Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/1434#discussion_r15561926
--- Diff:
extras/spark-kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala
---
@@ -0,0 +1,151 @@
+/*
+ * 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.streaming.kinesis
+
+import org.apache.spark.streaming.StreamingContext
+import org.apache.spark.streaming.api.java.JavaReceiverInputDStream
+import org.apache.spark.streaming.api.java.JavaStreamingContext
+import org.apache.spark.streaming.dstream.ReceiverInputDStream
+import
com.amazonaws.services.kinesis.clientlibrary.exceptions.ThrottlingException
+import
com.amazonaws.services.kinesis.clientlibrary.exceptions.KinesisClientLibDependencyException
+import
com.amazonaws.services.kinesis.clientlibrary.exceptions.ShutdownException
+import
com.amazonaws.services.kinesis.clientlibrary.exceptions.InvalidStateException
+import org.apache.spark.Logging
+import
com.amazonaws.services.kinesis.clientlibrary.interfaces.IRecordProcessorFactory
+import
com.amazonaws.services.kinesis.clientlibrary.interfaces.IRecordProcessor
+import scala.util.Random
+import
com.amazonaws.services.kinesis.clientlibrary.lib.worker.InitialPositionInStream
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.streaming.util.ManualClock
+import org.apache.spark.streaming.util.Clock
+import org.apache.spark.streaming.util.SystemClock
+
+/**
+ * Facade to create the Scala-based or Java-based streams.
+ * Also, contains a reusable utility methods.
+ */
+object KinesisUtils extends Logging {
+ /**
+ * Create an InputDStream that pulls messages from a Kinesis stream.
+ *
+ * @param StreamingContext object
+ * @param app name
+ * @param stream name
+ * @param endpoint
+ * @param checkpoint interval (millis) for Kinesis checkpointing (not
Spark checkpointing).
+ * See the Kinesis Spark Streaming documentation for more details on the
different types of checkpoints.
+ * The default is TRIM_HORIZON to avoid potential data loss. However,
this presents the risk of processing records more than once.
+ * @param in the absence of Kinesis checkpoint info, this is the
worker's initial starting position in the stream.
+ * The values are either the beginning of the stream per Kinesis' limit
of 24 hours (InitialPositionInStream.TRIM_HORIZON)
+ * or the tip of the stream using InitialPositionInStream.LATEST.
+ * The default is StorageLevel.MEMORY_AND_DISK_2 which replicates
in-memory and on-disk to 2 nodes total (primary and secondary)
+ *
+ * @return ReceiverInputDStream[Array[Byte]]
+ */
+ def createStream(
+ ssc: StreamingContext,
+ app: String,
+ stream: String,
+ endpoint: String,
+ checkpointIntervalMillis: Long,
+ initialPositionInStream: InitialPositionInStream =
InitialPositionInStream.TRIM_HORIZON,
+ storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_2):
ReceiverInputDStream[Array[Byte]] = {
+
+ ssc.receiverStream(new KinesisReceiver(app, stream, endpoint,
checkpointIntervalMillis, initialPositionInStream, storageLevel))
+ }
+
+ /**
+ * Create a Java-friendly InputDStream that pulls messages from a
Kinesis stream.
+ *
+ * @param JavaStreamingContext object
+ * @param app name
+ * @param stream name
+ * @param endpoint
+ * @param checkpoint interval (millis) for Kinesis checkpointing (not
Spark checkpointing).
+ * See the Kinesis Spark Streaming documentation for more details on the
different types of checkpoints.
+ * The default is TRIM_HORIZON to avoid potential data loss. However,
this presents the risk of processing records more than once.
+ * @param in the absence of Kinesis checkpoint info, this is the
worker's initial starting position in the stream.
+ * The values are either the beginning of the stream per Kinesis' limit
of 24 hours (InitialPositionInStream.TRIM_HORIZON)
+ * or the tip of the stream using InitialPositionInStream.LATEST.
+ * The default is StorageLevel.MEMORY_AND_DISK_2 which replicates
in-memory and on-disk to 2 nodes total (primary and secondary)
+ *
+ * @return JavaReceiverInputDStream[Array[Byte]]
+ */
+ def createJavaStream(
+ jssc: JavaStreamingContext,
+ app: String,
+ stream: String,
+ endpoint: String,
+ checkpointIntervalMillis: Long,
+ initialPositionInStream: InitialPositionInStream =
InitialPositionInStream.TRIM_HORIZON,
+ storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_2):
JavaReceiverInputDStream[Array[Byte]] = {
+
+ jssc.receiverStream(new KinesisReceiver(app, stream, endpoint,
checkpointIntervalMillis, initialPositionInStream, storageLevel))
+ }
+
+ /**
+ * Create checkpoint state using the existing system clock
+ * @param checkpointIntervalMillis
+ */
+ def createCheckpointState(checkpointIntervalMillis: Long):
CheckpointState = {
+ new CheckpointState(checkpointIntervalMillis)
+ }
+
+ /**
+ * Retry the given amount of times with a random backoff time (millis)
less than the given maxBackOffMillis
+ *
+ * @param expression expression to evalute
+ * @param numRetriesLeft number of retries left
+ * @param maxBackOffMillis: max millis between retries
+ *
+ * @return Evaluation of the given expression
+ * @throws Unretryable exception, unexpected exception,
+ * or any exception that persists after numRetriesLeft reaches 0
+ */
+ @annotation.tailrec
+ def retry[T](expression: => T, numRetriesLeft: Int, maxBackOffMillis:
Int): T = {
--- End diff --
What is the point of this function? Seems like this is only used in
unit-tests? In which case shouldnt this be in the test classes only? Either
way, if the user is not expected to use this function directly, this is should
not be exposed.
---
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.
---
