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
@@ -63,6 +63,36 @@
|
||||
`src/data/team_names.py` 维护 `NORMALIZE_MAP`(如 `Man City` → `Manchester City`),未命中映射的队名原样返回。
|
||||
归一前先做 Unicode NFKD 去重音。
|
||||
|
||||
**唯一键是归一后英文名**:`teams.name` 带 `UNIQUE` 约束,所有入库路径均经 `TeamRepository.get_or_create` 收敛归一化
|
||||
(events / standings 管线在调用前归一,仓库层再做一次幂等归一作为兜底)。创建新 Team 时打 `info` 日志记录「原始名 → 归一后名」。
|
||||
|
||||
> ⚠️ **`normalize` 当前大小写敏感**:仅当入参大小写与 `NORMALIZE_MAP` 键完全匹配时才触发映射
|
||||
>(如 `"Man City"` → `"Manchester City"`,但 `"man city"` 原样保留)。上游 bzzoiro 返回的队名首字母大写,
|
||||
>实际命中无问题;若新增数据源返回全小写/全大写队名,需先 `title()` 再归一,否则会绕过映射产生重复 Team。
|
||||
|
||||
**改名 / 合并流程**(人工):
|
||||
|
||||
当发现两个 `teams` 行实际是同一球队(如 `Manchester City` 与 `Man City` 因历史数据大小写差异各占一行):
|
||||
|
||||
1. 确定**保留行**(通常选归一后规范名、且被更多 Match 引用的那行)。
|
||||
2. 将被删行的所有引用指向保留行(`UPDATE matches SET home_team_id = 保留id WHERE home_team_id = 删行id`,客场同理;
|
||||
`standings` / `match_stats` 按 `team_id` 同理)。
|
||||
3. 删掉多余行:`DELETE FROM teams WHERE id = 删行id`。
|
||||
|
||||
> 此过程引入外键约束风险,务必在事务中执行并先 `BEGIN; ... ` 验证行数后再 `COMMIT`。
|
||||
> 暂不做自动合并(避免误合相似名),仅通过下方 Admin 接口列出「近似重名」候选,由人工判定。
|
||||
|
||||
## Admin:近似重名候选
|
||||
|
||||
`GET /api/v1/admin/team-name-duplicates` 只读列出启发式相似候选(大小写差异、子串包含、前缀碰撞),不做自动合并。
|
||||
典型用途:定期巡检,发现候选后走上方人工 SQL 合并。启发式规则:
|
||||
|
||||
- **大小写变体**:`lower(name)` 相同但 `name` 不同(如 `Arsenal FC` / `arsenal fc`)。
|
||||
- **子串包含**:A 是 B 的子串且长度 ≥ 5(如 `Manchester` / `Manchester City`)。
|
||||
- **前缀碰撞**:前 8 个字符相同的两队。
|
||||
|
||||
命中任一规则即列为候选,按相似度分组返回。
|
||||
|
||||
## 数据库 Schema
|
||||
|
||||
12 张表:核心业务表 5 张见下方 DDL,其余 7 张(积分榜/配置/调度/治理)见后文表格。
|
||||
|
||||
@@ -0,0 +1,343 @@
|
||||
"""后台管理:管理区统计、数据完整性分析、数据质量检查。
|
||||
|
||||
所有接口需管理员鉴权(require_admin)。路由前缀 /api/v1/admin。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from datetime import datetime, timedelta, timezone
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
from sqlalchemy import func, select
|
||||
|
||||
from src.api.deps import require_admin
|
||||
from src.db.base import AsyncSession, get_db_read
|
||||
from src.db.models import DataQualityCheck, IngestFailure, League, Match, MatchStats, Prediction, Standing
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api/v1/admin", tags=["admin"], dependencies=[Depends(require_admin)])
|
||||
|
||||
|
||||
@router.get("/stats")
|
||||
async def admin_stats(db: AsyncSession = Depends(get_db_read)):
|
||||
"""管理区统计(只读):预测次数 + 比赛覆盖。轻量聚合,无 LLM 调用。"""
|
||||
day_ago = datetime.now(timezone.utc) - timedelta(days=1)
|
||||
week_ago = datetime.now(timezone.utc) - timedelta(days=7)
|
||||
r = (
|
||||
await db.execute(
|
||||
select(
|
||||
func.count().label("total"),
|
||||
func.count().filter(Prediction.created_at >= day_ago).label("last_24h"),
|
||||
func.count().filter(Prediction.created_at >= week_ago).label("last_7d"),
|
||||
)
|
||||
)
|
||||
).one()
|
||||
# F3 修复: 补充真实比赛计数(非 limit=100 近似)
|
||||
match_cnt = (await db.execute(select(func.count()).select_from(Match))).scalar() or 0
|
||||
finished_cnt = (await db.execute(select(func.count()).where(Match.match_status == "finished"))).scalar() or 0
|
||||
stats_cnt = (await db.execute(select(func.count()).select_from(MatchStats))).scalar() or 0
|
||||
standings_cnt = (await db.execute(select(func.count()).select_from(Standing))).scalar() or 0
|
||||
return {
|
||||
"predictions": {"total": r.total, "last_24h": r.last_24h, "last_7d": r.last_7d},
|
||||
"matches": {"total": match_cnt, "finished": finished_cnt},
|
||||
"stats": {"total": stats_cnt},
|
||||
"standings": {"total": standings_cnt},
|
||||
}
|
||||
|
||||
|
||||
# ── 数据完整性分析(可视化数据源) ────────────────────────────────
|
||||
|
||||
|
||||
@router.get("/data-completeness")
|
||||
async def data_completeness(db: AsyncSession = Depends(get_db_read)):
|
||||
"""按联赛统计数据完整性:比赛覆盖、字段覆盖、积分榜覆盖。
|
||||
|
||||
前端「数据完整性」页据此渲染,回答三个问题:
|
||||
1. 数据是否齐全(各联赛比赛/统计/积分榜量级)
|
||||
2. 字段是否齐全(每张统计表各字段非空率)
|
||||
3. 覆盖是否新鲜(最近一场/最近一次采集)
|
||||
"""
|
||||
from src.data.config import BZZOIRO_LEAGUE_IDS, LEAGUE_NAMES, LEAGUE_COUNTRIES
|
||||
|
||||
out_leagues: list[dict] = []
|
||||
for code, bzz_id in BZZOIRO_LEAGUE_IDS.items():
|
||||
# 比赛覆盖
|
||||
m = (
|
||||
await db.execute(
|
||||
select(
|
||||
func.count().label("total"),
|
||||
func.count().filter(Match.match_status == "finished").label("finished"),
|
||||
func.count().filter(Match.match_status == "scheduled").label("scheduled"),
|
||||
func.count().filter(Match.source_event_id.is_not(None)).label("with_source_id"),
|
||||
func.max(Match.match_date).label("latest_match"),
|
||||
func.min(Match.match_date).label("earliest_match"),
|
||||
)
|
||||
.select_from(Match)
|
||||
.join(League, League.id == Match.league_id)
|
||||
.where(League.code == code)
|
||||
)
|
||||
).one()
|
||||
# 统计字段覆盖(联表 matches)
|
||||
s = (
|
||||
await db.execute(
|
||||
select(
|
||||
func.count().label("rows"),
|
||||
func.count(MatchStats.home_xg).label("xg"),
|
||||
func.count(MatchStats.home_shots).label("shots"),
|
||||
func.count(MatchStats.home_possession).label("possession"),
|
||||
func.count(MatchStats.home_corners).label("corners"),
|
||||
func.count(MatchStats.home_fouls).label("fouls"),
|
||||
func.count(MatchStats.home_big_chances).label("big_chances"),
|
||||
func.count(MatchStats.home_yellow_cards).label("cards"),
|
||||
)
|
||||
.select_from(MatchStats)
|
||||
.join(Match, Match.id == MatchStats.match_id)
|
||||
.join(League, League.id == Match.league_id)
|
||||
.where(League.code == code)
|
||||
)
|
||||
).one()
|
||||
# 积分榜覆盖
|
||||
st = (
|
||||
await db.execute(
|
||||
select(
|
||||
func.count().label("rows"),
|
||||
func.max(Standing.retrieved_at).label("latest_retrieved"),
|
||||
)
|
||||
.select_from(Standing)
|
||||
.join(League, League.id == Standing.league_id)
|
||||
.where(League.code == code)
|
||||
)
|
||||
).one()
|
||||
|
||||
stats_rows = s.rows or 0
|
||||
pct = lambda n: round(n / stats_rows * 100, 1) if stats_rows else 0.0 # noqa: E731
|
||||
out_leagues.append(
|
||||
{
|
||||
"code": code,
|
||||
"name": LEAGUE_NAMES.get(code, code),
|
||||
"country": LEAGUE_COUNTRIES.get(code),
|
||||
"matches": {
|
||||
"total": m.total or 0,
|
||||
"finished": m.finished or 0,
|
||||
"scheduled": m.scheduled or 0,
|
||||
"with_source_id": m.with_source_id or 0,
|
||||
"earliest_match": m.earliest_match.isoformat() if m.earliest_match else None,
|
||||
"latest_match": m.latest_match.isoformat() if m.latest_match else None,
|
||||
},
|
||||
"stats": {
|
||||
"rows": stats_rows,
|
||||
"fields": {
|
||||
"xg": {"count": s.xg or 0, "pct": pct(s.xg or 0)},
|
||||
"shots": {"count": s.shots or 0, "pct": pct(s.shots or 0)},
|
||||
"possession": {"count": s.possession or 0, "pct": pct(s.possession or 0)},
|
||||
"corners": {"count": s.corners or 0, "pct": pct(s.corners or 0)},
|
||||
"fouls": {"count": s.fouls or 0, "pct": pct(s.fouls or 0)},
|
||||
"big_chances": {"count": s.big_chances or 0, "pct": pct(s.big_chances or 0)},
|
||||
"cards": {"count": s.cards or 0, "pct": pct(s.cards or 0)},
|
||||
},
|
||||
},
|
||||
"standings": {
|
||||
"rows": st.rows or 0,
|
||||
"latest_retrieved": st.latest_retrieved.isoformat() if st.latest_retrieved else None,
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
# 整体健康信号
|
||||
total_finished = sum(l["matches"]["finished"] for l in out_leagues)
|
||||
total_stats = sum(l["stats"]["rows"] for l in out_leagues)
|
||||
stats_coverage = round(total_stats / total_finished * 100, 1) if total_finished else 0.0
|
||||
issues: list[str] = []
|
||||
for l in out_leagues:
|
||||
if l["matches"]["finished"] == 0:
|
||||
issues.append(f"{l['name']}: 无已完赛比赛,请先运行「比赛数据」采集")
|
||||
elif l["stats"]["rows"] == 0:
|
||||
issues.append(f"{l['name']}: 已完赛 {l['matches']['finished']} 场但无统计回填,请运行「统计回填」采集")
|
||||
elif stats_coverage < 80:
|
||||
issues.append(f"{l['name']}: 统计覆盖率仅 {stats_coverage}%,建议增量回填")
|
||||
if l["standings"]["rows"] == 0:
|
||||
issues.append(f"{l['name']}: 无积分榜数据,请运行「积分榜」采集")
|
||||
if not issues:
|
||||
issues.append("各联赛数据完整度良好")
|
||||
|
||||
return {
|
||||
"generated_at": datetime.now(timezone.utc).isoformat(),
|
||||
"leagues": out_leagues,
|
||||
"totals": {
|
||||
"finished_matches": total_finished,
|
||||
"stats_rows": total_stats,
|
||||
"stats_coverage_pct": stats_coverage,
|
||||
},
|
||||
"issues": issues,
|
||||
}
|
||||
|
||||
|
||||
# ── 数据质量检查 API ────────────────────────────────────────────
|
||||
|
||||
|
||||
@router.get("/data-quality")
|
||||
async def data_quality_checks(db: AsyncSession = Depends(get_db_read)):
|
||||
"""数据质量检查结果(只读)。"""
|
||||
# 最近的失败记录
|
||||
failures = (
|
||||
await db.execute(
|
||||
select(IngestFailure)
|
||||
.where(IngestFailure.status.in_(["pending", "retrying"]))
|
||||
.order_by(IngestFailure.created_at.desc())
|
||||
.limit(20)
|
||||
)
|
||||
).scalars().all()
|
||||
|
||||
# 最近的质量检查
|
||||
checks = (
|
||||
await db.execute(
|
||||
select(DataQualityCheck)
|
||||
.order_by(DataQualityCheck.checked_at.desc())
|
||||
.limit(20)
|
||||
)
|
||||
).scalars().all()
|
||||
|
||||
return {
|
||||
"failures": [
|
||||
{
|
||||
"id": f.id,
|
||||
"source": f.source_system,
|
||||
"entity_type": f.entity_type,
|
||||
"source_record_id": f.source_record_id,
|
||||
"error_type": f.error_type,
|
||||
"error_detail": f.error_detail,
|
||||
"retry_count": f.retry_count,
|
||||
"status": f.status,
|
||||
"created_at": f.created_at.isoformat() if f.created_at else None,
|
||||
}
|
||||
for f in failures
|
||||
],
|
||||
"checks": [
|
||||
{
|
||||
"id": c.id,
|
||||
"check_name": c.check_name,
|
||||
"entity_type": c.entity_type,
|
||||
"passed": c.passed,
|
||||
"severity": c.severity,
|
||||
"detail": c.detail,
|
||||
"checked_at": c.checked_at.isoformat() if c.checked_at else None,
|
||||
}
|
||||
for c in checks
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
@router.post("/data-quality/run")
|
||||
async def run_data_quality_check(db: AsyncSession = Depends(get_db_read)):
|
||||
"""手动触发一次数据质量检查。"""
|
||||
checks = []
|
||||
|
||||
# 检查1: 已完赛但无统计的比赛
|
||||
finished_no_stats = (
|
||||
await db.execute(
|
||||
select(func.count())
|
||||
.select_from(Match)
|
||||
.outerjoin(MatchStats, Match.id == MatchStats.match_id)
|
||||
.where(Match.match_status == "finished")
|
||||
.where(MatchStats.id.is_(None))
|
||||
)
|
||||
).scalar() or 0
|
||||
|
||||
checks.append(DataQualityCheck(
|
||||
check_name="finished_without_stats",
|
||||
entity_type="match",
|
||||
actual_value=float(finished_no_stats),
|
||||
passed=finished_no_stats == 0,
|
||||
severity="warning" if finished_no_stats > 0 else "info",
|
||||
detail={"message": f"{finished_no_stats} 场已完赛比赛缺少统计数据"},
|
||||
))
|
||||
|
||||
# 检查2: 积分榜缺失的联赛
|
||||
leagues_without_standings = (
|
||||
await db.execute(
|
||||
select(func.count())
|
||||
.select_from(League)
|
||||
.outerjoin(Standing, League.id == Standing.league_id)
|
||||
.where(Standing.id.is_(None))
|
||||
)
|
||||
).scalar() or 0
|
||||
|
||||
checks.append(DataQualityCheck(
|
||||
check_name="league_without_standings",
|
||||
entity_type="league",
|
||||
actual_value=float(leagues_without_standings),
|
||||
passed=leagues_without_standings == 0,
|
||||
severity="warning" if leagues_without_standings > 0 else "info",
|
||||
detail={"message": f"{leagues_without_standings} 个联赛缺少积分榜"},
|
||||
))
|
||||
|
||||
for c in checks:
|
||||
db.add(c)
|
||||
await db.commit()
|
||||
|
||||
return {"ok": True, "checks": [{"name": c.check_name, "passed": c.passed} for c in checks]}
|
||||
|
||||
|
||||
# ── 近似重名候选(只读,启发式,不做自动合并) ──────────────────────
|
||||
|
||||
|
||||
@router.get("/team-name-duplicates")
|
||||
async def team_name_duplicates(db: AsyncSession = Depends(get_db_read)):
|
||||
"""只读列出近似重名候选(大小写变体/子串包含/前缀碰撞)。
|
||||
|
||||
启发式规则(命中任一即列为候选):
|
||||
- 大小写变体: lower(name) 相同但 name 不同
|
||||
- 子串包含: A 是 B 的子串且 len(A) ≥ 5
|
||||
- 前缀碰撞: 前 8 字符相同(忽略大小写)
|
||||
|
||||
仅作排查参考,合并需走人工 SQL(见 docs/05-data.md)。
|
||||
"""
|
||||
teams = (await db.execute(select(Team.id, Team.name))).all()
|
||||
by_lower: dict[str, list[dict]] = {}
|
||||
for t in teams:
|
||||
key = (t.name or "").lower()
|
||||
by_lower.setdefault(key, []).append({"id": t.id, "name": t.name})
|
||||
|
||||
groups: list[dict] = []
|
||||
|
||||
# 规则1: 大小写变体(lower 相同但原名不同)
|
||||
for key, members in by_lower.items():
|
||||
if len(members) > 1:
|
||||
groups.append({
|
||||
"rule": "case_variant",
|
||||
"key": key,
|
||||
"members": members,
|
||||
})
|
||||
|
||||
# 规则2 & 3: 子串包含 / 前缀碰撞(仅在 lower 名不同的组间比较)
|
||||
distinct = [m for members in by_lower.values() for m in members]
|
||||
seen_pairs: set[tuple[int, int]] = set()
|
||||
for i, a in enumerate(distinct):
|
||||
na = (a["name"] or "").lower()
|
||||
for b in distinct[i + 1:]:
|
||||
nb = (b["name"] or "").lower()
|
||||
if na == nb:
|
||||
continue # 已被规则1覆盖
|
||||
pair = (min(a["id"], b["id"]), max(a["id"], b["id"]))
|
||||
if pair in seen_pairs:
|
||||
continue
|
||||
hit = None
|
||||
if len(na) >= 5 and na in nb:
|
||||
hit = "substring"
|
||||
elif len(nb) >= 5 and nb in na:
|
||||
hit = "substring"
|
||||
elif len(na) >= 8 and len(nb) >= 8 and na[:8] == nb[:8]:
|
||||
hit = "prefix"
|
||||
if hit:
|
||||
seen_pairs.add(pair)
|
||||
groups.append({
|
||||
"rule": hit,
|
||||
"members": [a, b],
|
||||
})
|
||||
|
||||
return {
|
||||
"count": len(groups),
|
||||
"hint": "命中任一启发式仅表示'可疑',合并前请人工确认是否同一球队",
|
||||
"groups": groups,
|
||||
}
|
||||
+19
-3
@@ -5,6 +5,10 @@ Repository 只负责查询,不负责事务提交。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
from datetime import datetime
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import selectinload
|
||||
@@ -108,10 +112,22 @@ class TeamRepository:
|
||||
return (await self._session.execute(stmt)).scalar_one_or_none()
|
||||
|
||||
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)。"""
|
||||
team = await self.get_by_name(name)
|
||||
"""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。
|
||||
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。
|
||||
"""
|
||||
from src.data.team_names import normalize as normalize_name
|
||||
|
||||
normalized = normalize_name(name) or name.strip()
|
||||
team = await self.get_by_name(normalized)
|
||||
if team is None:
|
||||
team = Team(name=name, name_zh=name_zh)
|
||||
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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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) == []
|
||||
Reference in New Issue
Block a user