szehon-ho commented on a change in pull request #2266:
URL: https://github.com/apache/iceberg/pull/2266#discussion_r591394866
##########
File path: python/iceberg/hive/hive_tables.py
##########
@@ -34,12 +42,59 @@ 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) -> None:
+ ops = self.new_table_ops(self.conf, database, table)
+ metadata = ops.current()
- def get_client(self):
+ 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)
+
+ if purge:
+ if metadata is not None:
Review comment:
Ohh yea this is much simpler.
(I still have to do a double loop , first loop to get manifest path which is
argument needed for the snapshot.get_filtered_manifest iterator)
##########
File path: python/iceberg/hive/hive_tables.py
##########
@@ -34,12 +42,59 @@ 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) -> None:
+ ops = self.new_table_ops(self.conf, database, table)
+ metadata = ops.current()
- def get_client(self):
+ 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)
+
+ if purge:
+ if metadata is not None:
+ manifest_lists_to_delete = []
+ manifests_to_delete = itertools.chain()
+
+ for s in metadata.snapshots:
+ manifests_to_delete = itertools.chain(manifests_to_delete,
(m for m in 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,
+ cpu_count())) as delete_pool:
+ delete_pool.map(self._delete_file(ops),
self._unique(self._get_data_files(manifests)))
+ delete_pool.map(self._delete_file(ops),
self._unique(m.manifest_path for m in manifests_to_delete))
+ delete_pool.map(self._delete_file(ops),
self._unique(manifest_lists_to_delete))
+ delete_pool.map(self._delete_file(ops),
[ops.current_metadata_location])
+
+ def get_client(self) -> HMSClient:
from urllib.parse import urlparse
metastore_uri = urlparse(self.conf[HiveTables.THRIFT_URIS])
client = hmsclient.HMSClient(host=metastore_uri.hostname,
port=metastore_uri.port)
return client
+
+ def _get_data_files(self, manifests) -> Iterator[str]:
+ return
itertools.chain.from_iterable(self._get_data_files_by_manifest(m) for m in
manifests)
+
+ def _get_data_files_by_manifest(self, manifest) -> Iterator[str]:
+ file = FileSystemInputFile.from_location(manifest.manifest_path,
self.conf)
+ reader = ManifestReader.read(file)
+ return (i.path() for i in reader.iterator())
+
+ @staticmethod
+ def _delete_file(ops):
+ return lambda path: (
+ _logger.info("Deleting file: {path}".format(path=path)),
+ ops.delete_file(path))
+
+ @staticmethod
+ def _unique(iterable: Iterator) -> Iterator:
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
