Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUGFIX] Resolve partition deleting bug in insert_overwrite mode #139

Closed
wants to merge 1 commit into from
Closed

[BUGFIX] Resolve partition deleting bug in insert_overwrite mode #139

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 23 additions & 15 deletions dbt/adapters/athena/impl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,21 +63,29 @@ def clean_up_partitions(
with boto3_client_lock:
glue_client = boto3.client('glue', region_name=client.region_name)
s3_resource = boto3.resource('s3', region_name=client.region_name)
partitions = glue_client.get_partitions(
# CatalogId='123456789012', # Need to make this configurable if it is different from default AWS Account ID
DatabaseName=database_name,
TableName=table_name,
Expression=where_condition
)
p = re.compile('s3://([^/]*)/(.*)')
for partition in partitions["Partitions"]:
logger.debug("Deleting objects for partition '{}' at '{}'", partition["Values"], partition["StorageDescriptor"]["Location"])
m = p.match(partition["StorageDescriptor"]["Location"])
if m is not None:
bucket_name = m.group(1)
prefix = m.group(2)
s3_bucket = s3_resource.Bucket(bucket_name)
s3_bucket.objects.filter(Prefix=prefix).delete()
continue_deleting: bool = True
next_token: str = ''
while continue_deleting:
partitions = glue_client.get_partitions(
# CatalogId='123456789012', # Need to make this configurable if it is different from default AWS Account ID
DatabaseName=database_name,
TableName=table_name,
Expression=where_condition,
NextToken=next_token
)
p = re.compile('s3://([^/]*)/(.*)')
for partition in partitions["Partitions"]:
logger.debug("Deleting objects for partition '{}' at '{}'", partition["Values"], partition["StorageDescriptor"]["Location"])
m = p.match(partition["StorageDescriptor"]["Location"])
if m is not None:
bucket_name = m.group(1)
prefix = m.group(2)
s3_bucket = s3_resource.Bucket(bucket_name)
s3_bucket.objects.filter(Prefix=prefix).delete()
if 'NextToken' in partitions:
next_token = partitions['NextToken']
else:
continue_deleting = False

@available
def clean_up_table(
Expand Down