Github user koeninger commented on a diff in the pull request: https://github.com/apache/spark/pull/20997#discussion_r180282891 --- Diff: external/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/KafkaDataConsumer.scala --- @@ -0,0 +1,381 @@ +/* + * 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.kafka010 + +import java.{util => ju} + +import scala.collection.JavaConverters._ + +import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord, KafkaConsumer} +import org.apache.kafka.common.{KafkaException, TopicPartition} + +import org.apache.spark.TaskContext +import org.apache.spark.internal.Logging + +private[kafka010] sealed trait KafkaDataConsumer[K, V] { + /** + * Get the record for the given offset if available. + * + * @param offset the offset to fetch. + * @param pollTimeoutMs timeout in milliseconds to poll data from Kafka. + */ + def get(offset: Long, pollTimeoutMs: Long): ConsumerRecord[K, V] = { + internalConsumer.get(offset, pollTimeoutMs) + } + + /** + * Start a batch on a compacted topic + * + * @param offset the offset to fetch. + * @param pollTimeoutMs timeout in milliseconds to poll data from Kafka. + */ + def compactedStart(offset: Long, pollTimeoutMs: Long): Unit = { + internalConsumer.compactedStart(offset, pollTimeoutMs) + } + + /** + * Get the next record in the batch from a compacted topic. + * Assumes compactedStart has been called first, and ignores gaps. + * + * @param pollTimeoutMs timeout in milliseconds to poll data from Kafka. + */ + def compactedNext(pollTimeoutMs: Long): ConsumerRecord[K, V] = { + internalConsumer.compactedNext(pollTimeoutMs) + } + + /** + * Rewind to previous record in the batch from a compacted topic. + * + * @throws NoSuchElementException if no previous element + */ + def compactedPrevious(): ConsumerRecord[K, V] = { + internalConsumer.compactedPrevious() + } + + /** + * Release this consumer from being further used. Depending on its implementation, + * this consumer will be either finalized, or reset for reuse later. + */ + def release(): Unit + + /** Reference to the internal implementation that this wrapper delegates to */ + protected def internalConsumer: InternalKafkaConsumer[K, V] +} + + +/** + * A wrapper around Kafka's KafkaConsumer. + * This is not for direct use outside this file. + */ +private[kafka010] +class InternalKafkaConsumer[K, V]( + val groupId: String, + val topicPartition: TopicPartition, + val kafkaParams: ju.Map[String, Object]) extends Logging { + + require(groupId == kafkaParams.get(ConsumerConfig.GROUP_ID_CONFIG), --- End diff -- This is mostly vestigial (there used to be a remove method that took a groupId, but no kafkaParams, so there was symmetry). I don't see a reason it can't be changed to match the SQL version at this point, i.e. assign groupId from the params.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org