Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/8880#discussion_r41583106
--- Diff:
core/src/main/scala/org/apache/spark/crypto/CryptoInputStream.scala ---
@@ -0,0 +1,439 @@
+/*
+ * 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, InputStream, FilterInputStream}
+import java.nio.ByteBuffer
+import java.nio.channels.ReadableByteChannel
+import java.security.GeneralSecurityException
+import java.util.Queue
+import java.util.concurrent.ConcurrentLinkedQueue
+
+import com.google.common.base.Preconditions
+
+/**
+ * CryptoInputStream decrypts 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 decryption is buffer based. The key points of the
decryption
+ * are (1) calculating the counter and (2) padding through stream position:
+ * <p/>
+ * counter = base + pos/(algorithm blocksize);
+ * padding = pos%(algorithm blocksize);
+ * <p/>
+ * The underlying stream offset is maintained as state.
+ */
+class CryptoInputStream(
+ in: InputStream,
+ codecVal: CryptoCodec,
+ bufferSizeVal: Integer,
+ keyVal: Array[Byte],
+ ivVal: Array[Byte],
+ streamOffsetVal: Long)
+ extends FilterInputStream(in: InputStream) with ReadableByteChannel {
+ val oneByteBuf = new Array[Byte](1)
+ val codec = codecVal
+
+ val bufferSize = CryptoStreamUtils.checkBufferSize(codecVal,
bufferSizeVal)
+ /**
+ * Input data buffer. The data starts at inBuffer.position() and ends at
+ * to inBuffer.limit().
+ */
+ val inBuffer: ByteBuffer = ByteBuffer.allocateDirect(bufferSizeVal)
+
+ /**
+ * The decrypted data buffer. The data starts at outBuffer.position() and
+ * ends at outBuffer.limit()
+ */
+ val outBuffer: ByteBuffer = ByteBuffer.allocateDirect(bufferSizeVal)
+ var streamOffset: Long = streamOffsetVal // Underlying stream offset.
+
+ /**
+ * Whether the underlying stream supports
+ * {@link org.apache.hadoop.fs.ByteBufferReadable}
+ */
+ var usingByteBufferRead: Boolean = false
+ var usingByteBufferReadInitialized: Boolean = false
+ /**
+ * Padding = pos%(algorithm blocksize) Padding is put into {@link
#inBuffer}
+ * before any other data goes in. The purpose of padding is to put the
input
+ * data at proper position.
+ */
+ var padding: Byte = '0'
+ var closed: Boolean = false
+ var key: Array[Byte] = keyVal.clone()
+ var initIV: Array[Byte] = ivVal.clone()
+ var iv: Array[Byte] = ivVal.clone()
+ var isReadableByteChannel: Boolean = in.isInstanceOf[ReadableByteChannel]
+
+ /** DirectBuffer pool */
+ var bufferPool: Queue[ByteBuffer] = new
ConcurrentLinkedQueue[ByteBuffer]()
+ /** Decryptor pool */
+ var decryptorPool: Queue[Decryptor] = new
ConcurrentLinkedQueue[Decryptor]()
+
+ var tmpBuf: Array[Byte] = null
+ var decryptor: Decryptor = getDecryptor
+ CryptoStreamUtils.checkCodec(codecVal)
+ resetStreamOffset(streamOffset)
+
+ def this(in: InputStream,
+ codec: CryptoCodec,
+ bufferSize: Integer,
+ key: Array[Byte],
+ iv: Array[Byte]) {
+ this(in, codec, bufferSize, key, iv, 0)
+ }
+
+ def this(in: InputStream,
+ codec: CryptoCodec,
+ key: Array[Byte],
+ iv: Array[Byte]) {
+ this(in, codec, CryptoStreamUtils.getBufferSize, key, iv)
+ }
+
+ def getWrappedStream(): InputStream = in
+
+ /**
+ * Decryption is buffer based.
+ * If there is data in {@link #outBuffer}, then read it out of this
buffer.
--- End diff --
`@link` and friends are javadoc, and this is scaladoc; I'm not sure what's
the scaladoc syntax for links, though.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
