sync_data.sh

#!/bin/bash

# 检查环境变量
if [[ -z "$HF_TOKEN" ]] || [[ -z "$DATASET_ID" ]]; then
    echo "未启用备份功能 - 缺少HF_TOKEN或DATASET_ID环境变量"
    exit 0
fi

# 创建临时目录
TEMP_DIR="/tmp/sillytavern_backup"
mkdir -p $TEMP_DIR

# 安装python和huggingface_hub
if ! command -v python3 &> /dev/null; then
    echo "正在安装Python..."
    apk add --no-cache python3 py3-pip
fi

if ! python3 -c "import huggingface_hub" &> /dev/null; then
    echo "正在安装huggingface_hub..."
    pip3 install --no-cache-dir huggingface_hub
fi

# 上传备份
upload_backup() {
import sys
import os
def manage_backups(api, repo_id, max_files=10):
    files = api.list_repo_files(repo_id=repo_id, repo_type='dataset')
    backup_files = [f for f in files if f.startswith('sillytavern_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'已删除旧备份: {file_to_delete}')
            except Exception as e:
                print(f'删除 {file_to_delete} 时出错: {str(e)}')
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'成功上传 $file_name')
    
    manage_backups(api, '$repo_id')
except Exception as e:
    print(f'上传文件时出错: {str(e)}')
"
}

download_latest_backup() {
    token="$HF_TOKEN"
    repo_id="$DATASET_ID"
    data_dir="/home/node/app/data"
    
    # 确保数据目录存在
    mkdir -p $data_dir

    python3 -c "
from huggingface_hub import HfApi
import os
import tarfile
import tempfile
api = HfApi(token='$token')
try:
    files = api.list_repo_files(repo_id='$repo_id', repo_type='dataset')
    backup_files = [f for f in files if f.startswith('sillytavern_backup_') and f.endswith('.tar.gz')]
    
    if not backup_files:
        print('未找到备份文件')
        sys.exit()
        
    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('$data_dir')
            print(f'成功从 {latest_backup} 恢复备份')
        
except Exception as e:
    print(f'下载备份时出错: {str(e)}')
"
}

# 首次启动时下载最新备份
echo "正在从HuggingFace下载最新备份..."
download_latest_backup

# 同步函数
sync_data() {
    while true; do
        echo "开始同步进程，时间: $(date)"
        
        data_dir="/home/node/app/data"
        if [ -d "$data_dir" ]; then
            timestamp=$(date +%Y%m%d_%H%M%S)
            backup_file="sillytavern_backup_${timestamp}.tar.gz"
            
            # 压缩数据目录
            tar -czf "${TEMP_DIR}/${backup_file}" -C "$data_dir" .
            
            echo "正在上传备份到HuggingFace..."
            upload_backup "${TEMP_DIR}/${backup_file}" "${backup_file}"
            
            rm -f "${TEMP_DIR}/${backup_file}"
        else
            echo "数据目录尚不存在，等待下次同步..."
        fi
        
        SYNC_INTERVAL=${SYNC_INTERVAL:-3600}
        echo "下次同步将在 ${SYNC_INTERVAL} 秒后进行..."
        sleep $SYNC_INTERVAL
    done
}

# 启动同步进程
sync_data