Skip to content

Commit

Permalink
Change function to check for bucket existence
Browse files Browse the repository at this point in the history
  • Loading branch information
krysal committed Jun 14, 2024
1 parent 6e52ba2 commit 9fae52d
Showing 1 changed file with 9 additions and 2 deletions.
11 changes: 9 additions & 2 deletions ingestion_server/ingestion_server/cleanup.py
Original file line number Diff line number Diff line change
Expand Up @@ -303,6 +303,10 @@ def save_cleaned_data(result: dict) -> dict[str, int]:


def _get_s3_resource():
"""
Locally, it connects to a MinIO instance through its endpoint and test credentials.
On live environments, the connection is allowed via IAM roles.
"""
if config("ENVIRONMENT", default="local") == "local":
return boto3.resource(
"s3",
Expand All @@ -317,15 +321,18 @@ def _get_s3_resource():


def _upload_to_s3(fields):
"""
Upload cleaned data to S3. It assumes that the bucket already exists.
"""
bucket_name = config("OPENVERSE_BUCKET", default="openverse-catalog")
s3_path = "shared/data-refresh-cleaned-data"
try:
s3 = _get_s3_resource()
s3.meta.client.head_bucket(Bucket=bucket_name)
bucket = s3.Bucket(bucket_name)
bucket.load()
log.info(f"Connected to S3 and '{bucket_name}' bucket loaded.")
except Exception as e:
log.error(f"Upload failed. Error connecting to S3 or loading bucket: {e}")
log.error(f"Files upload failed. Error connecting to S3.\n{e}")
return

for field in fields:
Expand Down

0 comments on commit 9fae52d

Please sign in to comment.