feat: add admin dashboard, pipeline service, lightbox, and update dependencies

2026-06-09 09:32:10 +08:00
parent 0d293422ac
commit 32978b3fc5
50 changed files with 4054 additions and 1618 deletions
@@ -0,0 +1,109 @@
+"""管理后台服务 — 统计聚合、系统状态。"""
+
+from __future__ import annotations
+
+from datetime import date
+from pathlib import Path
+
+from sqlalchemy import func, select, text
+from sqlalchemy.orm import Session
+
+from app.config import settings
+from app.models import CrawlLog, Paper, SummaryState, TaskLock
+from app.services.scheduler import get_scheduler
+from app.utils import PAPERS_DIR, TMP_DIR
+
+
+def _dir_size(path: Path) -> int:
+    """递归计算目录总字节数。"""
+    if not path.exists():
+        return 0
+    return sum(f.stat().st_size for f in path.rglob("*") if f.is_file())
+
+
+def _fmt_size(nbytes: int) -> str:
+    """字节数 → 人类可读字符串。"""
+    for unit in ("B", "KB", "MB", "GB"):
+        if nbytes < 1024:
+            return f"{nbytes:.1f} {unit}"
+        nbytes /= 1024
+    return f"{nbytes:.1f} TB"
+
+
+def get_admin_stats(db: Session) -> dict:
+    """管理仪表盘统计数据。"""
+    today = date.today()
+
+    # ── 论文统计 ──────────────────────────────────────────────────────
+    total_papers = db.scalar(select(func.count(Paper.id)))
+    today_papers = db.scalar(
+        select(func.count(Paper.id)).where(Paper.paper_date == today)
+    )
+
+    # ── 总结状态分布 ──────────────────────────────────────────────────
+    summary_rows = db.execute(
+        text("""
+            SELECT COALESCE(ss.status, 'none') AS status, COUNT(*) AS cnt
+            FROM papers p
+            LEFT JOIN summary_status ss ON ss.paper_id = p.id
+            GROUP BY status
+        """)
+    ).fetchall()
+    status_counts = {row[0]: row[1] for row in summary_rows}
+
+    # ── 存储概况 ──────────────────────────────────────────────────────
+    db_size = _fmt_size(settings.db_path.stat().st_size) if settings.db_path.exists() else "0 B"
+    papers_size = _fmt_size(_dir_size(PAPERS_DIR))
+    tmp_size = _fmt_size(_dir_size(TMP_DIR))
+
+    # ── 调度器状态 ────────────────────────────────────────────────────
+    scheduler = get_scheduler()
+    scheduler_enabled = scheduler is not None
+    next_run = None
+    if scheduler_enabled:
+        for job in scheduler.get_jobs():
+            if job.id == "daily_pipeline":
+                next_run = job.next_run_time
+                break
+
+    # ── 最近日志（5 条） ──────────────────────────────────────────────
+    recent_logs = (
+        db.execute(
+            select(CrawlLog)
+            .order_by(CrawlLog.started_at.desc())
+            .limit(5)
+        )
+        .scalars()
+        .all()
+    )
+
+    # ── 活跃锁 ────────────────────────────────────────────────────────
+    active_locks = (
+        db.execute(
+            select(TaskLock).where(TaskLock.status == "running")
+        )
+        .scalars()
+        .all()
+    )
+
+    return {
+        "total_papers": total_papers or 0,
+        "today_papers": today_papers or 0,
+        "pending_count": status_counts.get(SummaryState.PENDING, 0),
+        "failed_count": status_counts.get(SummaryState.FAILED, 0)
+        + status_counts.get(SummaryState.PERMANENT_FAILURE, 0),
+        "done_count": status_counts.get(SummaryState.DONE, 0),
+        "running_count": status_counts.get("running", 0)
+        + status_counts.get(SummaryState.PROCESSING, 0),
+        "none_count": status_counts.get("none", 0),
+        "status_counts": status_counts,
+        "db_size": db_size,
+        "papers_size": papers_size,
+        "tmp_size": tmp_size,
+        "scheduler_enabled": scheduler_enabled,
+        "schedule_time": f"{settings.SCHEDULE_HOUR:02d}:{settings.SCHEDULE_MINUTE:02d}",
+        "timezone": settings.APP_TIMEZONE,
+        "next_run": next_run.isoformat() if next_run else None,
+        "recent_logs": recent_logs,
+        "active_locks": active_locks,
+    }