feat: 球队实体一致性 — 归一化咽喉 + team_aliases 别名机制

events/standings 创建 Team 前均经 team_names.normalize(已有,确认),
TeamRepository.get_or_create 收敛为归一化唯一咽喉 + info 日志。

新增 team_aliases 表(NFKD 归一别名 → teams.id FK CASCADE),
定位三步链:normalize(name) → teams.name → team_aliases → insert。
不自动合并历史重复队;提供 POST /api/v1/admin/teams/aliases 显式添加。

迁移 0020_team_aliases + Admin 别名管理端点(admin_teams.py)。
全量测试 270 通过。
This commit is contained in:
shangfangjian
2026-09-22 00:27:53 +08:00
parent 4b0d6ee58a
commit e15b554ba3
10 changed files with 290 additions and 15 deletions
+4
View File
@@ -15,11 +15,15 @@ from fastapi import APIRouter
from src.api.routes.admin_config import router as admin_config_router
from src.api.routes.admin_datasources import router as admin_datasources_router
from src.api.routes.admin_ingest_jobs import router as admin_ingest_jobs_router
from src.api.routes.admin_llm import router as admin_llm_router
from src.api.routes.admin_quality import router as admin_quality_router
from src.api.routes.admin_teams import router as admin_teams_router
router = APIRouter()
router.include_router(admin_datasources_router)
router.include_router(admin_config_router)
router.include_router(admin_ingest_jobs_router)
router.include_router(admin_llm_router)
router.include_router(admin_quality_router)
router.include_router(admin_teams_router)
+60
View File
@@ -0,0 +1,60 @@
"""后台管理:球队别名管理(只读列表 + 添加别名)。
归一名(teams.name)是球队唯一键;别名(team_aliases)是同一球队的不同写法
(大小写/译名/缩写)到归一后 teams.id 的映射。入库时 normalize(name) 依次查
teams.name 与 team_aliases,命中即复用,避免重复 Team。
不自动合并历史重复队;需显式添加别名(或先 SQL/再经由此接口)。
"""
from __future__ import annotations
import logging
from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy import desc, select
from src.api.deps import require_admin
from src.api.schemas import TeamAliasIn, TeamAliasOut
from src.db.base import AsyncSession, get_db_read
from src.db.models import Team, TeamAlias
from src.db.repositories import TeamRepository
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/v1/admin", tags=["admin"], dependencies=[Depends(require_admin)])
@router.get("/teams/aliases", response_model=list[TeamAliasOut])
async def list_team_aliases(db: AsyncSession = Depends(get_db_read)):
"""列出所有球队别名(最新在前)。"""
rows = (await db.execute(select(TeamAlias).order_by(desc(TeamAlias.created_at)).limit(200))).scalars().all()
return [
TeamAliasOut(
alias_normalized=r.alias_normalized,
team_id=r.team_id,
original_alias=r.original_alias,
)
for r in rows
]
@router.post("/teams/aliases", response_model=TeamAliasOut, status_code=201)
async def add_team_alias(req: TeamAliasIn, db: AsyncSession = Depends(get_db_read)):
"""为已有 Team 添加别名(幂等:重复添加会更新指向)。
不自动合并历史重复队。若需合并 A→B:先为 A 的归一名添加别名指向 B,
再人工确认 A 是否仍有独立引用。
"""
# 校验目标 Team 存在
team = await db.get(Team, req.team_id)
if team is None:
raise HTTPException(404, f"目标 Team 不存在: id={req.team_id}")
repo = TeamRepository(db)
row = await repo.add_alias(req.alias, req.team_id)
logger.info("添加 Team 别名: %s -> team_id=%s", req.alias, req.team_id)
return TeamAliasOut(
alias_normalized=row.alias_normalized,
team_id=row.team_id,
original_alias=row.original_alias,
)
+35
View File
@@ -117,6 +117,19 @@ class IngestBzzoiroRequest(BaseModel):
season: str | None = Field(None, description="standings 赛季,如 '2026-2027';空 = 当前赛季")
class TeamAliasIn(BaseModel):
"""POST /api/v1/admin/teams/aliases 请求体:为已有 Team 添加别名。"""
alias: str = Field(..., min_length=1, max_length=120, description="球队别名(原始写法)")
team_id: int = Field(..., gt=0, description="归一后的目标 teams.id")
class TeamAliasOut(BaseModel):
alias_normalized: str
team_id: int
original_alias: str
class IngestResponse(BaseModel):
leagues: dict
total_inserted: int
@@ -124,6 +137,28 @@ class IngestResponse(BaseModel):
errors: list[str] = []
class IngestBzzoiroResponse(BaseModel):
"""POST /api/v1/ingest/bzzoiro 响应:兼容原 message 字段,新增 job_id 供轮询。"""
ok: bool = True
job_id: str = Field(..., description="采集任务 ID(GET /api/v1/admin/ingest/jobs/{job_id} 轮询)")
message: str = ""
class IngestJobOut(BaseModel):
"""采集任务状态详情。"""
id: str
task: str
params: dict
status: str # pending | running | success | failed
result: dict | None = None
error: str | None = None
created_at: datetime | None = None
started_at: datetime | None = None
finished_at: datetime | None = None
class ScheduleIn(BaseModel):
id: str = Field(..., description="任务唯一标识,如 'daily-events'")
task: str = Field(..., description="events / standings / stats / all")
+45
View File
@@ -56,6 +56,22 @@ class Team(Base):
away_matches: Mapped[list["Match"]] = relationship(foreign_keys="Match.away_team_id", back_populates="away_team")
class TeamAlias(Base):
"""球队别名:同一球队的不同写法(大小写/译名/缩写)映射到归一后的 teams.id。
入库流程(get_or_create):normalize(name) → 查 teams.name → 查 team_aliases
→ 都没有再 insert 新 Team。别名不自动合并历史重复队,需显式添加。
alias_normalized 为 normalize(别名)后的稳定幂等键,用作 PK 避免重复插入。
"""
__tablename__ = "team_aliases"
# normalize(别名)后的值,稳定幂等,用作主键
alias_normalized: Mapped[str] = mapped_column(String(120), primary_key=True)
team_id: Mapped[int] = mapped_column(ForeignKey("teams.id", ondelete="CASCADE"), nullable=False)
original_alias: Mapped[str] = mapped_column(String(120), nullable=False) # 原始写法(保留供参考)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
class Match(Base):
__tablename__ = "matches"
@@ -324,6 +340,35 @@ class RawEvent(Base):
)
class IngestJob(Base):
"""采集任务状态:跟踪每次触后台采集任务的执行进度与结果。
POST /api/v1/ingest/bzzoiro 触发时写入(pending→running→success/failed),
前端 Collection 页据此轮询到终态,替代此前"30 秒后盲标完成"的模拟。
分批 get_uow / BzzoiroSource / IngestFailure / Bronze/Lineage 均不受影响
(本表仅作状态追踪,不介入采集事务)。
"""
__tablename__ = "ingest_jobs"
id: Mapped[str] = mapped_column(String(36), primary_key=True) # uuid4
task: Mapped[str] = mapped_column(String(20), nullable=False)
params: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict)
status: Mapped[str] = mapped_column(String(20), nullable=False, server_default="pending")
result: Mapped[dict | None] = mapped_column(JSONB)
error: Mapped[str | None] = mapped_column(Text)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
__table_args__ = (
Index("ix_ingest_job_status_created", "status", "created_at"),
CheckConstraint(
"status IN ('pending', 'running', 'success', 'failed')",
name="ck_ingest_job_status",
),
)
class IngestFailure(Base):
"""采集失败死信:记录失败原因、重试次数与下次重试时间。
+45 -10
View File
@@ -114,24 +114,59 @@ class TeamRepository:
async def get_or_create(self, name: str, *, name_zh: str | None = None) -> Team:
"""按名获取球队,不存在则创建(name_zh 供 bzzoiro 管线写中文名)。
归一化咽喉:所有入库 Team.name 必须经过 team_names.normalize,
此处统一收敛,避免各调用点散落归一化逻辑导致重复 Team。
归一化咽喉 + 别名查找,三步定位:
1) normalize(name) → 查 teams.name
2) 查 team_aliases(以 normalize(name) 为幂等键)→ 复用已映射的 teams.id
3) 都没有 → insert 新 Team(归一名)
创建新 Team 时 info 打出原始名与归一后的规范名,便于排查重名。
不自动合并历史重复队;需显式添加别名。
"""
from src.data.team_names import normalize as normalize_name
from src.db.models import TeamAlias
normalized = normalize_name(name) or name.strip()
# 1) 归一名直查 teams
team = await self.get_by_name(normalized)
if team is None:
logger.info(
"创建新 Team: %s -> %s",
name, normalized,
)
team = Team(name=normalized, name_zh=name_zh)
self._session.add(team)
await self._session.flush()
if team is not None:
return team
# 2) 别名查找:normalize(别名) 作为幂等键,命中即复用已有 Team
alias = await self._session.get(TeamAlias, normalized)
if alias is not None:
team = await self._session.get(Team, alias.team_id)
if team is not None:
logger.info("Team 别名命中: %s -> %s(已有 id=%s)", name, normalized, team.id)
return team
# 3) 新建 Team(归一名)
logger.info("创建新 Team: %s -> %s", name, normalized)
team = Team(name=normalized, name_zh=name_zh)
self._session.add(team)
await self._session.flush()
return team
async def add_alias(self, alias: str, team_id: int) -> TeamAlias:
"""为已有 Team 添加别名。
幂等:以 normalize(alias) 为 PK,重复添加同一别名会 upsert。
不自动合并历史重复队,仅建立别名映射。
"""
from src.data.team_names import normalize as normalize_name
from src.db.models import TeamAlias
normalized = normalize_name(alias) or alias.strip()
existing = await self._session.get(TeamAlias, normalized)
if existing is not None:
existing.team_id = team_id # 允许重新指向
existing.original_alias = alias
await self._session.flush()
return existing
row = TeamAlias(alias_normalized=normalized, team_id=team_id, original_alias=alias)
self._session.add(row)
await self._session.flush()
return row
async def get_all_by_names(self, names: list[str]) -> dict[str, Team]:
"""批量获取球队,返回 name → Team 映射。"""
if not names: