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/database.py

@@ -1,6 +1,6 @@
 """数据库引擎、会话工厂、初始化。"""
 
-from sqlalchemy import event, create_engine
+from sqlalchemy import event, create_engine, text
 from sqlalchemy.orm import DeclarativeBase, sessionmaker
 
 from app.config import settings
@@ -10,6 +10,27 @@ class Base(DeclarativeBase):
     pass
 
 
+# ── FTS5 和索引 DDL（与 ORM 模型分开管理）───────────────────────────────
+
+FTS5_CREATE_SQL = """
+CREATE VIRTUAL TABLE IF NOT EXISTS papers_fts USING fts5(
+    title_en,
+    title_zh,
+    abstract,
+    authors,
+    tags,
+    summary_text,
+    tokenize='unicode61'
+);
+"""
+
+FTS5_TRIGGER_INDEX = """
+-- partial index for task_locks running
+CREATE UNIQUE INDEX IF NOT EXISTS uq_task_locks_running
+ON task_locks(task, lock_key) WHERE status = 'running';
+"""
+
+
 def _make_engine():
     """创建 SQLite 引擎，启用 foreign_keys。"""
     engine = create_engine(
@@ -39,3 +60,14 @@ def get_db():
         yield db
     finally:
         db.close()
+
+
+def init_db(engine):
+    """创建所有 ORM 表 + FTS5 虚拟表。"""
+    from app.models import Base  # noqa: F811 — 避免循环导入，延迟导入
+
+    Base.metadata.create_all(engine)
+    with engine.connect() as conn:
+        conn.execute(text(FTS5_CREATE_SQL))
+        conn.execute(text(FTS5_TRIGGER_INDEX))
+        conn.commit()