[GitHub] [spark] attilapiros commented on a change in pull request #32146: [SPARK-34990][SQL][TESTS] Add ParquetEncryptionSuite

[GitBox <gi...@apache.org>]

attilapiros commented on a change in pull request #32146:
URL: https://github.com/apache/spark/pull/32146#discussion_r615644250



##########
File path: sql/hive/src/test/scala/org/apache/spark/sql/hive/ParquetEncryptionSuite.scala
##########
@@ -0,0 +1,148 @@
+/*
+ * 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.spark.sql.hive
+
+import java.io.File
+import java.nio.charset.StandardCharsets
+import java.util.{Base64, HashMap, Map}
+
+import scala.sys.process._
+
+import org.apache.hadoop.conf.Configuration
+import org.apache.parquet.crypto.{KeyAccessDeniedException, ParquetCryptoRuntimeException}
+import org.apache.parquet.crypto.keytools.{KeyToolkit, KmsClient}
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.test.SharedSparkSession
+
+/**
+ * A test suite that tests parquet modular encryption usage.
+ */
+class ParquetEncryptionSuite extends QueryTest with SharedSparkSession {
+
+  private val encoder = Base64.getEncoder
+  private val footerKey =
+    encoder.encodeToString("0123456789012345".getBytes(StandardCharsets.UTF_8))
+  private val key1 = encoder.encodeToString("1234567890123450".getBytes(StandardCharsets.UTF_8))
+  private val key2 = encoder.encodeToString("1234567890123451".getBytes(StandardCharsets.UTF_8))
+
+  import testImplicits._
+
+  test("SPARK-34990: Write and read an encrypted parquet") {
+    withTempDir { dir =>
+      withSQLConf(
+        "parquet.crypto.factory.class" ->
+          "org.apache.parquet.crypto.keytools.PropertiesDrivenCryptoFactory",
+        "parquet.encryption.kms.client.class" -> "org.apache.spark.sql.hive.InMemoryKMS",
+        "parquet.encryption.key.list" ->
+          s"footerKey: ${footerKey}, key1: ${key1}, key2: ${key2}") {
+
+        val inputDF = Seq((1, 22, 333)).toDF("a", "b", "c")
+        val parquetDir = new File(dir, "parquet").getCanonicalPath
+        inputDF.write
+          .option("parquet.encryption.column.keys", "key1: a, b; key2: c")
+          .option("parquet.encryption.footer.key", "footerKey")
+          .parquet(parquetDir)
+
+        verifyParquetEncrypted(parquetDir)
+
+        val parquetDF = spark.read.parquet(parquetDir)
+        assert(parquetDF.inputFiles.nonEmpty)
+        val readDataset = parquetDF.select("a", "b", "c")
+        checkAnswer(readDataset, inputDF)
+      }
+    }
+  }
+
+  private def verifyParquetEncrypted(parquetDir: String) = {
+    val parquetPartitionFile = Seq("ls", "-tr", parquetDir).!!.split("\\s+")(0)
+    val fullFilename = parquetDir + "/" + parquetPartitionFile
+    val magic = Seq("tail", "-c", "4", fullFilename).!!
+    assert(magic.stripLineEnd.trim() == "PARE")
+  }
+}

Review comment:
       Do we really need to call `ls` and `tail` to check a file last 4 chars?
   
   You can list the files easily:
   
   ```scala
   val parquetPartitionFiles = new File(parquetDir).listFiles()
   assert(parquetPartitionFiles.size === 1)
   ```
   
   Then you can create a `RandomAccessFile` for the file and read the last 4 bytes after seeking to the end.
   This way you can get rid from all the `!!` and remove the import of the `scala.sys.process`.
   
   This saves creating new unnecessary processes during testing.




-- 
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:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org