refactor: restructure services and add image/pdf extraction utilities

- Add image_extractor, pdf_downloader, pi_client, trends services
- Add shared utils module
- Refactor summarizer, embedder, routes for cleaner separation
- Update tests to match new service structure

app/services/user_data.py

@@ -1,12 +1,13 @@
-"""用户数据服务 — 收藏、阅读状态、个人笔记。无账号体系，数据写入本地 SQLite。"""
+"""用户数据服务 — 收藏、阅读状态、个人笔记、阅读列表查询。无账号体系，数据写入本地 SQLite。"""
 
 from __future__ import annotations
 
 from datetime import datetime, timezone
 
-from sqlalchemy.orm import Session
+from sqlalchemy import or_
+from sqlalchemy.orm import Session, joinedload
 
-from app.models import Paper, UserBookmark, UserNote, UserReadingStatus
+from app.models import Paper, PaperTag, UserBookmark, UserNote, UserReadingStatus
 
 # ── 收藏 ──────────────────────────────────────────────────────────────
 
@@ -113,3 +114,47 @@ def save_note(db: Session, arxiv_id: str, content: str) -> dict:
         "content": content,
         "updated_at": now.isoformat(),
     }
+
+
+# ── 阅读列表 ──────────────────────────────────────────────────────────
+
+
+def query_reading_list(
+    db: Session,
+    filter_type: str,
+    tag: str | None,
+) -> list[Paper]:
+    """根据筛选条件查询阅读列表。"""
+    # 基础：有任意用户数据的论文
+    base = db.query(Paper).filter(
+        or_(
+            Paper.bookmark.has(),
+            Paper.reading_status.has(),
+            Paper.note.has(),
+        )
+    )
+
+    # 应用筛选
+    if filter_type == "has_note":
+        base = base.filter(Paper.note.has())
+    elif filter_type in ("unread", "skimmed", "read_summary", "read_full"):
+        base = base.filter(
+            Paper.reading_status.has(UserReadingStatus.status == filter_type)
+        )
+
+    # 应用标签
+    if tag:
+        base = base.filter(Paper.tags.any(PaperTag.tag == tag))
+
+    return (
+        base.options(
+            joinedload(Paper.authors),
+            joinedload(Paper.tags),
+            joinedload(Paper.summary_status),
+            joinedload(Paper.bookmark),
+            joinedload(Paper.reading_status),
+            joinedload(Paper.note),
+        )
+        .order_by(Paper.paper_date.desc(), Paper.upvotes.desc())
+        .all()
+    )