Update sync_data.sh
Browse files- sync_data.sh +18 -5
sync_data.sh
CHANGED
|
@@ -21,12 +21,23 @@ sync_data() {
|
|
| 21 |
|
| 22 |
tar -czf "/tmp/${backup_file}" data/
|
| 23 |
|
| 24 |
-
# 使用Python脚本上传到HuggingFace
|
| 25 |
python3 -c "
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
api = HfApi()
|
| 31 |
api.upload_file(
|
| 32 |
path_or_fileobj='/tmp/${backup_file}',
|
|
@@ -34,7 +45,9 @@ try:
|
|
| 34 |
repo_id='${DATASET_ID}',
|
| 35 |
repo_type='dataset'
|
| 36 |
)
|
| 37 |
-
print('Backup
|
|
|
|
|
|
|
| 38 |
except Exception as e:
|
| 39 |
print(f'Backup failed: {str(e)}')
|
| 40 |
"
|
|
|
|
| 21 |
|
| 22 |
tar -czf "/tmp/${backup_file}" data/
|
| 23 |
|
|
|
|
| 24 |
python3 -c "
|
| 25 |
+
from huggingface_hub import HfApi
|
| 26 |
+
import os
|
| 27 |
+
def manage_backups(api, repo_id, max_files=50):
|
| 28 |
+
files = api.list_repo_files(repo_id=repo_id, repo_type='dataset')
|
| 29 |
+
backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
|
| 30 |
+
backup_files.sort()
|
| 31 |
|
| 32 |
+
if len(backup_files) >= max_files:
|
| 33 |
+
files_to_delete = backup_files[:(len(backup_files) - max_files + 1)]
|
| 34 |
+
for file_to_delete in files_to_delete:
|
| 35 |
+
try:
|
| 36 |
+
api.delete_file(path_in_repo=file_to_delete, repo_id=repo_id, repo_type='dataset')
|
| 37 |
+
print(f'Deleted old backup: {file_to_delete}')
|
| 38 |
+
except Exception as e:
|
| 39 |
+
print(f'Error deleting {file_to_delete}: {str(e)}')
|
| 40 |
+
try:
|
| 41 |
api = HfApi()
|
| 42 |
api.upload_file(
|
| 43 |
path_or_fileobj='/tmp/${backup_file}',
|
|
|
|
| 45 |
repo_id='${DATASET_ID}',
|
| 46 |
repo_type='dataset'
|
| 47 |
)
|
| 48 |
+
print('Backup uploaded successfully')
|
| 49 |
+
|
| 50 |
+
manage_backups(api, '${DATASET_ID}')
|
| 51 |
except Exception as e:
|
| 52 |
print(f'Backup failed: {str(e)}')
|
| 53 |
"
|