mirror of
https://github.com/apache/arrow.git
synced 2026-10-29 00:56:31 +08:00
0793432ad0
### Rationale for this change The purpose of this pull request is to support modular encryption in the new Dataset API. See [https://docs.google.com/document/d/13EysCNC6-Nu9wnJ8YpdzmD-aMLn4i2KXUJTNqIihy7A/edit#](url) for supporting document. ### What changes are included in this PR? I made improvements to the C++ and Python code to enable the Dataset API to have per-file settings for each file saved. Previously, the Dataset API applied the same encryption properties to all saved files, but now I've updated the code to allow for greater flexibility. In the Python code, I've added support for the changes by updating the ParquetFormat class to accept DatasetEncryptionConfiguration and DatasetDecryptionConfiguration structures. With these changes, you can pass the format object to the write_dataset function, giving you the ability to set unique encryption properties for each file in your Dataset. ### Are these changes tested? Yes, unit tests are included. I have also included a python sample project. ### Are there any user-facing changes? Yes, as stated above the ParquetFormat class has optional parameters for DatasetEncryptionConfiguration and DatasetDecryptionConfiguration through setters and getters. The Dataset now has the option using this to set different file encryption properties per file * Closes: #29238 Lead-authored-by: Don <tolleybot@gmail.com> Co-authored-by: Donald Tolley <tolleybot@gmail.com> Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com> Co-authored-by: anjakefala <anja@voltrondata.com> Co-authored-by: Sutou Kouhei <kou@cozmixng.org> Co-authored-by: Weston Pace <weston.pace@gmail.com> Co-authored-by: Gang Wu <ustcwg@gmail.com> Co-authored-by: scoder <stefan_ml@behnel.de> Co-authored-by: Will Jones <willjones127@gmail.com> Signed-off-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>
94 lines
3.3 KiB
Python
94 lines
3.3 KiB
Python
# 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.
|
|
|
|
import shutil
|
|
import os
|
|
from datetime import timedelta
|
|
|
|
import pyarrow as pa
|
|
import pyarrow.dataset as ds
|
|
import pyarrow.parquet.encryption as pe
|
|
from pyarrow.tests.parquet.encryption import InMemoryKmsClient
|
|
|
|
""" A sample to demonstrate parquet dataset encryption and decryption"""
|
|
|
|
# create a list of dictionaries that will represent our dataset
|
|
table = pa.table({'year': [2020, 2022, 2021, 2022, 2019, 2021],
|
|
'n_legs': [2, 2, 4, 4, 5, 100],
|
|
'animal': ["Flamingo", "Parrot", "Dog", "Horse",
|
|
"Brittle stars", "Centipede"]})
|
|
|
|
# create a PyArrow dataset from the table
|
|
dataset = ds.dataset(table)
|
|
|
|
FOOTER_KEY = b"0123456789112345"
|
|
FOOTER_KEY_NAME = "footer_key"
|
|
COL_KEY = b"1234567890123450"
|
|
COL_KEY_NAME = "col_key"
|
|
|
|
encryption_config = pe.EncryptionConfiguration(
|
|
footer_key=FOOTER_KEY_NAME,
|
|
plaintext_footer=False,
|
|
# Use COL_KEY_NAME to encrypt `n_legs` and `animal` columns.
|
|
column_keys={
|
|
COL_KEY_NAME: ["n_legs", "animal"],
|
|
},
|
|
encryption_algorithm="AES_GCM_V1",
|
|
# requires timedelta or an assertion is raised
|
|
cache_lifetime=timedelta(minutes=5.0),
|
|
data_key_length_bits=256)
|
|
|
|
kms_connection_config = pe.KmsConnectionConfig(
|
|
custom_kms_conf={
|
|
FOOTER_KEY_NAME: FOOTER_KEY.decode("UTF-8"),
|
|
COL_KEY_NAME: COL_KEY.decode("UTF-8"),
|
|
}
|
|
)
|
|
|
|
decryption_config = pe.DecryptionConfiguration(cache_lifetime=300)
|
|
|
|
|
|
def kms_factory(kms_connection_configuration):
|
|
return InMemoryKmsClient(kms_connection_configuration)
|
|
|
|
|
|
crypto_factory = pe.CryptoFactory(kms_factory)
|
|
parquet_encryption_cfg = ds.ParquetEncryptionConfig(
|
|
crypto_factory, kms_connection_config, encryption_config)
|
|
parquet_decryption_cfg = ds.ParquetDecryptionConfig(crypto_factory,
|
|
kms_connection_config,
|
|
decryption_config)
|
|
|
|
# set encryption config for parquet fragment scan options
|
|
pq_scan_opts = ds.ParquetFragmentScanOptions()
|
|
pq_scan_opts.parquet_decryption_config = parquet_decryption_cfg
|
|
pformat = pa.dataset.ParquetFileFormat(default_fragment_scan_options=pq_scan_opts)
|
|
|
|
if os.path.exists('sample_dataset'):
|
|
shutil.rmtree('sample_dataset')
|
|
|
|
write_options = pformat.make_write_options(
|
|
encryption_config=parquet_encryption_cfg)
|
|
|
|
ds.write_dataset(data=dataset, base_dir="sample_dataset",
|
|
partitioning=['year'], format=pformat, file_options=write_options)
|
|
# read the dataset back
|
|
dataset = ds.dataset('sample_dataset', format=pformat)
|
|
|
|
# print the dataset
|
|
print(dataset.to_table())
|