reader / hf_sync.py
mao123qw's picture
Create hf_sync.py
ba0eecc verified
raw
history blame
2.62 kB
from huggingface_hub import HfApi
import sys
import os
import tarfile
import tempfile
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/storage/')
print(f"Successfully restored backup from {latest_backup}")
except Exception as e:
print(f"Error downloading backup: {str(e)}")
if __name__ == "__main__":
action = sys.argv[1]
token = sys.argv[2]
repo_id = sys.argv[3]
if action == "upload":
file_path = sys.argv[4]
file_name = sys.argv[5]
upload_backup(file_path, file_name, token, repo_id)
elif action == "download":
download_latest_backup(token, repo_id)
EOL