Files
Profeto/src/data/team_names.py
T
Profeto Agent 6c24672e87 安全加固 + 数据管线修复 + 质量改进(第2批)
安全加固:
- /api/v1/predict 限流改用 get_client_ip 防 X-Forwarded-For 伪造
- 新增 TRUST_PROXY_HEADERS/REQUIRE_ADMIN_AUTH 配置,默认 fail-closed
- 生产环境管理接口未配置鉴权时拒绝(503),不再放行

数据管线修复:
- injuries IntegrityError 改用 begin_nested(SAVEPOINT)隔离批次
- injuries 空名单 vs 未配置语义区分(has_data 精确标记)
- bzzoiro 统计字段映射(shots/possession/cards) + 入库条件放宽
- available_at 语义收紧(回测防泄漏)
- team_names NFKD 去变音双重查找 + 补齐变体键

预测系统改进:
- multi-agent 全专家失败时 status=degraded 跳过终裁
- agent_weights 独立持久化到 predictions 表

新增迁移:
- 0014_predictions_agent_weights.py

新增测试(8个文件):
- test_ip_spoofing.py: 限流防伪造
- test_require_admin_fail_closed.py: 生产 fail-closed
- test_injuries_integrity_rollback.py: SAVEPOINT 隔离
- test_injuries_slice_semantic.py: 空名单 vs 未配置
- test_available_at.py: 回测防泄漏
- test_bzzoirot_stats.py: 统计字段映射
- test_team_names_normalize.py: NFKD 变体
- test_multi_agent_degraded.py: 全失败 degraded
- test_agent_weights_persist.py: 权重持久化
2026-09-19 08:02:57 +00:00

164 lines
5.2 KiB
Python

"""队名归一化:各源队名 → 统一规范名。
迁移自旧项目 app/data/team_names.py。
NFKD 归一化会剥离变音符号(ü→u),导致「Bayern München」与「Bayern Munich」
映射到不同规范名。修复:双重查找(原始名 + NFKD 名) + 补齐常见变体键。
"""
from __future__ import annotations
import unicodedata
NORMALIZE_MAP = {
# ---- 英超 ----
"Man City": "Manchester City",
"Man United": "Manchester United",
"Newcastle": "Newcastle United",
"Nott'm Forest": "Nottingham Forest",
"Wolves": "Wolverhampton Wanderers",
"West Ham": "West Ham United",
"Tottenham": "Tottenham Hotspur",
"Spurs": "Tottenham Hotspur",
"Brighton": "Brighton and Hove Albion",
"West Brom": "West Bromwich Albion",
"Stoke": "Stoke City",
"Huddersfield": "Huddersfield Town",
"Swansea": "Swansea City",
"Hull": "Hull City",
"Cardiff": "Cardiff City",
"Luton": "Luton Town",
"Norwich": "Norwich City",
"Bournemouth": "AFC Bournemouth",
"Ipswich": "Ipswich Town",
"Leicester": "Leicester City",
"Leeds": "Leeds United",
"Sheffield United": "Sheffield United",
"Southampton": "Southampton",
"Arsenal": "Arsenal",
"Aston Villa": "Aston Villa",
"Brentford": "Brentford",
"Chelsea": "Chelsea",
"Crystal Palace": "Crystal Palace",
"Everton": "Everton",
"Fulham": "Fulham",
"Liverpool": "Liverpool",
# ---- 西甲 ----
"Atletico Madrid": "Atlético Madrid",
"Athletic Club": "Athletic Club",
"Real Betis": "Real Betis",
"Celta Vigo": "Celta Vigo",
"Deportivo Alaves": "Deportivo Alavés",
"Girona": "Girona",
"Las Palmas": "Las Palmas",
"Leganes": "Leganés",
"Mallorca": "Mallorca",
"Osasuna": "Osasuna",
"Rayo Vallecano": "Rayo Vallecano",
"Real Sociedad": "Real Sociedad",
"Sevilla": "Sevilla",
"Valencia": "Valencia",
"Villarreal": "Villarreal",
"Espanyol": "Espanyol",
"Getafe": "Getafe",
"Real Madrid": "Real Madrid",
"Barcelona": "Barcelona",
# ---- 德甲 ----
"Bayern Munich": "Bayern München",
"Bayern Munchen": "Bayern München", # NFKD stripped variant
"Bayern München": "Bayern München", # canonical with umlaut (direct hit)
"FC Koln": "FC Köln",
"FC Köln": "FC Köln",
"RB Leipzig": "RB Leipzig",
"Borussia Dortmund": "Borussia Dortmund",
"Borussia M'gladbach": "Borussia Mönchengladbach",
"Borussia Monchengladbach": "Borussia Mönchengladbach", # NFKD stripped
"Borussia Mönchengladbach": "Borussia Mönchengladbach", # canonical
"Bayer Leverkusen": "Bayer Leverkusen",
"Eintracht Frankfurt": "Eintracht Frankfurt",
"VfB Stuttgart": "VfB Stuttgart",
"VfL Wolfsburg": "VfL Wolfsburg",
"Werder Bremen": "Werder Bremen",
"TSG Hoffenheim": "TSG Hoffenheim",
"SC Freiburg": "SC Freiburg",
"Union Berlin": "Union Berlin",
"Mainz": "Mainz 05",
"Augsburg": "FC Augsburg",
"Bochum": "VfL Bochum",
"Heidenheim": "1. FC Heidenheim",
"St. Pauli": "FC St. Pauli",
"Holstein Kiel": "Holstein Kiel",
# ---- 意甲 ----
"AC Milan": "AC Milan",
"Inter": "Inter Milan",
"Inter Milan": "Inter Milan",
"Juventus": "Juventus",
"Napoli": "SSC Napoli",
"Roma": "AS Roma",
"Lazio": "Lazio",
"Atalanta": "Atalanta",
"Fiorentina": "ACF Fiorentina",
"Bologna": "Bologna",
"Torino": "Torino",
"Monza": "AC Monza",
"Udinese": "Udinese",
"Sassuolo": "Sassuolo",
"Empoli": "Empoli",
"Cagliari": "Cagliari",
"Genoa": "Genoa",
"Lecce": "Lecce",
"Hellas Verona": "Hellas Verona",
"Parma": "Parma",
"Como": "Como",
"Venezia": "Venezia",
# ---- 法甲 ----
"PSG": "Paris Saint-Germain",
"Paris Saint-Germain": "Paris Saint-Germain",
"Marseille": "Olympique Marseille",
"Lyon": "Olympique Lyonnais",
"Monaco": "AS Monaco",
"Lille": "Lille OSC",
"Nice": "OGC Nice",
"Rennes": "Stade Rennais",
"Lens": "RC Lens",
"Strasbourg": "RC Strasbourg",
"Brest": "Stade Brestois",
"Nantes": "FC Nantes",
"Reims": "Stade de Reims",
"Toulouse": "Toulouse FC",
"Montpellier": "Montpellier HSC",
"Le Havre": "Le Havre AC",
"Lorient": "FC Lorient",
"Saint-Etienne": "AS Saint-Étienne",
"Saint-Etienne": "AS Saint-Étienne", # NFKD stripped (ê → e)
"AS Saint-Étienne": "AS Saint-Étienne", # canonical prefix
"AS Saint-Etienne": "AS Saint-Étienne", # NFKD stripped with prefix
"Angers": "Angers SCO",
"Auxerre": "AJ Auxerre",
"Leganes": "Leganés",
}
def normalize(name: str) -> str:
"""队名归一化:变音符号变体 → 统一规范名。
双重查找策略:
1. 原始名(带变音)直接查表
2. NFKD 去变音后再查表
确保「Bayern München」「Bayern Munchen」「Bayern Munich」
都映射到同一规范名「Bayern München」。
"""
if not name:
return ""
# 1. 原始名直接查表(保留变音变体)
stripped = name.strip()
if stripped in NORMALIZE_MAP:
return NORMALIZE_MAP[stripped]
# 2. NFKD 去变音后查表
n = unicodedata.normalize("NFKD", stripped)
n = "".join(c for c in n if not unicodedata.combining(c))
n = n.strip()
return NORMALIZE_MAP.get(n, n)