utkarsharma2 commented on code in PR #30501:
URL: https://github.com/apache/airflow/pull/30501#discussion_r1178578389
##########
airflow/providers/amazon/aws/transfers/dynamodb_to_s3.py:
##########
@@ -118,11 +130,54 @@ def __init__(
self.dynamodb_scan_kwargs = dynamodb_scan_kwargs
self.s3_bucket_name = s3_bucket_name
self.s3_key_prefix = s3_key_prefix
+ self.export_time = export_time
+ self.export_format = export_format
- def execute(self, context: Context) -> None:
- hook = DynamoDBHook(aws_conn_id=self.source_aws_conn_id)
- table = hook.get_conn().Table(self.dynamodb_table_name)
+ if self.export_time and self.export_time > datetime.now():
+ raise ValueError("The export_time parameter cannot be a future
time.")
+ @cached_property
+ def hook(self):
+ """Create DynamoDBHook"""
+ return DynamoDBHook(aws_conn_id=self.source_aws_conn_id)
+
+ def execute(self, context: Context) -> None:
+ if self.export_time:
+ self._export_table_to_point_in_time()
+ else:
+ self._export_entire_data()
+
+ def _export_table_to_point_in_time(self):
+ """
+ Export data from start of epoc till `export_time`. Table export will
be a snapshot of the table's
+ state at this point in time.
+ """
+ client = self.hook.conn.meta.client
+ response = client.export_table_to_point_in_time(
+ TableArn=self.dynamodb_table_name,
+ ExportTime=self.export_time,
+ S3Bucket=self.s3_bucket_name,
+ S3Prefix=self.s3_key_prefix,
+ ExportFormat=self.export_format,
+ )
+ credentials = self.hook.get_credentials()
+ waiter = self.hook.get_waiter(
+ CUSTOM_WAITER_NAME,
+ client=boto3.client(
+ "dynamodb",
+ region_name=client.meta.region_name,
+ aws_access_key_id=credentials.access_key,
+ aws_secret_access_key=credentials.secret_key,
+ ),
+ )
+ export_arn = response.get("ExportDescription", {}).get("ExportArn")
+ waiter.wait(
+ ExportArn=export_arn,
+ )
Review Comment:
Done.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
