big update

backend/app/api/endpoints/events.py

@@ -1,69 +1,215 @@
 # app/api/endpoints/events.py
-from fastapi import APIRouter, Depends, Query
-from sqlalchemy.orm import Session
 from datetime import timedelta
 from typing import List
 
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy.orm import Session
+
 from app.api.dependencies import get_db
-from app.models.models import UnifiedEvent, TrendingEvent, InfoSource, RankingLog, utcnow
-# 导入你上传的 Schema
-from app.schemas.event_schema import UnifiedEventResponse, PlatformTrendResponse
+from app.models.models import (
+    ExtractedTopic,
+    InfoSource,
+    RankingLog,
+    TargetType,
+    TrendingEvent,
+    UnifiedEvent,
+    utcnow,
+)
+from app.schemas.event_schema import (
+    PaginatedUnifiedEventResponse,
+    PlatformTrendResponse,
+    UnifiedEventResponse,
+)
 
 router = APIRouter()
 
+# 排名轨迹最多返回多少个点，避免长时间跨度下数据过大
+MAX_RANKING_POINTS = 30
 
-@router.get("/unified", response_model=List[UnifiedEventResponse])
+
+@router.get("/unified", response_model=PaginatedUnifiedEventResponse)
 def list_unified_events(
-        min_hot: int = Query(5, description="热度过滤阈值"),
-        hours: int = Query(24, description="查询过去 X 小时的数据"),
-        db: Session = Depends(get_db)
+    min_hot: int = Query(5, ge=0, description="热度阈值，仅返回 hot_score >= 此值的事件"),
+    hours: int = Query(24, ge=1, le=720, description="查询最近多少小时的数据"),
+    skip: int = Query(0, ge=0, description="分页偏移量"),
+    limit: int = Query(10, ge=1, le=50, description="每页返回条数"),
+    db: Session = Depends(get_db),
 ):
-    """
-    获取聚合大事件列表，完全适配前端 template.html 所需的数据结构
-    """
-    # 计算时间水位线
+    """分页返回统一事件，附带各平台热搜、排名轨迹和标签。"""
     time_limit = utcnow() - timedelta(hours=hours)
 
-    # 1. 查询大事件（按热度降序，且满足时间范围）
-    events = db.query(UnifiedEvent).filter(
+    # 先查总数，用于前端判断是否还有更多
+    base_query = db.query(UnifiedEvent).filter(
         UnifiedEvent.hot_score >= min_hot,
-        UnifiedEvent.created_at >= time_limit
-    ).order_by(UnifiedEvent.hot_score.desc()).all()
+        UnifiedEvent.created_at >= time_limit,
+    )
+    total = base_query.count()
 
-    results = []
+    # 分页查询
+    events = (
+        base_query
+        .order_by(UnifiedEvent.hot_score.desc())
+        .offset(skip)
+        .limit(limit)
+        .all()
+    )
+
+    if not events:
+        return PaginatedUnifiedEventResponse(total=total, has_more=False, data=[])
+
+    event_ids = [ev.id for ev in events]
+
+    # 批量查询所有相关的热搜条目（避免 N+1）
+    trend_rows = (
+        db.query(TrendingEvent, InfoSource.source_name)
+        .join(InfoSource, TrendingEvent.source_id == InfoSource.id)
+        .filter(TrendingEvent.unified_event_id.in_(event_ids))
+        .all()
+    )
+
+    # 按 unified_event_id 分组
+    trend_map: dict[int, list[tuple]] = {}
+    trend_ids: list[int] = []
+    for trend, source_name in trend_rows:
+        trend_map.setdefault(trend.unified_event_id, []).append((trend, source_name))
+        trend_ids.append(trend.id)
+
+    # 批量查询排名日志（避免逐条查询）
+    ranking_map: dict[int, list[int]] = {}
+    if trend_ids:
+        ranking_rows = (
+            db.query(
+                RankingLog.event_id,
+                RankingLog.ranking_position,
+            )
+            .filter(
+                RankingLog.event_id.in_(trend_ids),
+                RankingLog.observed_at >= time_limit,
+            )
+            .order_by(RankingLog.event_id, RankingLog.observed_at.asc())
+            .all()
+        )
+        for event_id, position in ranking_rows:
+            ranking_map.setdefault(event_id, []).append(position)
+
+    # 批量查询标签
+    tag_map: dict[int, list[str]] = {}
+    tag_rows = (
+        db.query(ExtractedTopic.target_id, ExtractedTopic.topic_keyword)
+        .filter(
+            ExtractedTopic.target_type == TargetType.EVENT,
+            ExtractedTopic.target_id.in_(event_ids),
+        )
+        .order_by(ExtractedTopic.relevance_score.desc(), ExtractedTopic.created_at.desc())
+        .all()
+    )
+    for target_id, keyword in tag_rows:
+        tag_map.setdefault(target_id, []).append(keyword)
+
+    # 组装响应
+    results: list[UnifiedEventResponse] = []
     for ev in events:
-        # 2. 联表查询：获取该大事件下关联的所有平台及其具体热搜信息
-        trends = db.query(TrendingEvent, InfoSource.source_name).join(
-            InfoSource, TrendingEvent.source_id == InfoSource.id
-        ).filter(TrendingEvent.unified_event_id == ev.id).all()
+        platform_list: list[PlatformTrendResponse] = []
+        for trend, source_name in trend_map.get(ev.id, []):
+            history = ranking_map.get(trend.id, [])
+            # 截取尾部，只保留最近的点
+            if len(history) > MAX_RANKING_POINTS:
+                history = history[-MAX_RANKING_POINTS:]
 
-        platform_list = []
-        for trend, s_name in trends:
-            # 3. 获取排名历史轨迹 (用于前端渲染)
-            # 这里的排序顺序 asc 保证了数组从旧到新
-            logs = db.query(RankingLog.ranking_position).filter(
-                RankingLog.event_id == trend.id,
-                RankingLog.observed_at >= time_limit
-            ).order_by(RankingLog.observed_at.asc()).all()
+            platform_list.append(
+                PlatformTrendResponse(
+                    source_id=trend.source_id,
+                    platform_name=source_name,
+                    headline=trend.current_headline,
+                    url=trend.event_url,
+                    current_ranking=trend.current_ranking,
+                    ranking_history=history,
+                )
+            )
 
-            # 组装符合 PlatformTrendResponse 结构的字典
-            platform_list.append(PlatformTrendResponse(
+        results.append(
+            UnifiedEventResponse(
+                event_id=ev.id,
+                unified_title=ev.unified_title if ev.unified_title else "暂无标题",
+                summary=ev.ai_comprehensive_summary,
+                hot_score=ev.hot_score,
+                created_at=ev.created_at,
+                platforms=platform_list,
+                tags=tag_map.get(ev.id, []),
+            )
+        )
+
+    has_more = (skip + limit) < total
+    return PaginatedUnifiedEventResponse(total=total, has_more=has_more, data=results)
+
+
+@router.get("/unified/{event_id}", response_model=UnifiedEventResponse)
+def get_unified_event(
+    event_id: int,
+    db: Session = Depends(get_db),
+):
+    """按 ID 查询单个统一事件，用于推荐跳转时的聚光灯展示。"""
+    ev = db.query(UnifiedEvent).filter(UnifiedEvent.id == event_id).first()
+    if not ev:
+        raise HTTPException(status_code=404, detail="Event not found")
+
+    time_limit = utcnow() - timedelta(hours=720)
+
+    trend_rows = (
+        db.query(TrendingEvent, InfoSource.source_name)
+        .join(InfoSource, TrendingEvent.source_id == InfoSource.id)
+        .filter(TrendingEvent.unified_event_id == event_id)
+        .all()
+    )
+
+    trend_ids = [t.id for t, _ in trend_rows]
+    ranking_map: dict[int, list[int]] = {}
+    if trend_ids:
+        ranking_rows = (
+            db.query(RankingLog.event_id, RankingLog.ranking_position)
+            .filter(
+                RankingLog.event_id.in_(trend_ids),
+                RankingLog.observed_at >= time_limit,
+            )
+            .order_by(RankingLog.event_id, RankingLog.observed_at.asc())
+            .all()
+        )
+        for eid, pos in ranking_rows:
+            ranking_map.setdefault(eid, []).append(pos)
+
+    tag_rows = (
+        db.query(ExtractedTopic.topic_keyword)
+        .filter(
+            ExtractedTopic.target_type == TargetType.EVENT,
+            ExtractedTopic.target_id == event_id,
+        )
+        .order_by(ExtractedTopic.relevance_score.desc())
+        .all()
+    )
+    tags = [row[0] for row in tag_rows]
+
+    platform_list: list[PlatformTrendResponse] = []
+    for trend, source_name in trend_rows:
+        history = ranking_map.get(trend.id, [])
+        if len(history) > MAX_RANKING_POINTS:
+            history = history[-MAX_RANKING_POINTS:]
+        platform_list.append(
+            PlatformTrendResponse(
                 source_id=trend.source_id,
-                platform_name=s_name,
+                platform_name=source_name,
                 headline=trend.current_headline,
                 url=trend.event_url,
                 current_ranking=trend.current_ranking,
-                ranking_history=[log[0] for log in logs]
-            ))
+                ranking_history=history,
+            )
+        )
 
-        # 4. 组装符合 UnifiedEventResponse 结构的字典
-        results.append(UnifiedEventResponse(
-            event_id=ev.id,
-            unified_title=ev.unified_title if ev.unified_title else "暂无标题",
-            summary=ev.ai_comprehensive_summary,
-            hot_score=ev.hot_score,
-            created_at=ev.created_at,
-            platforms=platform_list
-        ))
-
-    return results
+    return UnifiedEventResponse(
+        event_id=ev.id,
+        unified_title=ev.unified_title if ev.unified_title else "暂无标题",
+        summary=ev.ai_comprehensive_summary,
+        hot_score=ev.hot_score,
+        created_at=ev.created_at,
+        platforms=platform_list,
+        tags=tags,
+    )