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

app/routes/pages.py

@@ -2,18 +2,20 @@
 
 from __future__ import annotations
 
+import json
 import logging
+import re
 from datetime import date, timedelta
-from pathlib import Path
 
 from fastapi import APIRouter, Depends, HTTPException, Query, Request
 from fastapi.responses import RedirectResponse
+from sqlalchemy import select
 from sqlalchemy.orm import Session, joinedload
 
 from app.config import settings
 from app.database import get_db
-from app.models import Paper
-from app.utils import templates, today_str
+from app.models import PAPER_FULL_LOAD, Paper
+from app.utils import PAPERS_DIR, safe_json_loads, templates, today_str, latest_paper_date
 
 logger = logging.getLogger(__name__)
 
@@ -21,9 +23,9 @@ router = APIRouter()
 
 
 @router.get("/")
-def index(request: Request):
-    """重定向到 /day/{today}。"""
-    return RedirectResponse(url=f"/day/{today_str()}")
+def index(request: Request, db: Session = Depends(get_db)):
+    """重定向到最新有论文的日期页。"""
+    return RedirectResponse(url=f"/day/{latest_paper_date(db)}")
 
 
 @router.get("/day/{date_str}")
@@ -39,23 +41,24 @@ def day_page(date_str: str, request: Request, db: Session = Depends(get_db)):
     today = today_str()
 
     papers = (
-        db.query(Paper)
-        .filter(Paper.paper_date == date_str)
-        .options(
-            joinedload(Paper.authors),
-            joinedload(Paper.tags),
-            joinedload(Paper.summary_status),
-            joinedload(Paper.bookmark),
+        db.execute(
+            select(Paper)
+            .where(Paper.paper_date == date_str)
+            .options(*PAPER_FULL_LOAD)
+            .order_by(Paper.upvotes.desc())
         )
-        .order_by(Paper.upvotes.desc())
+        .scalars()
+        .unique()
         .all()
     )
 
     dates_raw = (
-        db.query(Paper.paper_date)
-        .distinct()
-        .order_by(Paper.paper_date.desc())
-        .limit(30)
+        db.execute(
+            select(Paper.paper_date)
+            .distinct()
+            .order_by(Paper.paper_date.desc())
+            .limit(30)
+        )
         .all()
     )
     available_dates = [
@@ -81,18 +84,17 @@ def day_page(date_str: str, request: Request, db: Session = Depends(get_db)):
 def paper_detail(arxiv_id: str, request: Request, db: Session = Depends(get_db)):
     """论文详情页。"""
     paper = (
-        db.query(Paper)
-        .filter(Paper.arxiv_id == arxiv_id)
-        .options(
-            joinedload(Paper.authors),
-            joinedload(Paper.tags),
-            joinedload(Paper.summary),
-            joinedload(Paper.summary_status),
-            joinedload(Paper.bookmark),
-            joinedload(Paper.reading_status),
-            joinedload(Paper.note),
+        db.execute(
+            select(Paper)
+            .where(Paper.arxiv_id == arxiv_id)
+            .options(
+                joinedload(Paper.summary),
+                joinedload(Paper.note),
+                *PAPER_FULL_LOAD,
+            )
         )
-        .first()
+        .unique()
+        .scalar_one_or_none()
     )
     if not paper:
         raise HTTPException(status_code=404, detail="Paper not found")
@@ -108,28 +110,15 @@ def paper_detail(arxiv_id: str, request: Request, db: Session = Depends(get_db))
     images = _get_paper_images(arxiv_id)
 
     # 预处理 JSON 字段供模板直接使用
-    import json as _json
-
-    prereqs = {}
-    if paper.summary and paper.summary.prerequisites_json:
-        try:
-            prereqs = _json.loads(paper.summary.prerequisites_json)
-        except (ValueError, TypeError):
-            pass
-
-    benchmarks = []
-    if paper.summary and paper.summary.results_benchmarks_json:
-        try:
-            benchmarks = _json.loads(paper.summary.results_benchmarks_json)
-        except (ValueError, TypeError):
-            pass
-
-    figures_raw = []
-    if paper.summary and paper.summary.figures_json:
-        try:
-            figures_raw = _json.loads(paper.summary.figures_json)
-        except (ValueError, TypeError):
-            pass
+    prereqs = safe_json_loads(
+        paper.summary.prerequisites_json if paper.summary else None, default={}
+    )
+    benchmarks = safe_json_loads(
+        paper.summary.results_benchmarks_json if paper.summary else None, default=[]
+    )
+    figures_raw = safe_json_loads(
+        paper.summary.figures_json if paper.summary else None, default=[]
+    )
 
     linked_figures = _link_figures_with_images(figures_raw, images, arxiv_id)
 
@@ -228,9 +217,12 @@ def _get_similar_papers(db: Session, arxiv_id: str, top_k: int = 6) -> list[dict
             return []
 
         papers = (
-            db.query(Paper)
-            .filter(Paper.arxiv_id.in_(list(papers_info.keys())))
-            .options(joinedload(Paper.tags))
+            db.execute(
+                select(Paper)
+                .where(Paper.arxiv_id.in_(list(papers_info.keys())))
+                .options(joinedload(Paper.tags))
+            )
+            .scalars()
             .all()
         )
 
@@ -260,7 +252,7 @@ def _get_similar_papers(db: Session, arxiv_id: str, top_k: int = 6) -> list[dict
 
 def _get_paper_images(arxiv_id: str) -> list[dict]:
     """获取论文提取的图片列表。"""
-    images_dir = Path("data/papers") / arxiv_id / "images"
+    images_dir = PAPERS_DIR / arxiv_id / "images"
     if not images_dir.exists():
         return []
 
@@ -286,15 +278,12 @@ def _link_figures_with_images(
     if not figures or not images:
         return figures
 
-    import json as _json
-    import re
-
-    manifest_path = Path("data/papers") / arxiv_id / "images" / "manifest.json"
+    manifest_path = PAPERS_DIR / arxiv_id / "images" / "manifest.json"
     if not manifest_path.exists():
         return figures
 
     try:
-        manifest = _json.loads(manifest_path.read_text(encoding="utf-8"))
+        manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
     except (ValueError, TypeError):
         return figures