Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/3798#discussion_r23586464 --- Diff: external/kafka/src/main/scala/org/apache/spark/rdd/kafka/KafkaCluster.scala --- @@ -0,0 +1,318 @@ +/* + * 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.rdd.kafka + +import scala.util.control.NonFatal +import scala.util.Random +import scala.collection.mutable.ArrayBuffer +import java.util.Properties +import kafka.api._ +import kafka.common.{ErrorMapping, OffsetMetadataAndError, TopicAndPartition} +import kafka.consumer.{ConsumerConfig, SimpleConsumer} + +/** + * Convenience methods for interacting with a Kafka cluster. + * @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 + */ +class KafkaCluster(val kafkaParams: Map[String, String]) extends Serializable { + import KafkaCluster.{Err, LeaderOffset} + + val seedBrokers: Array[(String, Int)] = + kafkaParams.get("metadata.broker.list") + .orElse(kafkaParams.get("bootstrap.servers")) + .getOrElse(throw new Exception("Must specify metadata.broker.list or bootstrap.servers")) + .split(",").map { hp => + val hpa = hp.split(":") + (hpa(0), hpa(1).toInt) + } + + // ConsumerConfig isn't serializable + @transient private var _config: ConsumerConfig = null + + def config: ConsumerConfig = this.synchronized { + if (_config == null) { + _config = KafkaCluster.consumerConfig(kafkaParams) + } + _config + } + + def connect(host: String, port: Int): SimpleConsumer = + new SimpleConsumer(host, port, config.socketTimeoutMs, + config.socketReceiveBufferBytes, config.clientId) + + def connect(hostAndPort: (String, Int)): SimpleConsumer = + connect(hostAndPort._1, hostAndPort._2) + + def connectLeader(topic: String, partition: Int): Either[Err, SimpleConsumer] = + findLeader(topic, partition).right.map(connect) + + def findLeader(topic: String, partition: Int): Either[Err, (String, Int)] = { + val req = TopicMetadataRequest(TopicMetadataRequest.CurrentVersion, + 0, config.clientId, Seq(topic)) + val errs = new Err + withBrokers(Random.shuffle(seedBrokers), errs) { consumer => + val resp: TopicMetadataResponse = consumer.send(req) + resp.topicsMetadata.find(_.topic == topic).flatMap { t => --- End diff -- this block of code is pretty hard to understand with so many level of nesting. can you rewrite it? maybe by introducing variables and adding comments to explain what is going on. overall I feel this PR went slightly overboard with Scala. With no explicit type, intermediate variable, and comment, it is pretty hard to understand a lot of blocks
--- 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