smaheshwar-pltr commented on code in PR #1452: URL: https://github.com/apache/iceberg-python/pull/1452#discussion_r1909330087
########## pyiceberg/table/locations.py: ########## @@ -0,0 +1,82 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +from typing import Optional + +import mmh3 + +from pyiceberg.partitioning import PartitionKey +from pyiceberg.table import LocationProvider, TableProperties +from pyiceberg.typedef import Properties +from pyiceberg.utils.properties import property_as_bool + + +class DefaultLocationProvider(LocationProvider): + def __init__(self, table_location: str, table_properties: Properties): + super().__init__(table_location, table_properties) + + def new_data_location(self, data_file_name: str, partition_key: Optional[PartitionKey] = None) -> str: + prefix = f"{self.table_location}/data" + return f"{prefix}/{partition_key.to_path()}/{data_file_name}" if partition_key else f"{prefix}/{data_file_name}" + + +HASH_BINARY_STRING_BITS = 20 +ENTROPY_DIR_LENGTH = 4 +ENTROPY_DIR_DEPTH = 3 + + +class ObjectStoreLocationProvider(LocationProvider): + _include_partition_paths: bool + + def __init__(self, table_location: str, table_properties: Properties): + super().__init__(table_location, table_properties) + self._include_partition_paths = property_as_bool( + table_properties, + TableProperties.WRITE_OBJECT_STORE_PARTITIONED_PATHS, + TableProperties.WRITE_OBJECT_STORE_PARTITIONED_PATHS_DEFAULT, + ) + + def new_data_location(self, data_file_name: str, partition_key: Optional[PartitionKey] = None) -> str: Review Comment: Also, I've **not** yet changed `WRITE_OBJECT_STORE_PARTITIONED_PATHS_DEFAULT` to `False` (Java/docs have true) even though that's more aligned with object storage - from the [docs](https://iceberg.apache.org/docs/latest/aws/#object-store-file-layout): > We have also added a new table property write.object-storage.partitioned-paths that if set to false(default=true), this will omit the partition values from the file path. Iceberg does not need these values in the file path and setting this value to false can further reduce the key size. I'm very open to be swayed / discuss this. After reading through https://github.com/apache/iceberg/pull/11112 it seems there was a strong case for still supporting partition values in paths though I haven't been able to flesh it out fully. Perhaps it's backwards compatibility, for folks that inspect storage to see how their files are actually laid out (e.g. before vs after partition evolution); it does group the files together nicely. I'd be happy to change the default if there's reason for it. The readability of file paths will arguably anyway decrease with these hashes so this might be a non-issue. -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
