aboutsummaryrefslogtreecommitdiff
path: root/external
diff options
context:
space:
mode:
authorYash Sharma <ysharma@atlassian.com>2017-04-13 08:49:19 +0100
committerSean Owen <sowen@cloudera.com>2017-04-13 08:49:19 +0100
commitec68d8f8cfdede8a0de1d56476205158544cc4eb (patch)
tree44c1539b81e42e45d3939da73e44d41cb1250ee3 /external
parentc5f1cc370f0aa1f0151fd34251607a8de861395e (diff)
downloadspark-ec68d8f8cfdede8a0de1d56476205158544cc4eb.tar.gz
spark-ec68d8f8cfdede8a0de1d56476205158544cc4eb.tar.bz2
spark-ec68d8f8cfdede8a0de1d56476205158544cc4eb.zip
[SPARK-20189][DSTREAM] Fix spark kinesis testcases to remove deprecated createStream and use Builders
## What changes were proposed in this pull request? The spark-kinesis testcases use the KinesisUtils.createStream which are deprecated now. Modify the testcases to use the recommended KinesisInputDStream.builder instead. This change will also enable the testcases to automatically use the session tokens automatically. ## How was this patch tested? All the existing testcases work fine as expected with the changes. https://issues.apache.org/jira/browse/SPARK-20189 Author: Yash Sharma <ysharma@atlassian.com> Closes #17506 from yssharma/ysharma/cleanup_kinesis_testcases.
Diffstat (limited to 'external')
-rw-r--r--external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala2
-rw-r--r--external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala58
2 files changed, 38 insertions, 22 deletions
diff --git a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala
index 8970ad2baf..77553412ed 100644
--- a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala
+++ b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisInputDStream.scala
@@ -267,7 +267,7 @@ object KinesisInputDStream {
getRequiredParam(checkpointAppName, "checkpointAppName"),
checkpointInterval.getOrElse(ssc.graph.batchDuration),
storageLevel.getOrElse(DEFAULT_STORAGE_LEVEL),
- handler,
+ ssc.sc.clean(handler),
kinesisCredsProvider.getOrElse(DefaultCredentials),
dynamoDBCredsProvider,
cloudWatchCredsProvider)
diff --git a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala
index ed7e358050..341a6898cb 100644
--- a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala
+++ b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala
@@ -22,7 +22,6 @@ import scala.concurrent.duration._
import scala.language.postfixOps
import scala.util.Random
-import com.amazonaws.regions.RegionUtils
import com.amazonaws.services.kinesis.clientlibrary.lib.worker.InitialPositionInStream
import com.amazonaws.services.kinesis.model.Record
import org.scalatest.{BeforeAndAfter, BeforeAndAfterAll}
@@ -173,11 +172,15 @@ abstract class KinesisStreamTests(aggregateTestData: Boolean) extends KinesisFun
* and you have to set the system environment variable RUN_KINESIS_TESTS=1 .
*/
testIfEnabled("basic operation") {
- val awsCredentials = KinesisTestUtils.getAWSCredentials()
- val stream = KinesisUtils.createStream(ssc, appName, testUtils.streamName,
- testUtils.endpointUrl, testUtils.regionName, InitialPositionInStream.LATEST,
- Seconds(10), StorageLevel.MEMORY_ONLY,
- awsCredentials.getAWSAccessKeyId, awsCredentials.getAWSSecretKey)
+ val stream = KinesisInputDStream.builder.streamingContext(ssc)
+ .checkpointAppName(appName)
+ .streamName(testUtils.streamName)
+ .endpointUrl(testUtils.endpointUrl)
+ .regionName(testUtils.regionName)
+ .initialPositionInStream(InitialPositionInStream.LATEST)
+ .checkpointInterval(Seconds(10))
+ .storageLevel(StorageLevel.MEMORY_ONLY)
+ .build()
val collected = new mutable.HashSet[Int]
stream.map { bytes => new String(bytes).toInt }.foreachRDD { rdd =>
@@ -198,12 +201,17 @@ abstract class KinesisStreamTests(aggregateTestData: Boolean) extends KinesisFun
}
testIfEnabled("custom message handling") {
- val awsCredentials = KinesisTestUtils.getAWSCredentials()
def addFive(r: Record): Int = JavaUtils.bytesToString(r.getData).toInt + 5
- val stream = KinesisUtils.createStream(ssc, appName, testUtils.streamName,
- testUtils.endpointUrl, testUtils.regionName, InitialPositionInStream.LATEST,
- Seconds(10), StorageLevel.MEMORY_ONLY, addFive(_),
- awsCredentials.getAWSAccessKeyId, awsCredentials.getAWSSecretKey)
+
+ val stream = KinesisInputDStream.builder.streamingContext(ssc)
+ .checkpointAppName(appName)
+ .streamName(testUtils.streamName)
+ .endpointUrl(testUtils.endpointUrl)
+ .regionName(testUtils.regionName)
+ .initialPositionInStream(InitialPositionInStream.LATEST)
+ .checkpointInterval(Seconds(10))
+ .storageLevel(StorageLevel.MEMORY_ONLY)
+ .buildWithMessageHandler(addFive(_))
stream shouldBe a [ReceiverInputDStream[_]]
@@ -233,11 +241,15 @@ abstract class KinesisStreamTests(aggregateTestData: Boolean) extends KinesisFun
val localTestUtils = new KPLBasedKinesisTestUtils(1)
localTestUtils.createStream()
try {
- val awsCredentials = KinesisTestUtils.getAWSCredentials()
- val stream = KinesisUtils.createStream(ssc, localAppName, localTestUtils.streamName,
- localTestUtils.endpointUrl, localTestUtils.regionName, InitialPositionInStream.LATEST,
- Seconds(10), StorageLevel.MEMORY_ONLY,
- awsCredentials.getAWSAccessKeyId, awsCredentials.getAWSSecretKey)
+ val stream = KinesisInputDStream.builder.streamingContext(ssc)
+ .checkpointAppName(localAppName)
+ .streamName(localTestUtils.streamName)
+ .endpointUrl(localTestUtils.endpointUrl)
+ .regionName(localTestUtils.regionName)
+ .initialPositionInStream(InitialPositionInStream.LATEST)
+ .checkpointInterval(Seconds(10))
+ .storageLevel(StorageLevel.MEMORY_ONLY)
+ .build()
val collected = new mutable.HashSet[Int]
stream.map { bytes => new String(bytes).toInt }.foreachRDD { rdd =>
@@ -303,13 +315,17 @@ abstract class KinesisStreamTests(aggregateTestData: Boolean) extends KinesisFun
ssc = new StreamingContext(sc, Milliseconds(1000))
ssc.checkpoint(checkpointDir)
- val awsCredentials = KinesisTestUtils.getAWSCredentials()
val collectedData = new mutable.HashMap[Time, (Array[SequenceNumberRanges], Seq[Int])]
- val kinesisStream = KinesisUtils.createStream(ssc, appName, testUtils.streamName,
- testUtils.endpointUrl, testUtils.regionName, InitialPositionInStream.LATEST,
- Seconds(10), StorageLevel.MEMORY_ONLY,
- awsCredentials.getAWSAccessKeyId, awsCredentials.getAWSSecretKey)
+ val kinesisStream = KinesisInputDStream.builder.streamingContext(ssc)
+ .checkpointAppName(appName)
+ .streamName(testUtils.streamName)
+ .endpointUrl(testUtils.endpointUrl)
+ .regionName(testUtils.regionName)
+ .initialPositionInStream(InitialPositionInStream.LATEST)
+ .checkpointInterval(Seconds(10))
+ .storageLevel(StorageLevel.MEMORY_ONLY)
+ .build()
// Verify that the generated RDDs are KinesisBackedBlockRDDs, and collect the data in each batch
kinesisStream.foreachRDD((rdd: RDD[Array[Byte]], time: Time) => {