refactor: 以 bzzoiro 为唯一数据源的全面重构

数据源统一为 bzzoiro,移除 Understat 与 injuries:
- 删除 src/data/understat.py / injuries.py 及相关测试
- 删除 injuries 模型与表;扩展 match_stats(xG 之外增加 big_chances/fouls)
- 新增 standings 表(联赛积分榜:位置/积分/xG/走势/分区)
- matches 表增加 source_event_id 血缘列,支撑统计回填

采集管线(bzzoiro 三条管线):
- events:赛程/比分(/events/),记录 source_event_id
- standings:积分榜快照(/leagues/{id}/standings/)
- stats:已完赛比赛详细统计回填(/events/{id}/stats/)

预测增强:
- standings_slice 替代 injuries_slice;积分榜专家替代阵容完整性专家
- AGENT_META runtime_config 同步更新

管理后台:
- ingest 路由重写为单一 bzzoiro 入口 + task 参数(events/standings/stats/all)
- 新增 /admin/data-completeness 数据完整性分析 API
- 数据源状态页简化为 bzzoiro 单源

前端:
- 采集页重构为任务驱动(比赛/积分榜/统计回填/全量)
- 新增「数据完整性」可视化页(覆盖率矩阵/字段完整率/健康摘要)
- 新增主站积分榜页(/standings)与比赛详情完整统计面板
- agent 名称同步更新(injuries→standings)

迁移 0015_bzzoiro_single_source 已在容器内验证通过,后端测试全部通过。

Co-Authored-By: new-provider/LongCat-2.0 <<EMAIL>>
This commit is contained in:
shangfangjian
2026-09-20 19:13:07 +08:00
co-authored by new-provider/LongCat-2.0 <
parent ec8f36abb2
commit f05dc1ae15
41 changed files with 1603 additions and 1885 deletions
+107 -96
View File
@@ -1,5 +1,11 @@
/**
* Admin 后台 - 数据采集页面(报刊风)
* Admin 后台 - 数据采集页面(bzzoiro 单一数据源)
*
* 三个采集任务:
* events — 比赛日程与比分
* standings — 联赛积分榜
* stats — 已完赛比赛详细统计回填(xG/射门/控球等)
* all — 依次执行以上三项
*
* 响应式布局: 移动端单列,桌面端双列
*/
@@ -9,45 +15,22 @@ import { triggerCollection, fetchLeagues } from '../dal'
import type { CollectionRequest, League } from '../types'
import { Card, CardBody, CardHeader, Badge, SectionHeader, Alert, Spinner } from '../components'
const SOURCES = [
{ value: 'bzzoiro', label: 'Bzzoiro', desc: '历史赛程与比分' },
{ value: 'understat', label: 'Understat', desc: 'xG 进阶数据' },
{ value: 'injuries', label: 'Injuries', desc: '球员伤停' },
const TASKS = [
{ value: 'events', label: '比赛数据', desc: '赛程 / 比分 / 未开赛安排', icon: '⚽' },
{ value: 'standings', label: '积分榜', desc: '联赛排名 / 积分 / xG差 / 近期走势', icon: '🏆' },
{ value: 'stats', label: '统计回填', desc: '已完赛比赛的 xG / 射门 / 控球等详细统计', icon: '📊' },
{ value: 'all', label: '全量采集', desc: '依次采集比赛 + 积分榜 + 统计回填', icon: '⏵⏵' },
] as const
/** 把采集接口返回摘要成一两行可读文字 */
function summarizeResult(res: any, source: string): { title: string; detail: string } {
if (res && typeof res === 'object') {
if (source === 'bzzoiro' && ('total_inserted' in res || 'total_updated' in res)) {
return {
title: `采集完成:新增 ${res.total_inserted ?? 0} 条,更新 ${res.total_updated ?? 0}`,
detail: Array.isArray(res.errors) && res.errors.length > 0 ? res.errors.join('\n') : '',
}
}
if ('count' in res || 'updated' in res) {
const parts = [
`新增 ${res.count ?? 0}`,
`更新 ${res.updated ?? 0}`,
`跳过 ${res.skipped ?? 0}`,
`未匹配 ${res.unmatched ?? 0}`,
]
return {
title: `采集完成:${parts.join(' / ')}`,
detail: Array.isArray(res.errors) && res.errors.length > 0 ? res.errors.join('\n') : '',
}
}
}
return { title: '采集完成', detail: JSON.stringify(res)?.slice(0, 300) ?? '' }
}
export default function CollectionPage() {
const [leagues, setLeagues] = useState<League[]>([])
const [source, setSource] = useState<string>('bzzoiro')
const [task, setTask] = useState<string>('events')
const [leagueCode, setLeagueCode] = useState('')
const [dateFrom, setDateFrom] = useState('')
const [dateTo, setDateTo] = useState('')
const [season, setSeason] = useState('')
const [ingestStatus, setIngestStatus] = useState('') // 空 = 已完赛+未开赛
const [limit, setLimit] = useState(100)
const [loading, setLoading] = useState(false)
const [error, setError] = useState<string | null>(null)
const [result, setResult] = useState<{ title: string; detail: string } | null>(null)
@@ -59,6 +42,8 @@ export default function CollectionPage() {
useEffect(() => { loadLeagues() }, [loadLeagues])
const isEventsTask = task === 'events' || task === 'all'
async function handleSubmit(e: React.FormEvent) {
e.preventDefault()
setError(null)
@@ -67,18 +52,20 @@ export default function CollectionPage() {
try {
const body: CollectionRequest = {
source: source as CollectionRequest['source'],
source: 'bzzoiro',
leagues: leagueCode ? [leagueCode] : undefined,
league: leagueCode || undefined,
task: task as CollectionRequest['task'],
limit,
season: season || undefined,
status: ingestStatus || undefined,
date_from: dateFrom || undefined,
date_to: dateTo || undefined,
// 仅 events/all 任务生效
date_from: isEventsTask ? dateFrom || undefined : undefined,
date_to: isEventsTask ? dateTo || undefined : undefined,
}
await triggerCollection(body)
setResult({
title: '采集任务已启动',
detail: '正在后台执行(上游限速时可能需要分钟)。完成结果与错误请到「系统日志」页查看(支持自动刷新)。',
detail: '正在后台执行(上游限速时可能需要分钟)。完成结果与错误请到「系统日志」页查看(支持自动刷新)。',
})
} catch (err: unknown) {
setError(err instanceof Error ? err.message : '采集触发失败')
@@ -91,7 +78,7 @@ export default function CollectionPage() {
<div className="space-y-6">
<SectionHeader
title="数据采集"
description="触发数据源采集,支持联赛筛选和日期范围。采集为同步执行,大范围日期耗时较长。"
description="bzzoiro 单一数据源:比赛数据、积分榜、比赛统计三条管线。采集为后台异步执行。"
/>
<div className="grid gap-6 lg:grid-cols-2">
@@ -100,20 +87,26 @@ export default function CollectionPage() {
<CardHeader title="新建采集任务" />
<CardBody>
<form onSubmit={handleSubmit} className="space-y-4">
{/* 数据源选择 */}
{/* 任务类型 */}
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<select
value={source}
onChange={e => setSource(e.target.value)}
className="field w-full"
>
{SOURCES.map(s => (
<option key={s.value} value={s.value}>
{s.label} {s.desc}
</option>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<div className="grid grid-cols-2 gap-2 sm:grid-cols-4">
{TASKS.map(t => (
<button
key={t.value}
type="button"
onClick={() => setTask(t.value)}
className={`rounded-lg border px-3 py-2 text-left text-xs transition-colors ${
task === t.value
? 'border-brand-500 bg-brand-50 text-brand-700'
: 'border-ink-200 text-ink-600 hover:border-ink-300'
}`}
>
<span className="mr-1">{t.icon}</span>
<span className="font-medium">{t.label}</span>
</button>
))}
</select>
</div>
</div>
{/* 联赛选择 */}
@@ -131,57 +124,73 @@ export default function CollectionPage() {
</select>
</div>
{/* Bzzoiro 专用: 比赛状态 */}
{source === 'bzzoiro' && (
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<select
value={ingestStatus}
onChange={e => setIngestStatus(e.target.value)}
className="field w-full"
>
<option value="">( + )</option>
<option value="finished"></option>
<option value="scheduled"></option>
</select>
</div>
{/* events/all 任务专用: 比赛状态 + 日期 */}
{isEventsTask && (
<>
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<select
value={ingestStatus}
onChange={e => setIngestStatus(e.target.value)}
className="field w-full"
>
<option value="">( + )</option>
<option value="finished"></option>
<option value="scheduled"></option>
</select>
</div>
<div className="grid grid-cols-1 gap-3 sm:grid-cols-2">
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<input
type="date"
value={dateFrom}
onChange={e => setDateFrom(e.target.value)}
className="field w-full"
/>
</div>
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<input
type="date"
value={dateTo}
onChange={e => setDateTo(e.target.value)}
className="field w-full"
/>
</div>
</div>
</>
)}
{/* Understat 专用: 赛季 */}
{source === 'understat' && (
{/* standings 任务专用: 赛季 */}
{(task === 'standings') && (
<div>
<label className="mb-1.5 block text-xs text-ink-500">()</label>
<label className="mb-1.5 block text-xs text-ink-500">()</label>
<input
type="number"
type="text"
value={season}
onChange={e => setSeason(e.target.value)}
placeholder="2025"
placeholder="2026-2027"
className="field w-full"
/>
</div>
)}
{/* 日期范围 */}
{source !== 'injuries' && (
<div className="grid grid-cols-1 gap-3 sm:grid-cols-2">
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<input
type="date"
value={dateFrom}
onChange={e => setDateFrom(e.target.value)}
className="field w-full"
/>
</div>
<div>
<label className="mb-1.5 block text-xs text-ink-500"></label>
<input
type="date"
value={dateTo}
onChange={e => setDateTo(e.target.value)}
className="field w-full"
/>
</div>
{/* stats 任务专用: 回填数量 */}
{(task === 'stats') && (
<div>
<label className="mb-1.5 block text-xs text-ink-500">(1-500)</label>
<input
type="number"
min={1}
max={500}
value={limit}
onChange={e => setLimit(parseInt(e.target.value) || 100)}
className="field w-full"
/>
<p className="mt-1 text-2xs text-ink-400">
source_event_id (), 1.2 /
</p>
</div>
)}
@@ -206,22 +215,24 @@ export default function CollectionPage() {
{/* 数据源说明 */}
<Card>
<CardHeader title="数据源说明" />
<CardHeader title="采集任务说明" />
<CardBody>
<div className="space-y-3">
{SOURCES.map(s => (
<div key={s.value} className="border-b border-ink-200 px-1 py-3 last:border-b-0">
{TASKS.map(t => (
<div key={t.value} className="border-b border-ink-200 px-1 py-3 last:border-b-0">
<div className="flex items-center gap-3">
<Badge status="info">{s.label}</Badge>
<p className="text-xs text-ink-600">{s.desc}</p>
<span>{t.icon}</span>
<Badge status="info">{t.label}</Badge>
<p className="text-xs text-ink-600">{t.desc}</p>
</div>
</div>
))}
</div>
<p className="mt-4 border-l-2 border-ink-300 pl-3 text-2xs leading-relaxed text-ink-500">
401 ,
(401 )
线 bzzoiro (Understat / injuries )
线 source_event_id,
</p>
</CardBody>
</Card>