Github user budde commented on a diff in the pull request:
https://github.com/apache/spark/pull/17250#discussion_r105806348
--- Diff:
external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisDStream.scala
---
@@ -0,0 +1,559 @@
+/*
+ * 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 scala.reflect.ClassTag
+
+import
com.amazonaws.services.kinesis.clientlibrary.lib.worker.InitialPositionInStream
+import com.amazonaws.services.kinesis.model.Record
+
+import org.apache.spark.annotation.InterfaceStability
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.streaming.{Duration, StreamingContext}
+import org.apache.spark.streaming.api.java.JavaStreamingContext
+
+@InterfaceStability.Stable
+object KinesisDStream {
+ /**
+ * Builder for [[KinesisInputDStream]] instances.
+ *
+ * @param ssc StreamingContext to be used for creating DStreams
+ * @param streamName Name of Kinesis stream
+ * @param messageHandler Function for extracting DStream data type from
KCL Record
+ *
+ * @since 2.2.0
+ */
+ @InterfaceStability.Stable
+ class Builder[T: ClassTag](
+ ssc: StreamingContext,
+ streamName: String,
+ messageHandler: Record => T) {
+ private var endpointUrl = DEFAULT_KINESIS_ENDPOINT_URL
+ private var regionName = DEFAULT_KINESIS_REGION_NAME
+ private var initialPositionInStream =
DEFAULT_INITIAL_POSITION_IN_STREAM
+ private var checkpointAppName = ssc.sparkContext.appName
+ private var checkpointInterval = ssc.graph.batchDuration
+ private var storageLevel = DEFAULT_STORAGE_LEVEL
+ private var kinesisCredsProvider: SerializableCredentialsProvider =
DefaultCredentialsProvider
+ private var dynamoDBCredsProvider:
Option[SerializableCredentialsProvider] = None
+ private var cloudWatchCredsProvider:
Option[SerializableCredentialsProvider] = None
+
+ /**
+ * Sets the AWS Kinesis endpoint URL. Defaults to
"https://kinesis.us-east-1.amazonaws.com"; if
+ * no custom value is specified
+ *
+ * @param url Kinesis endpoint URL to use
+ * @return Reference to this [[KinesisDStream.Builder]]
+ */
+ def endpointUrl(url: String): Builder[T] = {
+ endpointUrl = url
+ this
+ }
+
+ /**
+ * Sets the AWS region to construct clients for. Defaults to
"us-east-1" if no custom value
+ * is specified.
+ *
+ * @param regionName Name of AWS region to use (e.g. "us-west-2")
+ * @return Reference to this [[KinesisDStream.Builder]]
+ */
+ def regionName(regionName: String): Builder[T] = {
+ this.regionName = regionName
+ this
+ }
+
+ /**
+ * Sets the initial position data is read from in the Kinesis stream.
Defaults to
+ * InitialPositionInStream.LATEST if no custom value is specified.
+ *
+ * @param initialPosition InitialPositionInStream value specifying
where Spark Streaming
+ * will start reading records in the Kinesis
stream from
+ * @return Reference to this [[KinesisDStream.Builder]]
+ */
+ def initialPositionInStream(initialPosition: InitialPositionInStream):
Builder[T] = {
+ initialPositionInStream = initialPosition
+ this
+ }
+
+ /**
+ * Sets the KCL application name to use when checkpointing state to
DynamoDB. Defaults to the
--- End diff --
We'll make this requited
---
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
