|
#!/bin/bash |
|
|
|
|
|
if [ -z "$HF_TOKEN" ] || [ -z "$DATASET_ID" ]; then |
|
echo "Starting without backup functionality - missing HF_TOKEN or DATASET_ID" |
|
exec python main.py |
|
fi |
|
|
|
|
|
export HUGGING_FACE_HUB_TOKEN=$HF_TOKEN |
|
|
|
|
|
sync_data() { |
|
while true; do |
|
echo "Starting sync process at $(date)" |
|
|
|
|
|
cd /app |
|
timestamp=$(date +%Y%m%d_%H%M%S) |
|
backup_file="backup_${timestamp}.tar.gz" |
|
|
|
tar -czf "/tmp/${backup_file}" data/ |
|
|
|
|
|
python3 -c " |
|
try: |
|
from huggingface_hub import HfApi |
|
import os |
|
|
|
api = HfApi() |
|
api.upload_file( |
|
path_or_fileobj='/tmp/${backup_file}', |
|
path_in_repo='${backup_file}', |
|
repo_id='${DATASET_ID}', |
|
repo_type='dataset' |
|
) |
|
print('Backup completed successfully') |
|
except Exception as e: |
|
print(f'Backup failed: {str(e)}') |
|
" |
|
|
|
rm -f "/tmp/${backup_file}" |
|
|
|
|
|
SYNC_INTERVAL=${SYNC_INTERVAL:-7200} |
|
echo "Next sync in ${SYNC_INTERVAL} seconds..." |
|
sleep $SYNC_INTERVAL |
|
done |
|
} |
|
|
|
|
|
restore_latest() { |
|
echo "Attempting to restore latest backup..." |
|
python3 -c " |
|
try: |
|
from huggingface_hub import HfApi |
|
import os |
|
|
|
api = HfApi() |
|
files = api.list_repo_files('${DATASET_ID}', repo_type='dataset') |
|
backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')] |
|
|
|
if backup_files: |
|
latest = sorted(backup_files)[-1] |
|
api.hf_hub_download( |
|
repo_id='${DATASET_ID}', |
|
filename=latest, |
|
repo_type='dataset', |
|
local_dir='/tmp' |
|
) |
|
os.system(f'tar -xzf /tmp/{latest} -C /app') |
|
os.remove(f'/tmp/{latest}') |
|
print(f'Restored from {latest}') |
|
else: |
|
print('No backup found') |
|
except Exception as e: |
|
print(f'Restore failed: {str(e)}') |
|
" |
|
} |
|
|
|
|
|
( |
|
|
|
restore_latest |
|
|
|
|
|
sync_data & |
|
|
|
|
|
exec python main.py |
|
) 2>&1 | tee -a /app/data/backup.log |