tags.find_or_create("Naruto", TagKind.character)
copy = await tags.find_or_create("Naruto", TagKind.fandom)
aliases = AliasService(db)
await aliases.create("naruto", "character", char.id)
await aliases.create("naruto", "copyright", copy.id)
assert (await aliases.resolve("naruto", "character")).id == char.id
assert (await aliases.resolve("naruto", "copyright")).id == copy.id
@pytest.mark.asyncio
async def test_create_idempotent(db):
tags = TagService(db)
t = await tags.find_or_create("X", TagKind.general)
aliases = AliasService(db)
await aliases.create("x_alias", "general", t.id)
await aliases.create("x_alias", "general", t.id) # no error
assert (await aliases.resolve("x_alias", "general")).id == t.id
@pytest.mark.asyncio
async def test_resolve_many(db):
tags = TagService(db)
a = await tags.find_or_create("Alice", TagKind.character)
b = await tags.find_or_create("Bob", TagKind.artist)
aliases = AliasService(db)
await aliases.create("alice_x", "character", a.id)
await aliases.create("bob_x", "artist", b.id)
out = await aliases.resolve_many(
[("alice_x", "character"), ("bob_x", "artist"), ("unknown", "general")]
)
assert out[("alice_x", "character")].id == a.id
assert out[("bob_x", "artist")].id == b.id
assert ("unknown", "general") not in out
@pytest.mark.asyncio
async def test_remove(db):
tags = TagService(db)
t = await tags.find_or_create("Y", TagKind.general)
aliases = AliasService(db)
await aliases.create("y_alias", "general", t.id)
await aliases.remove("y_alias", "general")
assert await aliases.resolve("y_alias", "general") is None
@pytest.mark.asyncio
async def test_list_all(db):
tags = TagService(db)
t = await tags.find_or_create("Z", TagKind.general)
aliases = AliasService(db)
await aliases.create("z1", "general", t.id)
rows = await aliases.list_all()
assert any(r.alias_string == "z1" and r.canonical_tag_name == "Z" for r in rows)