Update sync_data.sh

sync_data.sh

@@ -1,33 +1,38 @@
-#!/bin/sh
+#!/bin/bash
 
-# 设置默认的同步间隔为 600 秒 (10 分钟)，可以作为环境变量传入
-SYNC_INTERVAL=${SYNC_INTERVAL:-600}
-
-# 设置备份保留数量，默认为 5，可以作为环境变量传入
-BACKUP_RETENTION=${BACKUP_RETENTION:-5}
-
-# 检查环境变量
+# 检查 Hugging Face Token 和 Dataset ID 环境变量
 if [[ -z "$HF_TOKEN" ]] || [[ -z "$DATASET_ID" ]]; then
-    echo "Starting without backup functionality - missing HF_TOKEN or DATASET_ID"
-    exec ./cloudreve
+    echo "Starting Cloudreve without backup functionality - missing HF_TOKEN or DATASET_ID"
+    exec /opt/cloudreve/cloudreve -c /opt/cloudreve/config.ini
     exit 0
 fi
 
-# 激活虚拟环境
-. /opt/venv/bin/activate
+# 定义 Cloudreve 数据目录和配置文件路径
+DATA_DIR="/opt/cloudreve/data"
+CONFIG_FILE="/opt/cloudreve/config.ini"
+BACKUP_PREFIX="cloudreve_backup"
 
-# 上传备份
+# 激活 Python 虚拟环境
+if [ -f "/opt/venv/bin/activate" ]; then
+    source /opt/venv/bin/activate
+fi
+
+# Python 函数：上传备份
 upload_backup() {
-    file_path="$1"
-    file_name="$2"
+    local file_path="$1"
+    local file_name="$2"
+    local token="$HF_TOKEN"
+    local repo_id="$DATASET_ID"
 
     python3 -c "
 from huggingface_hub import HfApi
 import sys
 import os
-def manage_backups(api, repo_id, max_files=50):
+import glob
+
+def manage_backups(api, repo_id, max_files=5):
     files = api.list_repo_files(repo_id=repo_id, repo_type='dataset')
-    backup_files = [f for f in files if f.startswith('cloudreve_backup_') and f.endswith('.tar.gz')]
+    backup_files = [f for f in files if f.startswith('$BACKUP_PREFIX') and f.endswith('.tar.gz')]
     backup_files.sort()
 
     if len(backup_files) >= max_files:
@@ -38,108 +43,107 @@ def manage_backups(api, repo_id, max_files=50):
                 print(f'Deleted old backup: {file_to_delete}')
             except Exception as e:
                 print(f'Error deleting {file_to_delete}: {str(e)}')
-api = HfApi(token='$HF_TOKEN')
+
+api = HfApi(token='$token')
 try:
     api.upload_file(
         path_or_fileobj='$file_path',
         path_in_repo='$file_name',
-        repo_id='$DATASET_ID',
+        repo_id='$repo_id',
         repo_type='dataset'
     )
     print(f'Successfully uploaded $file_name')
 
-    manage_backups(api, '$DATASET_ID')
+    manage_backups(api, '$repo_id')
 except Exception as e:
     print(f'Error uploading file: {str(e)}')
 "
 }
 
-# 下载最新备份
+# Python 函数：下载最新备份
 download_latest_backup() {
+    local token="$HF_TOKEN"
+    local repo_id="$DATASET_ID"
+
     python3 -c "
 from huggingface_hub import HfApi
 import sys
 import os
 import tarfile
 import tempfile
-import shutil # 确保这一行存在
-api = HfApi(token='$HF_TOKEN')
+import glob
+
+api = HfApi(token='$token')
 try:
-    files = api.list_repo_files(repo_id='$DATASET_ID', repo_type='dataset')
-    backup_files = [f for f in files if f.startswith('cloudreve_backup_') and f.endswith('.tar.gz')]
+    files = api.list_repo_files(repo_id='$repo_id', repo_type='dataset')
+    backup_files = [f for f in files if f.startswith('$BACKUP_PREFIX') and f.endswith('.tar.gz')]
 
     if not backup_files:
-        print('在 HuggingFace Dataset 上没有找到备份文件')
-        sys.exit(0)
+        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='$DATASET_ID',
+            repo_id='$repo_id',
             filename=latest_backup,
             repo_type='dataset',
             local_dir=temp_dir
         )
 
         if filepath and os.path.exists(filepath):
-            print(f'找到最新的备份：{latest_backup}，尝试恢复...')
-            # 删除现有的数据目录
-            if os.path.isdir('/opt/cloudreve/data'):
-                print('删除现有的数据目录:/opt/cloudreve/data')
-                shutil.rmtree('/opt/cloudreve/data')
-            # 创建数据目录（如果被删除）
-            os.makedirs('/opt/cloudreve/data', exist_ok=True)
-
+            # 删除现有的数据目录和配置文件
+            if [ -d \"$DATA_DIR\" ]; then
+                echo \"Deleting existing data directory: $DATA_DIR\"
+                rm -rf \"$DATA_DIR\"
+            fi
+            if [ -f \"$CONFIG_FILE\" ]; then
+                echo \"Deleting existing config file: $CONFIG_FILE\"
+                rm -rf \"$CONFIG_FILE\"
+            fi
+            mkdir -p \"$DATA_DIR\"
             with tarfile.open(filepath, 'r:gz') as tar:
-                tar.extractall('/opt/cloudreve/data')
-            print(f'成功从 {latest_backup} 恢复备份')
-
+                tar.extractall(\"/opt/cloudreve\") # 将备份恢复到 /opt/cloudreve 目录
+            echo f'Successfully restored backup from {latest_backup}'
 except Exception as e:
-    print('从 HuggingFace Dataset 下载备份时出错：{}'.format(e))
+    print(f'Error downloading backup: {str(e)}')
 "
 }
 
-# 首次启动时下载最新备份和后续每次启动时都尝试恢复
-echo "尝试从 HuggingFace Dataset 下载并恢复最新备份..."
+# 首次启动时下载最新备份
+echo "Downloading latest backup from HuggingFace..."
 download_latest_backup
 
-# 同步函数
+# 后台启动同步进程
 sync_data() {
     while true; do
-        echo "开始同步进程于 $(date)"
+        echo "Starting sync process at $(date)"
 
-        if [ -d /opt/cloudreve/data ]; then
+        if [ -d "$DATA_DIR" ]; then
             timestamp=$(date +%Y%m%d_%H%M%S)
-            backup_file="cloudreve_backup_${timestamp}.tar.gz"
-            backup_file_path="/tmp/${backup_file}"
-
-            echo "创建备份归档：${backup_file_path}"
-            echo "在备份之前列出 /opt/cloudreve/data 的内容："
-            ls -al /opt/cloudreve/data
-
-            # 尝试直接打包 /opt/cloudreve/data 目录，并显示详细信息
-            tar -czvf "${backup_file_path}" /opt/cloudreve/data
-
-            if [ -f "${backup_file_path}" ]; then
-                echo "正在上传备份到 HuggingFace Dataset..."
-                upload_backup "${backup_file_path}" "${backup_file}"
-                rm -f "${backup_file_path}"
-            else:
-                echo "创建备份归档失败。"
-            fi
-        else:
-            echo "数据目录尚不存在，等待下一次同步..."
+            backup_file="${BACKUP_PREFIX}_${timestamp}.tar.gz"
+            backup_path="/tmp/${backup_file}"
+
+            echo "Compressing data directory and config file..."
+            tar -czf "$backup_path" -C /opt/cloudreve cloudreve config.ini
+
+            echo "Uploading backup to HuggingFace..."
+            upload_backup "$backup_path" "${backup_file}"
+
+            rm -f "$backup_path"
+        else
+            echo "Data directory does not exist yet, waiting for next sync..."
         fi
 
-        SYNC_INTERVAL=${SYNC_INTERVAL:-7200}
-        echo "下一次同步将在 ${SYNC_INTERVAL} 秒后进行..."
-        sleep "$SYNC_INTERVAL"
+        SYNC_INTERVAL=${SYNC_INTERVAL:-3600} # 默认同步间隔为 1 小时
+        echo "Next sync in ${SYNC_INTERVAL} seconds..."
+        sleep $SYNC_INTERVAL
     done
 }
 
-# 后台启动同步进程
 sync_data &
 
 # 启动 Cloudreve
-exec ./cloudreve
+echo "Starting Cloudreve..."
+exec /opt/cloudreve/cloudreve -c /opt/cloudreve/config.ini