sync_data.sh

#!/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"
    exit 1
fi

# 激活虚拟环境
. /home/app/venv/bin/activate

# 上传备份
cat > /home/app/uptime-kuma/hf_sync.py << 'EOL'
from huggingface_hub import HfApi
import sys
import os
import tarfile
import tempfile
import requests
import json

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('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)]
        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")
                print(f'Deleted old backup: {file_to_delete}')
            except Exception as e:
                print(f'Error deleting {file_to_delete}: {str(e)}')

def upload_backup(file_path, file_name, token, repo_id):
    api = HfApi(token=token)
    try:
        api.upload_file(
            path_or_fileobj=file_path,
            path_in_repo=file_name,
            repo_id=repo_id,
            repo_type="dataset"
        )
        print(f"Successfully uploaded {file_name}")
        
        manage_backups(api, repo_id)
    except Exception as e:
        print(f"Error uploading file: {str(e)}")

# 下载最新备份
def download_latest_backup(token, repo_id):
    try:
        api = HfApi(token=token)
        files = api.list_repo_files(repo_id=repo_id, repo_type="dataset")
        backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
        
        if not backup_files:
            print("No backup files found")
            return
            
        latest_backup = sorted(backup_files)[-1]
        
        with tempfile.TemporaryDirectory() as temp_dir:
            filepath = api.hf_hub_download(
                repo_id=repo_id,
                filename=latest_backup,
                repo_type="dataset",
                local_dir=temp_dir
            )
            
            if filepath and os.path.exists(filepath):
                with tarfile.open(filepath, 'r:gz') as tar:
                    tar.extractall('/home/app/uptime-kuma/')
                print(f"Successfully restored backup from {latest_backup}")
                
    except Exception as e:
        print(f"Error downloading backup: {str(e)}")

def clear_tmp_bak(account, password, repo_ids, save_num):
    # 登录获取 token
    login_url = "https://huggingface.co/login"
    login_data = {
        "username": account,
        "password": password
    }
    
    try:
        # 发送登录请求，允许重定向
        session = requests.Session()
        login_response = session.post(login_url, data=login_data, allow_redirects=True)
        if not login_response.ok:
            print("Login failed")
            return
            
        # 从 session 的 cookies 中获取 token
        token = session.cookies.get('token')
        if not token:
            print("Failed to get token")
            return
            
        # 准备请求头
        headers = {
            'Cookie': f'token={token}',
            'Content-Type': 'application/json'
        }

        # 处理多个仓库ID
        repo_id_list = [repo_id.strip() for repo_id in repo_ids.split(',')]
        print(f"Processing {len(repo_id_list)} repositories for cleanup")
        
        for repo_id in repo_id_list:
            print(f"\nProcessing repository: {repo_id}")
            
            # 首先获取 LFS 文件列表
            list_url = f"https://huggingface.co/api/datasets/{repo_id}/lfs-files"
            list_response = requests.get(list_url, headers=headers)
            
            if not list_response.ok:
                print(f"Failed to get file list for {repo_id}: {list_response.status_code}")
                continue
                
            # 解析文件列表并按时间排序
            files = list_response.json()
            files.sort(key=lambda x: x['pushedAt'], reverse=True)
            
            # Print current file list
            print(f"Current LFS file list for {repo_id}:")
            for file in files:
                print(f"Filename: {file['filename']}, Upload time: {file['pushedAt']}, FileOid: {file['fileOid']}")
            
            # 保留最新的文件，删除其他文件
            if len(files) > int(save_num):
                # 跳过要保留的文件
                files_to_delete = files[int(save_num):]
                sha_list = [file['fileOid'] for file in files_to_delete]
                
                lfs_url = f"https://huggingface.co/api/datasets/{repo_id}/lfs-files/batch"
                
                # 构造删除请求的数据
                delete_data = {
                    "deletions": {
                        "rewriteHistory": True,
                        "sha": sha_list
                    }
                }
                
                # 发送删除请求
                delete_response = requests.post(lfs_url, headers=headers, data=json.dumps(delete_data))
                
                if delete_response.ok:
                    print(f"Successfully deleted {len(sha_list)} old files from {repo_id}")
                else:
                    print(f"Cleanup failed for {repo_id}: {delete_response.status_code} - {delete_response.text}")
            else:
                print(f"No files need to be cleaned for {repo_id}")
            
    except Exception as e:
        print(f"Error during cleanup process: {str(e)}")

if __name__ == "__main__":
    
    
    action = sys.argv[1]
    
    if action == "upload":
        token = os.environ.get("HF_TOKEN")
        repo_id = os.environ.get("DATASET_ID")
        file_path = sys.argv[2]
        file_name = sys.argv[3]
        upload_backup(file_path, file_name, token, repo_id)
    elif action == "download":
        token = os.environ.get("HF_TOKEN")
        repo_id = os.environ.get("DATASET_ID")
        download_latest_backup(token, repo_id)
    elif action == "clear":
        token = os.environ.get("HF_TOKEN")
        account = os.environ.get("ACCOUNT")
        password = os.environ.get("PASSWORD")
        repo_ids = os.environ.get("CLEAR_DATA_IDS")
        save_num = os.environ.get("SAVENUMS", "10")
        clear_tmp_bak(account, password, repo_ids, save_num)
EOL

# 首次启动时从HuggingFace下载最新备份
echo "Downloading latest backup from HuggingFace..."
python hf_sync.py download

# 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/uptime-kuma/data" ]; then
            # 创建备份
            cd /home/app/uptime-kuma
            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}" data/
            
            # 上传到HuggingFace
            echo "Uploading backup to HuggingFace..."
            python hf_sync.py upload "/tmp/${backup_file}" "${backup_file}"
            
            # 清理临时文件
            rm -f "/tmp/${backup_file}"
        else
            echo "Data directory does not exist yet, waiting for next sync..."
        fi
        
        # 同步间隔
        SYNC_INTERVAL=${SYNC_INTERVAL:-7200}
        current_timestamp=$(date +%s)
        next_timestamp=$((current_timestamp + SYNC_INTERVAL))
        next_time=$(date -r $next_timestamp "+%Y-%m-%d %H:%M:%S" 2>/dev/null || date -d "@$next_timestamp" "+%Y-%m-%d %H:%M:%S" 2>/dev/null || echo "$(date) + $SYNC_INTERVAL seconds")
        echo "Next sync at ${next_time} (in ${SYNC_INTERVAL} seconds)..."
        sleep $SYNC_INTERVAL
    done
}

# 同步函数
clear_lfs() {

    # Check if required environment variables exist
    if [ -z "$ACCOUNT" ] || [ -z "$PASSWORD" ] || [ -z "$CLEAR_DATA_IDS" ]; then
        echo "Skipping clear process - missing ACCOUNT, PASSWORD or CLEAR_DATA_IDS environment variables"
        return
    fi
    SAVENUMS=${SAVENUMS:-10}
    while true; do
        echo "Starting clear process at $(date)"
        # 直接调用清理脚本，从环境变量读取参数
        python hf_sync.py clear
        # 同步间隔 默认7天清理一次
        CLEAR_INTERVAL=${CLEAR_INTERVAL:-604800}
        current_timestamp=$(date +%s)
        next_timestamp=$((current_timestamp + CLEAR_INTERVAL))
        next_time=$(date -r $next_timestamp "+%Y-%m-%d %H:%M:%S" 2>/dev/null || date -d "@$next_timestamp" "+%Y-%m-%d %H:%M:%S" 2>/dev/null || echo "$(date) + $CLEAR_INTERVAL seconds")
        echo "Next clear at ${next_time} (in ${CLEAR_INTERVAL} seconds)..."
        sleep $CLEAR_INTERVAL
    done
}

# 启动同步进程
sync_data &
# 启动清理进程
clear_lfs &

# 启动主应用
exec node server/server.js