Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/3798#discussion_r23822761 --- Diff: external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaUtils.scala --- @@ -144,4 +149,182 @@ object KafkaUtils { createStream[K, V, U, T]( jssc.ssc, kafkaParams.toMap, Map(topics.mapValues(_.intValue()).toSeq: _*), storageLevel) } + + /** A batch-oriented interface for consuming from Kafka. + * Starting and ending offsets are specified in advance, + * so that you can control exactly-once semantics. + * @param sc SparkContext object + * @param kafkaParams Kafka <a href="http://kafka.apache.org/documentation.html#configuration"> + * configuration parameters</a>. + * Requires "metadata.broker.list" or "bootstrap.servers" to be set with Kafka broker(s), + * NOT zookeeper servers, specified in host1:port1,host2:port2 form. + * @param batch Each OffsetRange in the batch corresponds to a + * range of offsets for a given Kafka topic/partition + */ + def createRDD[ + K: ClassTag, + V: ClassTag, + U <: Decoder[_]: ClassTag, + T <: Decoder[_]: ClassTag, + R: ClassTag] ( + sc: SparkContext, + kafkaParams: Map[String, String], + batch: Array[OffsetRange] + ): RDD[(K, V)] with HasOffsetRanges = { + val messageHandler = (mmd: MessageAndMetadata[K, V]) => (mmd.key, mmd.message) + val kc = new KafkaCluster(kafkaParams) + val topics = batch.map(o => TopicAndPartition(o.topic, o.partition)).toSet + val leaderMap = kc.findLeaders(topics).fold( + errs => throw new SparkException(errs.mkString("\n")), + ok => ok + ) + val rddParts = batch.zipWithIndex.map { case (o, i) => + val tp = TopicAndPartition(o.topic, o.partition) + val (host, port) = leaderMap(tp) + new KafkaRDDPartition(i, o.topic, o.partition, o.fromOffset, o.untilOffset, host, port) + }.toArray + new KafkaRDD[K, V, U, T, (K, V)](sc, kafkaParams, rddParts, messageHandler) + } + + /** A batch-oriented interface for consuming from Kafka. + * Starting and ending offsets are specified in advance, + * so that you can control exactly-once semantics. + * @param sc SparkContext object + * @param kafkaParams Kafka <a href="http://kafka.apache.org/documentation.html#configuration"> + * configuration parameters</a>. + * Requires "metadata.broker.list" or "bootstrap.servers" to be set with Kafka broker(s), + * NOT zookeeper servers, specified in host1:port1,host2:port2 form. + * @param batch Each OffsetRange in the batch corresponds to a + * range of offsets for a given Kafka topic/partition + * @param leaders Kafka leaders for each offset range in batch + * @param messageHandler function for translating each message into the desired type + */ + def createRDD[ + K: ClassTag, + V: ClassTag, + U <: Decoder[_]: ClassTag, + T <: Decoder[_]: ClassTag, + R: ClassTag] ( + sc: SparkContext, + kafkaParams: Map[String, String], + batch: Array[OffsetRange], + leaders: Array[Leader], + messageHandler: MessageAndMetadata[K, V] => R + ): RDD[R] with HasOffsetRanges = { + val leaderMap = leaders.map(l => (l.topic, l.partition) -> (l.host, l.port)).toMap + val rddParts = batch.zipWithIndex.map { case (o, i) => + val (host, port) = leaderMap((o.topic, o.partition)) + new KafkaRDDPartition(i, o.topic, o.partition, o.fromOffset, o.untilOffset, host, port) + }.toArray + + new KafkaRDD[K, V, U, T, R](sc, kafkaParams, rddParts, messageHandler) + } + + /** + * Compared to `createStream`, the stream created by this can guarantee that each message + * from Kafka is included in transformations (as opposed to output actions) exactly once, + * even in most failure situations. + * + * Points to note: + * + * Failure Recovery - You must checkpoint this stream, or save offsets yourself and provide them + * as the fromOffsets parameter on restart. + * Kafka must have sufficient log retention to obtain messages after failure. + * + * Getting offsets from the stream - see programming guide + * +. * Zookeeper - This does not use Zookeeper to store offsets. For interop with Kafka monitors + * that depend on Zookeeper, you must store offsets in ZK yourself. + * + * End-to-end semantics - This does not guarantee that any output operation will push each record + * exactly once. To ensure end-to-end exactly-once semantics (that is, receiving exactly once and + * outputting exactly once), you have to either ensure that the output operation is + * idempotent, or transactionally store offsets with the output. See the programming guide for + * more details. + * + * @param ssc StreamingContext object + * @param kafkaParams Kafka <a href="http://kafka.apache.org/documentation.html#configuration"> + * configuration parameters</a>. + * Requires "metadata.broker.list" or "bootstrap.servers" to be set with Kafka broker(s), + * NOT zookeeper servers, specified in host1:port1,host2:port2 form. + * @param messageHandler function for translating each message into the desired type + * @param fromOffsets per-topic/partition Kafka offsets defining the (inclusive) + * starting point of the stream + * @param maxRetries maximum number of times in a row to retry getting leaders' offsets + */ + def createNewStream[ --- End diff -- BTW, all these public methods needs to annotated with "@Experimental" (see org.apache.spark.annotation.Experimental and its uses).
--- 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