rymurr commented on a change in pull request #2266:
URL: https://github.com/apache/iceberg/pull/2266#discussion_r584151108
##########
File path: python/iceberg/hive/hive_tables.py
##########
@@ -34,8 +41,45 @@ def __init__(self, conf):
def new_table_ops(self, conf, database, table):
return HiveTableOperations(conf, self.get_client(), database, table)
- def drop(self, database, table):
- raise RuntimeError("Not yet implemented")
+ def drop(self, database, table, purge=False):
+ ops = self.new_table_ops(self.conf, database, table)
+ metadata = ops.current()
+
+ with self.get_client() as open_client:
+ _logger.info("Deleting {database}.{table} from Hive
Metastore".format(database=database, table=table))
+ open_client.drop_table(database, table, deleteData=False)
+
+ manifest_lists_to_delete = []
+ manifests_to_delete = itertools.chain()
+
+ if purge:
+ if metadata is not None:
+ for s in metadata.snapshots:
+ manifests_to_delete = itertools.chain(manifests_to_delete,
s.manifests)
+ if s.manifest_location is not None:
+ manifest_lists_to_delete.append(s.manifest_location())
+
+ # Make a copy, as it is drained as we explore the manifest to list
files.
+ (manifests, manifests_to_delete) = itertools.tee(manifests_to_delete)
+
+ with Pool(self.conf.get(WORKER_THREAD_POOL_SIZE_PROP,
Review comment:
I think async is cooler but I don't know if adding async here is really
going to do a lot of good. Complicates the code and reduce the number of people
who can read it so maybe (for now) threading module is best. What do you guys
think?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
