Update sync_data.sh

sync_data.sh

@@ -1,4 +1,5 @@
 #!/bin/sh
+
 # 检查环境变量
 if [ -z "$HF_TOKEN" ] || [ -z "$DATASET_ID" ]; then
     echo "Starting without backup functionality - missing HF_TOKEN or DATASET_ID"
@@ -9,35 +10,30 @@ fi
 # 激活虚拟环境
 . /opt/venv/bin/activate
 
-# 上传备份（含自动清理旧备份）
+# 上传备份
 upload_backup() {
     file_path="$1"
     file_name="$2"
+    
     python3 -c "
 from huggingface_hub import HfApi
 import sys
 import os
-
 def manage_backups(api, repo_id, max_files=50):
     files = api.list_repo_files(repo_id=repo_id, repo_type='dataset')
     backup_files = [f for f in files if f.startswith('electerm_backup_') and f.endswith('.tar.gz')]
     backup_files.sort()
+    
     if len(backup_files) >= max_files:
-        files_to_delete = backup_files[:len(backup_files) - max_files + 1]
+        files_to_delete = backup_files[:(len(backup_files) - max_files + 1)]
         for file_to_delete in files_to_delete:
             try:
-                api.delete_file(
-                    path_in_repo=file_to_delete,
-                    repo_id=repo_id,
-                    repo_type='dataset'
-                )
+                api.delete_file(path_in_repo=file_to_delete, repo_id=repo_id, repo_type='dataset')
                 print(f'Deleted old backup: {file_to_delete}')
             except Exception as e:
                 print(f'Error deleting {file_to_delete}: {str(e)}')
-
 api = HfApi(token='$HF_TOKEN')
 try:
-    # 上传新备份
     api.upload_file(
         path_or_fileobj='$file_path',
         path_in_repo='$file_name',
@@ -46,14 +42,13 @@ try:
     )
     print(f'Successfully uploaded $file_name')
     
-    # 清理旧备份
     manage_backups(api, '$DATASET_ID')
 except Exception as e:
     print(f'Error uploading file: {str(e)}')
 "
 }
 
-# 下载最新备份（补充完整）
+# 下载最新备份
 download_latest_backup() {
     python3 -c "
 from huggingface_hub import HfApi
@@ -61,15 +56,17 @@ import sys
 import os
 import tarfile
 import tempfile
-
 api = HfApi(token='$HF_TOKEN')
 try:
     files = api.list_repo_files(repo_id='$DATASET_ID', repo_type='dataset')
     backup_files = [f for f in files if f.startswith('electerm_backup_') and f.endswith('.tar.gz')]
+    
     if not backup_files:
         print('No backup files found')
         sys.exit()
+        
     latest_backup = sorted(backup_files)[-1]
+    
     with tempfile.TemporaryDirectory() as temp_dir:
         filepath = api.hf_hub_download(
             repo_id='$DATASET_ID',
@@ -77,17 +74,12 @@ try:
             repo_type='dataset',
             local_dir=temp_dir
         )
+        
         if filepath and os.path.exists(filepath):
-            # 确保目标目录存在
-            os.makedirs('/app/electerm-web/data', exist_ok=True)
-            # 清空旧数据（防止残留文件干扰）
-            if os.listdir('/app/electerm-web/data'):
-                for f in os.listdir('/app/electerm-web/data'):
-                    os.remove(os.path.join('/app/electerm-web/data', f))
-            # 解压备份
             with tarfile.open(filepath, 'r:gz') as tar:
                 tar.extractall('/app/electerm-web/data')
             print(f'Successfully restored backup from {latest_backup}')
+        
 except Exception as e:
     print(f'Error downloading backup: {str(e)}')
 "
@@ -101,17 +93,22 @@ download_latest_backup
 sync_data() {
     while true; do
         echo "Starting sync process at $(date)"
+        
         if [ -d /app/electerm-web/data ]; then
             timestamp=$(date +%Y%m%d_%H%M%S)
             backup_file="electerm_backup_${timestamp}.tar.gz"
-            # 压缩数据目录（排除临时文件）
+            
+            # 压缩数据目录
             tar -czf "/tmp/${backup_file}" -C /app/electerm-web/data .
+            
             echo "Uploading backup to HuggingFace..."
             upload_backup "/tmp/${backup_file}" "${backup_file}"
+            
             rm -f "/tmp/${backup_file}"
         else
             echo "Data directory does not exist yet, waiting for next sync..."
         fi
+        
         SYNC_INTERVAL=${SYNC_INTERVAL:-7200}
         echo "Next sync in ${SYNC_INTERVAL} seconds..."
         sleep $SYNC_INTERVAL