feat: standings Bronze 血缘补齐 + 队名归一 MVP

standings 成功 upsert 后写入 RawEvent(source_record_id=standings:{league}:{season})
+ DataLineage(target_table=standings),与 events/stats 管线对称。

队名归一化收敛到 TeamRepository.get_or_create 唯一咽喉点,
创建新 Team 时 info 日志打出原始名与归一后名;
Admin 新增 GET /api/v1/admin/team-name-duplicates 只读接口,
启发式列出近似重名候选(大小写变体/子串/前缀碰撞),不做自动合并。
This commit is contained in:
shangfangjian
2026-09-21 23:28:46 +08:00
parent 317a5e338a
commit 66f0844798
5 changed files with 685 additions and 5 deletions
+5 -2
View File
@@ -125,7 +125,7 @@ class _FakeDb:
async def test_r2_standings_actually_upserts(monkeypatch):
"""行为测试: 喂一份积分榜 payload,断言真的构造了 Standing 且计数 > 0。"""
import src.data.bzzoiro as bz
from src.db.models import League, Standing, Team
from src.db.models import DataLineage, League, RawEvent, Standing, Team
payload = {
"season": {"start_date": "2025-08-01", "end_date": "2026-05-31"},
@@ -166,7 +166,10 @@ async def test_r2_standings_actually_upserts(monkeypatch):
standings = [o for o in db.added if isinstance(o, Standing)]
assert len(standings) == 2, "应真的构造 Standing 行"
assert all(isinstance(o, (Standing, Team)) for o in db.added)
# standings 采集接线 Bronze 后(RawEvent + DataLineage),add 的对象类型白名单随之放宽
assert all(
isinstance(o, (Standing, Team, RawEvent, DataLineage)) for o in db.added
)
first = standings[0]
assert first.league_id == 42
+288
View File
@@ -0,0 +1,288 @@
"""standings 成功路径 Bronze 层回归测试(RawEvent + DataLineage)。
背景: events/stats 管线成功后均已补写 Bronze 层,唯独 standings 采集
成功后既不留原始载荷,也不留血缘 —— 三条管线的溯源链条在积分榜一环
缺失。本测试守护(与 test_events_bronze.py 对称):
1. 联赛成功 upsert → RawEvent(幂等键=standings:{league}:{season})
+ Lineage(target_table="standings", transform_name="standings_ingest")
2. 更新已有快照(非插入)同样写 Bronze —— 积分榜是快照,刷新即采集
3. RawEvent 幂等: 同 source_record_id 已存在则跳过,血缘照写
4. 基础设施写入失败 → 只 warning,不拖垮采集主流程
5. 抓取失败路径继续走 _safe_write_ingest_failure,且不写 Bronze
范式: 假 db(按查询实体分发预置数据 + 记录 add,flush 分配自增 id)
+ monkeypatch 抓取函数,不依赖真实数据库。
"""
from __future__ import annotations
import pytest
import src.data.bzzoiro as bz
from src.db.models import DataLineage, IngestFailure, League, RawEvent, Standing, Team
def _payload():
"""构造一份最小合法的 bzzoiro /leagues/{id}/standings/ 原始载荷。"""
return {
"season": {"start_date": "2025-08-01", "end_date": "2026-05-31"},
"standings": [
{
"position": 1, "team_name": "Arsenal FC",
"played": 10, "won": 8, "drawn": 1, "lost": 1,
"gf": 22, "ga": 8, "gd": 14, "pts": 25,
"zone": {"key": "champions_league", "label": "Champions League"},
},
{
"position": 2, "team_name": "Chelsea FC",
"played": 10, "won": 6, "drawn": 2, "lost": 2,
"gf": 18, "ga": 12, "gd": 6, "pts": 20,
},
],
}
def _patch_fetch(monkeypatch, payload):
async def _fetch(league_code, season=None):
return payload
monkeypatch.setattr(bz, "fetch_bzzoiro_standings", _fetch)
class _FakeResult:
"""支持 .scalars().all() / .scalar_one_or_none() 的最小假结果集。"""
def __init__(self, items):
self._items = list(items)
def scalars(self):
return self
def __iter__(self):
return iter(self._items)
def all(self):
return self._items
def scalar_one_or_none(self):
return self._items[0] if self._items else None
class _FakeDB:
"""按查询实体分发预置数据;记录 add();flush 为无 id 对象分配自增主键。"""
def __init__(self, leagues=(), teams=(), standings=(), raw_events=()):
self.added = []
self._by_entity = {
League: list(leagues),
Team: list(teams),
Standing: list(standings),
RawEvent: list(raw_events),
}
self._next_id = 0
def add(self, obj):
self.added.append(obj)
async def execute(self, stmt):
entities = set()
for d in (stmt.column_descriptions or []):
entities.add(d.get("entity") or d.get("type"))
for entity, items in self._by_entity.items():
if entity in entities:
return _FakeResult(self._filter(entity, items, stmt))
return _FakeResult([])
@staticmethod
def _filter(entity, items, stmt):
"""RawEvent 查询按 source_record_id 过滤 —— 幂等测试需区分不同键。"""
if entity is RawEvent:
try:
params = stmt.compile().params
except Exception:
return items
rid = next((v for k, v in params.items() if "source_record_id" in k), None)
if rid is not None:
return [i for i in items if i.source_record_id == rid]
return items
async def flush(self):
for obj in self.added:
if getattr(obj, "id", None) is None:
self._next_id += 1
obj.id = self._next_id
def _preset_league():
lg = League(code="EPL", name="Premier League", country="England")
lg.id = 42
return lg
def _raw_events(db):
return [o for o in db.added if isinstance(o, RawEvent)]
def _lineages(db):
return [o for o in db.added if isinstance(o, DataLineage)]
# ============================================================
# 1. 成功 upsert → RawEvent + DataLineage
# ============================================================
class TestStandingsBronzeOnUpsert:
async def test_upsert_writes_raw_event_and_lineage(self, monkeypatch):
_patch_fetch(monkeypatch, _payload())
db = _FakeDB(leagues=[_preset_league()])
result = await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
assert result["errors"] == []
assert result["total_upserted"] == 2
raws = _raw_events(db)
assert len(raws) == 1
raw = raws[0]
assert raw.source_system == "bzzoiro"
# 幂等键: 联赛 + 实际入库的赛季标签(由载荷日期推导,与 Standing.season 同口径)
assert raw.source_record_id == "standings:EPL:2025-2026"
assert raw.ingest_batch_id.startswith("bzzoiro-standings-EPL-")
# 整份原始载荷完整保留
assert raw.raw_payload["standings"][0]["team_name"] == "Arsenal FC"
lineages = _lineages(db)
assert len(lineages) == 1
lin = lineages[0]
assert lin.source_system == "bzzoiro"
assert lin.source_record_id == "standings:EPL:2025-2026"
assert lin.target_table == "standings"
assert lin.target_id == 42 # 联赛 id
assert lin.transform_name == "standings_ingest"
assert lin.transform_detail == {
"league": "EPL", "season": "2025-2026", "rows_upserted": 2,
}
# RawEvent 与 Lineage 同批次,便于按批追溯
assert lin.batch_id == raw.ingest_batch_id
async def test_updated_snapshot_also_writes_bronze(self, monkeypatch):
"""已有快照就地更新(非插入)同样是成功采集,必须留 Bronze 记录。"""
payload = _payload()
payload["standings"] = payload["standings"][:1] # 单队,便于命中同一行
_patch_fetch(monkeypatch, payload)
team = Team(name="Arsenal FC", name_zh="阿森纳")
team.id = 7
existing = Standing(league_id=42, season="2025-2026", team_id=7, position=9)
existing.points = 1
db = _FakeDB(leagues=[_preset_league()], teams=[team], standings=[existing])
result = await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
assert result["total_upserted"] == 1
assert result["leagues"]["EPL"]["teams_created"] == 0
# 快照刷新也要留痕: RawEvent(幂等) + 血缘
assert len(_raw_events(db)) == 1
lineages = _lineages(db)
assert len(lineages) == 1
assert lineages[0].transform_name == "standings_ingest"
assert lineages[0].transform_detail["rows_upserted"] == 1
async def test_empty_upsert_writes_no_bronze(self, monkeypatch):
"""载荷有行但全部队名为空 → 没有任何 upsert,不应产生 RawEvent/Lineage。"""
payload = {"standings": [{"position": 1, "team_name": ""}]}
_patch_fetch(monkeypatch, payload)
db = _FakeDB(leagues=[_preset_league()])
result = await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
assert result["total_upserted"] == 0
assert _raw_events(db) == []
assert _lineages(db) == []
# ============================================================
# 2. RawEvent 幂等: 同 source_record_id 跳过
# ============================================================
class TestStandingsRawEventIdempotent:
async def test_existing_raw_event_is_skipped(self, monkeypatch):
existing = RawEvent(
source_system="bzzoiro",
source_record_id="standings:EPL:2025-2026",
raw_payload={"old": True},
)
_patch_fetch(monkeypatch, _payload())
db = _FakeDB(leagues=[_preset_league()], raw_events=[existing])
await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
new_raws = [r for r in _raw_events(db) if r is not existing]
assert new_raws == []
assert len(_lineages(db)) == 1 # 血缘仍然记录本次采集
async def test_different_season_writes_new_raw_event(self, monkeypatch):
"""幂等键含赛季: 同联赛不同赛季各留一条 RawEvent。"""
payload = _payload()
payload["season"] = {"start_date": "2024-08-01", "end_date": "2025-05-31"}
existing = RawEvent(
source_system="bzzoiro",
source_record_id="standings:EPL:2025-2026",
raw_payload={"old": True},
)
_patch_fetch(monkeypatch, payload)
db = _FakeDB(leagues=[_preset_league()], raw_events=[existing])
await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
new_raws = [r for r in _raw_events(db) if r is not existing]
assert len(new_raws) == 1
assert new_raws[0].source_record_id == "standings:EPL:2024-2025"
# ============================================================
# 3. 基础设施写入失败: 尽力而为,不拖垮主流程
# ============================================================
class TestStandingsBronzeIsBestEffort:
async def test_bronze_write_failure_does_not_break_ingest(self, monkeypatch):
async def _boom(*args, **kwargs):
raise RuntimeError("infra down")
monkeypatch.setattr(bz, "_write_raw_event", _boom)
monkeypatch.setattr(bz, "_write_lineage", _boom)
_patch_fetch(monkeypatch, _payload())
db = _FakeDB(leagues=[_preset_league()])
# 不应抛异常:Bronze 写不进去只记 warning
result = await bz.ingest_bzzoiro_standings(db, leagues=["EPL"])
assert result["total_upserted"] == 2
assert [o for o in db.added if isinstance(o, Standing)]
# ============================================================
# 4. 抓取失败: 继续写死信,且不写 Bronze
# ============================================================
class TestStandingsFailurePathKeepsDeadLetter:
async def test_fetch_failure_writes_deadletter_and_no_bronze(self, monkeypatch):
async def _boom(league_code, season=None):
raise RuntimeError("upstream 500")
monkeypatch.setattr(bz, "fetch_bzzoiro_standings", _boom)
db = _FakeDB()
result = await bz.ingest_bzzoiro_standings(db, leagues=["SP1"], season="2025-2026")
assert result["errors"]
failures = [o for o in db.added if isinstance(o, IngestFailure)]
assert len(failures) == 1
assert failures[0].entity_type == "standings"
assert failures[0].error_type == "fetch_error"
# 失败路径绝不写 Bronze(没有任何成功 upsert)
assert _raw_events(db) == []
assert _lineages(db) == []