fix(P0-01): missing score 不得变 0:0 — score_status + CHECK 约束

新增 matches.score_status(known/missing/unknown):
- 替换 ck_matches_finished_has_score 为 ck_matches_score_integrity:
  known → 必须有分; missing/unknown → goals 必须 NULL(不伪造 0:0)
- normalize: 完赛缺分不再静默降级为 scheduled,改设 score_status=missing
- events ingest: 创建/更新 Match 同步 score_status(比分由缺变 known / 确认缺分 missing)
- slices(form/h2h/home_away)/backtest: 显式加 score_status='known' 过滤完赛样本
- 迁移 0022 回填现有数据(绝不 UPDATE goals=0)

测试 tests/test_p0_score_status.py(9/9):约束存在性/Match 构造/normalize 行为。
54 相关测试全绿。
This commit is contained in:
shangfangjian
2026-09-22 02:32:53 +08:00
parent f563d5cc99
commit 63caa6736c
9 changed files with 226 additions and 4 deletions
@@ -0,0 +1,63 @@
"""P0-01: 比分可信度——score_status + 允许完赛缺分(NULL,禁止伪造 0:0)
替换 ck_matches_finished_has_score:引入 score_status(known/missing/unknown),
完赛 + score_status=missing 时 home/away_goals 必须 NULL(不伪造比分)。
Revision ID: 0022_match_score_status
Revises: 0021_match_source_event_id_unique
Create Date: 2026-09-22
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
revision: str = '0022_match_score_status'
down_revision: Union[str, None] = '0021_match_source_event_id_unique'
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# 1) 新增 score_status 列(默认 unknown)
op.add_column(
'matches',
sa.Column('score_status', sa.String(20), server_default='unknown', nullable=False),
)
# 2) 按现有数据回填 score_status(绝不写 goals=0):
# - 有比分(两列均非 NULL) → known
# - 无比分 + 完赛 → missing(缺分)
# - 其余 → unknown
op.execute(
"UPDATE matches SET score_status = 'known'"
" WHERE home_goals IS NOT NULL AND away_goals IS NOT NULL"
)
op.execute(
"UPDATE matches SET score_status = 'missing'"
" WHERE match_status = 'finished' AND home_goals IS NULL AND away_goals IS NULL"
)
# 3) 删除旧约束,加新约束
op.drop_constraint('ck_matches_finished_has_score', 'matches', type_='check')
op.create_check_constraint(
'ck_matches_score_status_enum', 'matches',
"score_status IN ('known', 'missing', 'unknown')",
)
op.create_check_constraint(
'ck_matches_score_integrity', 'matches',
"match_status <> 'finished'"
" OR (score_status = 'known' AND home_goals IS NOT NULL AND away_goals IS NOT NULL)"
" OR (score_status IN ('missing', 'unknown') AND home_goals IS NULL AND away_goals IS NULL)",
)
def downgrade() -> None:
op.drop_constraint('ck_matches_score_integrity', 'matches', type_='check')
op.drop_constraint('ck_matches_score_status_enum', 'matches', type_='check')
op.create_check_constraint(
'ck_matches_finished_has_score', 'matches',
"match_status <> 'finished' OR (home_goals IS NOT NULL AND away_goals IS NOT NULL)",
)
op.remove_column('matches', 'score_status')
+11
View File
@@ -202,6 +202,7 @@ class BzzoiroSource:
match_date=nm.date, match_date=nm.date,
match_date_date=_to_date(nm.date), match_date_date=_to_date(nm.date),
match_status=nm.match_status, match_status=nm.match_status,
score_status=nm.score_status,
home_goals=nm.home_goals, home_goals=nm.home_goals,
away_goals=nm.away_goals, away_goals=nm.away_goals,
home_ht_goals=nm.home_ht_goals, home_ht_goals=nm.home_ht_goals,
@@ -238,6 +239,16 @@ class BzzoiroSource:
existing_match.away_goals = nm.away_goals existing_match.away_goals = nm.away_goals
existing_match.home_ht_goals = nm.home_ht_goals existing_match.home_ht_goals = nm.home_ht_goals
existing_match.away_ht_goals = nm.away_ht_goals existing_match.away_ht_goals = nm.away_ht_goals
# 比分由缺变有 → 标记 known
existing_match.score_status = "known"
changed = True
elif (
nm.match_status == "finished"
and nm.home_goals is None
and existing_match.score_status == "unknown"
):
# 确认完赛仍缺分 → 标记 missing(不伪造 0:0)
existing_match.score_status = "missing"
changed = True changed = True
if existing_match.match_stage is None and nm.match_stage: if existing_match.match_stage is None and nm.match_stage:
existing_match.match_stage = nm.match_stage existing_match.match_stage = nm.match_stage
+9 -1
View File
@@ -35,6 +35,8 @@ class NormalizedMatch:
home_team: str home_team: str
away_team: str away_team: str
match_status: str = "finished" match_status: str = "finished"
# P0-01:比分可信度。known=可靠比分;missing=完赛缺分;unknown=待定。
score_status: str = "unknown"
home_goals: int | None = None home_goals: int | None = None
away_goals: int | None = None away_goals: int | None = None
season_label: str = "" season_label: str = ""
@@ -217,5 +219,11 @@ def normalize_bzzoiro(raw: dict, league_type: str) -> NormalizedMatch | None:
m.away_red_cards = _to_int(raw.get("away_red_cards", raw.get("red_cards_away"))) m.away_red_cards = _to_int(raw.get("away_red_cards", raw.get("red_cards_away")))
if m.match_status == "finished" and m.home_goals is None: if m.match_status == "finished" and m.home_goals is None:
m.match_status = "scheduled" # P0-01: 完赛缺分不再静默降级为 scheduled(那会丢失「已完赛」事实);
# 保留 status=finished,score_status=missing,goals=NULL(禁止伪造 0:0)。
m.score_status = "missing"
elif m.home_goals is not None and m.away_goals is not None:
m.score_status = "known"
else:
m.score_status = "unknown"
return m return m
+15 -3
View File
@@ -88,6 +88,9 @@ class Match(Base):
index=True, index=True,
) )
match_status: Mapped[str] = mapped_column(String(20), default="scheduled") match_status: Mapped[str] = mapped_column(String(20), default="scheduled")
# P0-01:比分可信度标记。known=有可靠比分;missing=完赛但缺分(保留 NULL 不伪造 0:0);
# unknown=待定(无比分且未确认完赛)。禁止把缺分写成 0:0。
score_status: Mapped[str] = mapped_column(String(20), server_default="unknown", nullable=False)
home_goals: Mapped[int | None] = mapped_column(Integer) home_goals: Mapped[int | None] = mapped_column(Integer)
away_goals: Mapped[int | None] = mapped_column(Integer) away_goals: Mapped[int | None] = mapped_column(Integer)
home_ht_goals: Mapped[int | None] = mapped_column(Integer) home_ht_goals: Mapped[int | None] = mapped_column(Integer)
@@ -127,10 +130,19 @@ class Match(Base):
"match_date_date", "match_date_date",
unique=True, unique=True,
), ),
# DB-5: 数据库级约束 — 已完赛比赛必须有比分 # P0-01:比分可信度约束(替代原 ck_matches_finished_has_score):
# - score_status=known → 必须有比分(非 NULL)
# - score_status=missing → 必须 NULL(完赛缺分,禁止伪造 0:0)
# - score_status=unknown → 必须 NULL
CheckConstraint( CheckConstraint(
"match_status <> 'finished' OR (home_goals IS NOT NULL AND away_goals IS NOT NULL)", "score_status IN ('known', 'missing', 'unknown')",
name="ck_matches_finished_has_score", name="ck_matches_score_status_enum",
),
CheckConstraint(
"match_status <> 'finished'"
" OR (score_status = 'known' AND home_goals IS NOT NULL AND away_goals IS NOT NULL)"
" OR (score_status IN ('missing', 'unknown') AND home_goals IS NULL AND away_goals IS NULL)",
name="ck_matches_score_integrity",
), ),
CheckConstraint( CheckConstraint(
"match_status IN ('finished', 'scheduled', 'in_play', 'paused', 'postponed', 'cancelled', 'suspended')", "match_status IN ('finished', 'scheduled', 'in_play', 'paused', 'postponed', 'cancelled', 'suspended')",
+1
View File
@@ -130,6 +130,7 @@ async def _get_historical_matches(
selectinload(Match.away_team), selectinload(Match.away_team),
) )
.where(Match.match_status == "finished") .where(Match.match_status == "finished")
.where(Match.score_status == "known")
.where(Match.home_goals.is_not(None)) .where(Match.home_goals.is_not(None))
.where(Match.away_goals.is_not(None)) .where(Match.away_goals.is_not(None))
) )
+1
View File
@@ -74,6 +74,7 @@ async def _get_form(db, team_id: int, before, *, limit: int = 5) -> list[Match]:
selectinload(Match.away_team), selectinload(Match.away_team),
) )
.where(Match.match_status == "finished") .where(Match.match_status == "finished")
.where(Match.score_status == "known")
.where(Match.home_goals.is_not(None)) .where(Match.home_goals.is_not(None))
.where((Match.home_team_id == team_id) | (Match.away_team_id == team_id)) .where((Match.home_team_id == team_id) | (Match.away_team_id == team_id))
.order_by(Match.match_date.desc()) .order_by(Match.match_date.desc())
+1
View File
@@ -74,6 +74,7 @@ async def _get_h2h(db, home_id: int, away_id: int, before, *, limit: int = 5) ->
selectinload(Match.away_team), selectinload(Match.away_team),
) )
.where(Match.match_status == "finished") .where(Match.match_status == "finished")
.where(Match.score_status == "known")
.where(Match.home_goals.is_not(None)) .where(Match.home_goals.is_not(None))
.where( .where(
((Match.home_team_id == home_id) & (Match.away_team_id == away_id)) ((Match.home_team_id == home_id) & (Match.away_team_id == away_id))
+1
View File
@@ -68,6 +68,7 @@ async def _get_home_away(db, team_id: int, side: str, before, *, limit: int = 10
selectinload(Match.away_team), selectinload(Match.away_team),
) )
.where(Match.match_status == "finished") .where(Match.match_status == "finished")
.where(Match.score_status == "known")
.where(Match.home_goals.is_not(None)) .where(Match.home_goals.is_not(None))
.order_by(Match.match_date.desc()) .order_by(Match.match_date.desc())
.limit(limit) .limit(limit)
+124
View File
@@ -0,0 +1,124 @@
"""P0-01 回归测试: missing score 不得变 0:0。
运行: pytest tests/test_p0_score_status.py -v
(无需真实 PG;用 fake DB + 模型元数据断言。)
"""
import pytest
from src.db.models import League, Match, Team
# ── fake DB(对齐现有测试约定) ────────────────────────────────────
class _FakeResult:
def __init__(self, items): self._items = list(items)
def scalars(self): return self
def all(self): return list(self._items)
def scalar_one_or_none(self): return self._items[0] if self._items else None
class _FakeDB:
def __init__(self): self.added = []
def add(self, obj): self.added.append(obj)
async def execute(self, stmt): return _FakeResult([])
async def flush(self):
for o in self.added:
if getattr(o, "id", None) is None:
o.id = 1
def _league(lid=1):
lg = League(id=lid, code="E0", name="Test", country="X")
return lg
def _teams():
return Team(id=10, name="Arsenal FC", name_zh="阿森纳"), Team(id=20, name="Chelsea FC", name_zh="切尔西")
class TestScoreStatusConstraintPresence:
"""模型必须定义 score_status 相关 CHECK 约束。"""
def test_score_status_column_exists(self):
cols = {c.name for c in Match.__table__.columns}
assert "score_status" in cols
def test_score_integrity_check_exists(self):
names = {c.name for c in Match.__table__.constraints if c.name}
# 新约束 ck_matches_score_integrity 必须存在
assert any("score_integrity" in n for n in names), \
f"ck_matches_score_integrity 未找到,现有约束: {names}"
def test_old_finished_has_score_check_removed(self):
names = {c.name for c in Match.__table__.constraints}
assert "ck_matches_finished_has_score" not in names, \
"旧约束 ck_matches_finished_has_score 应已被替换"
class TestMatchAcceptsMissingScore:
"""Match 对象层面: 完赛 + score_status=missing + goals=NULL 必须可构造。"""
def test_construct_finished_missing_null_goals(self):
home, away = _teams()
m = Match(
id=1, league_id=_league().id, home_team_id=home.id, away_team_id=away.id,
match_date="2026-01-01 15:00:00+00:00",
match_status="finished", score_status="missing",
home_goals=None, away_goals=None,
)
assert m.home_goals is None
assert m.away_goals is None
assert m.score_status == "missing"
def test_add_to_fake_db(self):
db = _FakeDB()
home, away = _teams()
m = Match(
league_id=_league().id, home_team_id=home.id, away_team_id=away.id,
match_date="2026-01-01 15:00:00+00:00",
match_status="finished", score_status="missing",
home_goals=None, away_goals=None,
)
db.add(m)
def test_server_default_is_unknown(self):
"""score_status 列的 server_default 必须为 unknown(DB 插入未显式赋值时兜底)。"""
col = Match.__table__.c.score_status
assert col.server_default is not None
assert "unknown" in str(col.server_default.arg)
class TestNormalizeNoDowngrade:
"""normalize_bzzoiro 不得把完赛缺分静默降级为 scheduled。"""
def _raw(self, status="finished", home_score=None, away_score=None):
return {
"event_date": "2026-01-01 15:00:00",
"status": status,
"home_team": "Arsenal",
"away_team": "Chelsea",
"home_score": home_score,
"away_score": away_score,
}
def test_finished_missing_score_keeps_finished(self):
from src.data.normalize import normalize_bzzoiro
m = normalize_bzzoiro(self._raw("finished", None, None), "E0")
assert m is not None
assert m.match_status == "finished", "完赛缺分不得降级为 scheduled"
assert m.score_status == "missing"
assert m.home_goals is None
assert m.away_goals is None
def test_finished_with_score_is_known(self):
from src.data.normalize import normalize_bzzoiro
m = normalize_bzzoiro(self._raw("finished", 2, 1), "E0")
assert m.match_status == "finished"
assert m.score_status == "known"
assert m.home_goals == 2 and m.away_goals == 1
def test_scheduled_no_score_is_unknown(self):
from src.data.normalize import normalize_bzzoiro
m = normalize_bzzoiro(self._raw("scheduled", None, None), "E0")
assert m.match_status == "scheduled"
assert m.score_status == "unknown"
assert m.home_goals is None