Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/8880#discussion_r42059715
--- Diff:
core/src/main/scala/org/apache/spark/crypto/CryptoOutputStream.scala ---
@@ -0,0 +1,225 @@
+/*
+ * 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.crypto
+
+import java.io.{IOException, FilterOutputStream, OutputStream}
+import java.nio.ByteBuffer
+import java.security.GeneralSecurityException
+
+import com.google.common.base.Preconditions
+
+import org.apache.spark.Logging
+
+/**
+ * CryptoOutputStream encrypts data. It is not thread-safe. AES CTR mode is
+ * required in order to ensure that the plain text and cipher text have a
1:1
+ * mapping. The encryption is buffer based. The key points of the
encryption are
+ * (1) calculating counter and (2) padding through stream position.
+ *
+ * counter = base + pos/(algorithm blocksize);
+ * padding = pos%(algorithm blocksize);
+ *
+ * The underlying stream offset is maintained as state.
+ */
+private[spark] class CryptoOutputStream(
+ out: OutputStream,
+ private[spark] val codec: CryptoCodec,
+ bufferSizeVal: Int,
+ keyVal: Array[Byte],
+ ivVal: Array[Byte],
+ streamOffsetVal: Long,
+ isDirectBuf: Boolean) extends FilterOutputStream(out: OutputStream)
with Logging {
+ var encryptor: Encryptor = null
+ var streamOffset: Long = 0
+ /**
+ * Padding = pos%(algorithm blocksize); Padding is put into [[inBuffer]]
+ * before any other data goes in. The purpose of padding is to put input
data
+ * at proper position.
+ */
+ var padding: Byte = 0
+ var closed: Boolean = false
+ var key: Array[Byte] = null
+ var initIV: Array[Byte] = null
+ var iv: Array[Byte] = null
+ val oneByteBuf: Array[Byte] = new Array[Byte](1)
+
+ CryptoStreamUtils.checkCodec(codec)
+ var bufferSize = CryptoStreamUtils.checkBufferSize(codec, bufferSizeVal)
+
+ lazy val tmpBuf: Array[Byte] = new Array[Byte](bufferSize)
+
+ key = keyVal.clone()
+ initIV = ivVal.clone()
+ iv = ivVal.clone()
+
+ /**
+ * Input data buffer. The data starts at inBuffer.position() and ends at
+ * inBuffer.limit().
+ */
+ lazy val inBuffer = if (isDirectBuf) {
+ ByteBuffer.allocateDirect(bufferSize)
+ } else {
+ ByteBuffer.allocate(bufferSize)
+ }
+
+ /**
+ * Encrypted data buffer. The data starts at outBuffer.position() and
ends at
+ * outBuffer.limit();
+ */
+ lazy val outBuffer = if (isDirectBuf) {
+ ByteBuffer.allocateDirect(bufferSize)
+ } else {
+ ByteBuffer.allocate(bufferSize)
+ }
+ streamOffset = streamOffsetVal
+ encryptor = codec.createEncryptor()
+
+ updateEncryptor()
+
+ def this(
--- End diff --
BTW are all these constructors really needed? If everything goes through
`createCryptoOutputStream` and `createCryptoInputStream`, you should only need
one constructor in each class.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
