feat: HDF5迁移至DuckDB存储

- 新增DuckDB Storage与ThreadSafeStorage实现
- 新增db_manager模块支持增量同步策略
- DataLoader与Sync模块适配DuckDB
- 补充迁移相关文档与测试
- 修复README文档链接

src/data/sync.py

@@ -36,7 +36,7 @@ import threading
 import sys
 
 from src.data.client import TushareClient
-from src.data.storage import Storage
+from src.data.storage import ThreadSafeStorage
 from src.data.api_wrappers import get_daily
 from src.data.api_wrappers import (
     get_first_trading_day,
@@ -83,7 +83,7 @@ class DataSync:
         Args:
             max_workers: Number of worker threads (default: 10)
         """
-        self.storage = Storage()
+        self.storage = ThreadSafeStorage()
         self.client = TushareClient()
         self.max_workers = max_workers or self.DEFAULT_MAX_WORKERS
         self._stop_flag = threading.Event()
@@ -667,11 +667,15 @@ class DataSync:
             finally:
                 pbar.close()
 
-        # Write all data at once (only if no error)
+        # Queue all data for batch write (only if no error)
         if results and not error_occurred:
-            combined_data = pd.concat(results.values(), ignore_index=True)
-            self.storage.save("daily", combined_data, mode="append")
-            print(f"\n[DataSync] Saved {len(combined_data)} rows to storage")
+            for ts_code, data in results.items():
+                if not data.empty:
+                    self.storage.queue_save("daily", data)
+            # Flush all queued writes at once
+            self.storage.flush()
+            total_rows = sum(len(df) for df in results.values())
+            print(f"\n[DataSync] Saved {total_rows} rows to storage")
 
         # Summary
         print("\n" + "=" * 60)