ggershinsky commented on a change in pull request #928: URL: https://github.com/apache/parquet-mr/pull/928#discussion_r717312882
########## File path: parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/ColumnEncryptor.java ########## @@ -0,0 +1,339 @@ +/* + * 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. + */ +package org.apache.parquet.hadoop.util; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.parquet.HadoopReadOptions; +import org.apache.parquet.bytes.BytesInput; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.column.ParquetProperties; +import org.apache.parquet.column.page.DictionaryPage; +import org.apache.parquet.column.page.PageReadStore; +import org.apache.parquet.column.values.bloomfilter.BloomFilter; +import org.apache.parquet.crypto.AesCipher; +import org.apache.parquet.crypto.FileEncryptionProperties; +import org.apache.parquet.crypto.InternalColumnEncryptionSetup; +import org.apache.parquet.crypto.InternalFileEncryptor; +import org.apache.parquet.format.BlockCipher; +import org.apache.parquet.format.DataPageHeader; +import org.apache.parquet.format.DataPageHeaderV2; +import org.apache.parquet.format.DictionaryPageHeader; +import org.apache.parquet.format.PageHeader; +import org.apache.parquet.format.converter.ParquetMetadataConverter; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.ParquetFileWriter; +import org.apache.parquet.hadoop.api.WriteSupport; +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData; +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.parquet.hadoop.metadata.ParquetMetadata; +import org.apache.parquet.internal.column.columnindex.ColumnIndex; +import org.apache.parquet.internal.column.columnindex.OffsetIndex; +import org.apache.parquet.io.ParquetEncodingException; +import org.apache.parquet.schema.MessageType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +import static org.apache.parquet.column.ParquetProperties.DEFAULT_COLUMN_INDEX_TRUNCATE_LENGTH; +import static org.apache.parquet.column.ParquetProperties.DEFAULT_STATISTICS_TRUNCATE_LENGTH; +import static org.apache.parquet.crypto.ModuleCipherFactory.ModuleType; +import static org.apache.parquet.format.converter.ParquetMetadataConverter.NO_FILTER; +import static org.apache.parquet.hadoop.ParquetWriter.DEFAULT_BLOCK_SIZE; +import static org.apache.parquet.hadoop.ParquetWriter.MAX_PADDING_SIZE_DEFAULT; + +/** + * This class is for fast rewriting existing file with column encryption + * + * For columns to be encrypted, all the pages of those columns are read, but decompression/decoding, + * it is encrypted immediately and write back. + * + * For columns not to be encrypted, the whole column chunk will be appended directly to writer. + */ +public class ColumnEncryptor { + private static final Logger LOG = LoggerFactory.getLogger(ColumnEncryptor.class); + + private static class EncryptorRunTime { + private final InternalColumnEncryptionSetup colEncrSetup; + private final BlockCipher.Encryptor dataEncryptor; + private final BlockCipher.Encryptor metaDataEncryptor; + private final byte[] fileAAD ; + + private byte[] dataPageHeaderAAD; + private byte[] dataPageAAD; + private byte[] dictPageHeaderAAD; + private byte[] dictPageAAD; + + public EncryptorRunTime(InternalFileEncryptor fileEncryptor, ColumnChunkMetaData chunk, + int blockId, int columnId) throws IOException { + this.colEncrSetup = fileEncryptor.getColumnSetup(chunk.getPath(), true, toShortWithCheck(columnId)); + this.dataEncryptor = colEncrSetup.getDataEncryptor(); + this.metaDataEncryptor = colEncrSetup.getMetaDataEncryptor(); + + this.fileAAD = fileEncryptor.getFileAAD(); + this.dataPageHeaderAAD = AesCipher.createModuleAAD(fileAAD, ModuleType.DataPageHeader, + toShortWithCheck(blockId), toShortWithCheck(columnId), (short) 0); + this.dataPageAAD = AesCipher.createModuleAAD(fileAAD, ModuleType.DataPage, + toShortWithCheck(blockId), toShortWithCheck(columnId), (short) 0); + this.dictPageHeaderAAD = AesCipher.createModuleAAD(fileAAD, ModuleType.DictionaryPageHeader, + toShortWithCheck(blockId), toShortWithCheck(columnId), (short) 0); + this.dictPageAAD = AesCipher.createModuleAAD(fileAAD, ModuleType.DictionaryPage, + toShortWithCheck(blockId), toShortWithCheck(columnId), (short) 0); + } + + public InternalColumnEncryptionSetup getColEncrSetup() { + return this.colEncrSetup; + } + + public BlockCipher.Encryptor getDataEncryptor() { + return this.dataEncryptor; + } + + public BlockCipher.Encryptor getMetaDataEncryptor() { + return this.metaDataEncryptor; + } + + public byte[] getFileAAD() { + return this.fileAAD; + } + + public byte[] getDataPageHeaderAAD() { + return this.dataPageHeaderAAD; + } + + public byte[] getDataPageAAD() { + return this.dataPageAAD; + } + + public byte[] getDictPageHeaderAAD() { + return this.dictPageHeaderAAD; + } + + public byte[] getDictPageAAD() { + return this.dictPageAAD; + } + } + + private final int PAGE_BUFFER_SIZE = ParquetProperties.DEFAULT_PAGE_SIZE * 2; + private byte[] pageBuffer; + private Configuration conf; + + public ColumnEncryptor(Configuration conf) { + this.pageBuffer = new byte[PAGE_BUFFER_SIZE]; + this.conf = conf; + } + + /** + * Given the input file, encrypt the columns specified by paths, and output the file. + * The encryption settings can be specified in the parameter of fileEncryptionProperties + * @param inputFile Input file + * @param outputFile Output file + * @param paths columns to be encrypted + * @param fileEncryptionProperties FileEncryptionProperties of the file + * @throws IOException + */ + public void encryptColumns(String inputFile, String outputFile, List<String> paths, FileEncryptionProperties fileEncryptionProperties) throws IOException { Review comment: an excellent point. I agree it would be good to support this scenario. It is somewhat harder to explain and define (check if each column is already encrypted; if yes, compare its encryption properties). It might be easier to start with a simpler scenario, where the input files are not encrypted at all. But I'm ok either way. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
