Update sync_data.sh

sync_data.sh

@@ -6,8 +6,11 @@ if [ -z "$HF_TOKEN" ] || [ -z "$DATASET_ID" ]; then
     exit 1
 fi
 
+# 激活虚拟环境
+. /home/app/venv/bin/activate
+
 # 上传备份
-cat > /home/app/hf_sync.py << 'EOL'
+cat > hf_sync.py << 'EOL'
 from huggingface_hub import HfApi
 import sys
 import os
@@ -44,7 +47,7 @@ def upload_backup(file_path, file_name, token, repo_id):
         print(f"Error uploading file: {str(e)}")
 
 # 下载最新备份
-def download_latest_backup(token, repo_id):
+def download_latest_backup(token, repo_id, extract_path):
     try:
         api = HfApi(token=token)
         files = api.list_repo_files(repo_id=repo_id, repo_type="dataset")
@@ -66,7 +69,7 @@ def download_latest_backup(token, repo_id):
             
             if filepath and os.path.exists(filepath):
                 with tarfile.open(filepath, 'r:gz') as tar:
-                    tar.extractall('/home/app/storage/')
+                    tar.extractall(extract_path)  # 解压到指定路径
                 print(f"Successfully restored backup from {latest_backup}")
                 
     except Exception as e:
@@ -82,27 +85,28 @@ if __name__ == "__main__":
         file_name = sys.argv[5]
         upload_backup(file_path, file_name, token, repo_id)
     elif action == "download":
-        download_latest_backup(token, repo_id)
+        extract_path = sys.argv[4] if len(sys.argv) > 4 else '.'  # 默认为当前目录
+        download_latest_backup(token, repo_id, extract_path)
 EOL
 
-# 首次启动时从HuggingFace下载最新备份
+# 首次启动时从HuggingFace下载最新备份（解压到应用目录）
 echo "Downloading latest backup from HuggingFace..."
-python3 hf_sync.py download "${HF_TOKEN}" "${DATASET_ID}"
+python hf_sync.py download "${HF_TOKEN}" "${DATASET_ID}" "./"  
 
 # 同步函数
 sync_data() {
     while true; do
         echo "Starting sync process at $(date)"
         
-        # 确保数据目录存在
-        if [ -d "/home/app/storage" ]; then
+        # 确保数据目录存在（选择你的实际路径）
+        STORAGE_PATH="./storage"  # 或改为"./storage"
+        if [ -d "${STORAGE_PATH}" ]; then
             # 创建备份
-            cd /home/app/
             timestamp=$(date +%Y%m%d_%H%M%S)
             backup_file="backup_${timestamp}.tar.gz"
             
-            # 压缩数据目录
-            tar -czf "/tmp/${backup_file}" storage/
+            # 压缩目录（使用-C避免包含父路径）
+            tar -czf "/tmp/${backup_file}" -C "$(dirname "${STORAGE_PATH}")" "$(basename "${STORAGE_PATH}")"
             
             # 上传到HuggingFace
             echo "Uploading backup to HuggingFace..."
@@ -111,7 +115,7 @@ sync_data() {
             # 清理临时文件
             rm -f "/tmp/${backup_file}"
         else
-            echo "Data directory does not exist yet, waiting for next sync..."
+            echo "Storage directory ${STORAGE_PATH} does not exist, waiting..."
         fi
         
         # 同步间隔
@@ -124,5 +128,5 @@ sync_data() {
 # 启动同步进程
 sync_data &
 
-# 启动主应用
-exec bash install_reader.sh
+# 启动主应用（根据实际路径调整）
+exec node /app/server.js  # 或改为你的启动命令