[GLUTEN-8455][VL] Port encrypted file checks to shim layer #8501
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,175 @@ | ||
| /* | ||
| * 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.gluten.utils | ||
|
|
||
| import org.apache.gluten.sql.shims.SparkShimLoader | ||
|
|
||
| import org.apache.spark.sql.{GlutenQueryTest, SparkSession} | ||
|
|
||
| import org.apache.hadoop.conf.Configuration | ||
| import org.apache.hadoop.fs.{FileSystem, LocatedFileStatus, Path} | ||
| import org.apache.parquet.crypto.{ColumnEncryptionProperties, FileEncryptionProperties} | ||
| import org.apache.parquet.example.data.simple.SimpleGroup | ||
| import org.apache.parquet.hadoop.example.ExampleParquetWriter | ||
| import org.apache.parquet.hadoop.metadata.ColumnPath | ||
| import org.apache.parquet.schema.{MessageType, PrimitiveType, Type, Types} | ||
| import org.junit.Assert._ | ||
|
|
||
| import java.nio.charset.StandardCharsets | ||
| import java.util.Base64 | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
|
|
||
| /** | ||
| * This suite attempt to test parquet encryption for fallback of scan operator. Will check the | ||
| * following: | ||
| * 1. Plain Parquet File: | ||
| * - Writes a Parquet file with no encryption. | ||
| * - Asserts that parquet is not encrypted | ||
| * | ||
| * 2. Encrypted Parquet File (with encrypted footer): | ||
| * - Writes a Parquet file with column-level encryption and an encrypted footer. | ||
| * - Asserts that the file is encrypted. | ||
| * | ||
| * 3. Encrypted Parquet File (with plaintext footer): | ||
| * - Writes a Parquet file with column-level encryption but a plaintext (unencrypted) footer. | ||
| * - Ensures the file is still detected as encrypted despite the plaintext footer. | ||
| */ | ||
|
|
||
| class ParquetEncryptionDetectionSuite extends GlutenQueryTest { | ||
|
|
||
| private val masterKey = | ||
| Base64.getEncoder.encodeToString("0123456789012345".getBytes(StandardCharsets.UTF_8)) | ||
| private val columnKey = | ||
| Base64.getEncoder.encodeToString("1234567890123456".getBytes(StandardCharsets.UTF_8)) | ||
|
|
||
| private val schema: MessageType = Types | ||
| .buildMessage() | ||
| .addField( | ||
| Types.primitive(PrimitiveType.PrimitiveTypeName.INT32, Type.Repetition.REQUIRED).named("id")) | ||
| .addField( | ||
| Types | ||
| .primitive(PrimitiveType.PrimitiveTypeName.BINARY, Type.Repetition.REQUIRED) | ||
| .named("name")) | ||
| .named("TestSchema") | ||
|
|
||
| private var _spark: SparkSession = _ | ||
|
|
||
| override protected def spark: SparkSession = _spark | ||
|
|
||
| private def writeParquet( | ||
| path: String, | ||
| encryptionProperties: Option[FileEncryptionProperties], | ||
| data: Seq[Map[String, Any]] | ||
| ): Unit = { | ||
| val configuration = new Configuration() | ||
| val writerBuilder = ExampleParquetWriter | ||
| .builder(new Path(path)) | ||
| .withConf(configuration) | ||
| .withType(schema) | ||
| .withWriteMode(org.apache.parquet.hadoop.ParquetFileWriter.Mode.OVERWRITE) | ||
|
|
||
| encryptionProperties.foreach(writerBuilder.withEncryption) | ||
|
|
||
| val writer = writerBuilder.build() | ||
| try { | ||
| data.foreach { | ||
| row => | ||
| val group = new SimpleGroup(schema) | ||
| row.foreach { | ||
| case (key, value) => | ||
| value match { | ||
| case i: Int => group.add(key, i) | ||
| case s: String => group.add(key, s) | ||
| } | ||
| } | ||
| writer.write(group) | ||
| } | ||
| } finally { | ||
| writer.close() | ||
| } | ||
| } | ||
|
|
||
| private def getLocatedFileStatus(path: String): LocatedFileStatus = { | ||
| val conf = new Configuration() | ||
| val fs = FileSystem.get(conf) | ||
| fs.listFiles(new Path(path), false).next() | ||
| } | ||
|
|
||
| testWithSpecifiedSparkVersion( | ||
| "Detect encrypted Parquet with encrypted footer", | ||
| Array("3.2", "3.3", "3.4")) { | ||
| withTempDir { | ||
| tempDir => | ||
| val filePath = s"${tempDir.getAbsolutePath}/encrypted_footer.parquet" | ||
| val encryptionProps = FileEncryptionProperties | ||
| .builder(Base64.getDecoder.decode(masterKey)) | ||
| .withEncryptedColumns( | ||
| Map( | ||
| ColumnPath.get("name") -> ColumnEncryptionProperties | ||
| .builder(ColumnPath.get("name")) | ||
| .withKey(Base64.getDecoder.decode(columnKey)) | ||
| .build()).asJava) | ||
| .build() | ||
|
|
||
| writeParquet(filePath, Some(encryptionProps), Seq(Map("id" -> 1, "name" -> "Alice"))) | ||
| val fileStatus = getLocatedFileStatus(filePath) | ||
|
|
||
| assertTrue( | ||
| SparkShimLoader.getSparkShims.isParquetFileEncrypted(fileStatus, new Configuration())) | ||
| } | ||
| } | ||
|
|
||
| testWithSpecifiedSparkVersion( | ||
| "Detect encrypted Parquet without encrypted footer (plaintext footer)", | ||
| Array("3.2", "3.3", "3.4")) { | ||
| withTempDir { | ||
| tempDir => | ||
| val filePath = s"${tempDir.getAbsolutePath}/plaintext_footer.parquet" | ||
| val encryptionProps = FileEncryptionProperties | ||
| .builder(Base64.getDecoder.decode(masterKey)) | ||
| .withEncryptedColumns( | ||
| Map( | ||
| ColumnPath.get("name") -> ColumnEncryptionProperties | ||
| .builder(ColumnPath.get("name")) | ||
| .withKey(Base64.getDecoder.decode(columnKey)) | ||
| .build()).asJava) | ||
| .withPlaintextFooter() | ||
| .build() | ||
|
|
||
| writeParquet(filePath, Some(encryptionProps), Seq(Map("id" -> 1, "name" -> "Bob"))) | ||
| val fileStatus = getLocatedFileStatus(filePath) | ||
| assertTrue( | ||
| SparkShimLoader.getSparkShims.isParquetFileEncrypted(fileStatus, new Configuration())) | ||
| } | ||
| } | ||
|
|
||
| testWithSpecifiedSparkVersion( | ||
| "Detect plain (unencrypted) Parquet file", | ||
| Array("3.2", "3.3", "3.4")) { | ||
| withTempDir { | ||
| tempDir => | ||
| val filePath = s"${tempDir.getAbsolutePath}/plain.parquet" | ||
|
|
||
| writeParquet(filePath, None, Seq(Map("id" -> 1, "name" -> "Charlie"))) | ||
| val fileStatus = getLocatedFileStatus(filePath) | ||
|
|
||
| assertFalse( | ||
| SparkShimLoader.getSparkShims.isParquetFileEncrypted(fileStatus, new Configuration())) | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| /* | ||
| * 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.gluten.utils | ||
|
|
||
| object ExceptionUtils { | ||
|
|
||
| /** | ||
| * Utility to check the exception for the specified type. | ||
| * | ||
| * @param throwable | ||
| * Exception to check | ||
| * @param causeType | ||
| * Class of the cause to look for | ||
| * @tparam T | ||
| * Type of the cause | ||
| * @return | ||
| * True if the cause is found; false otherwise | ||
| */ | ||
| def hasCause[T <: Throwable](throwable: Throwable, causeType: Class[T]): Boolean = { | ||
| var current = throwable | ||
| while (current != null) { | ||
| if (causeType.isInstance(current)) { | ||
| return true | ||
| } | ||
| current = current.getCause | ||
| } | ||
| false | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can this function be implemented in it's parent class: shims/common/src/main/scala/org/apache/gluten/sql/shims/SparkShims.scala
?
If it has a different implement, just to override it.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The logic will be different for 3.5 shim, will check if consolidation can be done when that is added
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is a common issue in our shim code. Perhaps we should develop a better way than the current one to manage these code duplications in shim layer in future.