Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/15102#discussion_r81658824
--- Diff:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala
---
@@ -0,0 +1,163 @@
+/*
+ * 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.sql.kafka010
+
+import java.{util => ju}
+
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.kafka.clients.consumer.{ConsumerRecord,
OffsetOutOfRangeException}
+import org.apache.kafka.common.TopicPartition
+
+import org.apache.spark.{Partition, SparkContext, TaskContext}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.storage.StorageLevel
+
+
+/** Offset range that one partition of the KafkaSourceRDD has to read */
+private[kafka010] case class KafkaSourceRDDOffsetRange(
+ topicPartition: TopicPartition,
+ fromOffset: Long,
+ untilOffset: Long,
+ preferredLoc: Option[String]) {
+ def topic: String = topicPartition.topic
+ def partition: Int = topicPartition.partition
+ def size: Long = untilOffset - fromOffset
+}
+
+
+/** Partition of the KafkaSourceRDD */
+private[kafka010] case class KafkaSourceRDDPartition(
+ index: Int, offsetRange: KafkaSourceRDDOffsetRange) extends Partition
+
+
+/**
+ * An RDD that reads data from Kafka based on offset ranges across
multiple partitions.
+ * Additionally, it allows preferred locations to be set for each topic +
partition, so that
+ * the [[KafkaSource]] can ensure the same executor always reads the same
topic + partition
+ * and cached KafkaConsuemrs (see [[CachedKafkaConsumer]] can be used read
data efficiently.
+ *
+ * Note that this is a simplified version of the
org.apache.spark.streaming.kafka010.KafkaRDD.
+ *
+ * @param executorKafkaParams Kafka configuration for creating
KafkaConsumer on the executors
+ * @param offsetRanges Offset ranges that define the Kafka data belonging
to this RDD
+ */
+private[kafka010] class KafkaSourceRDD(
+ sc: SparkContext,
+ executorKafkaParams: ju.Map[String, Object],
+ offsetRanges: Seq[KafkaSourceRDDOffsetRange])
+ extends RDD[ConsumerRecord[Array[Byte], Array[Byte]]](sc, Nil) {
+
+ override def persist(newLevel: StorageLevel): this.type = {
+ logError("Kafka ConsumerRecord is not serializable. " +
+ "Use .map to extract fields before calling .persist or .window")
+ super.persist(newLevel)
+ }
+
+ override def getPartitions: Array[Partition] = {
+ offsetRanges.zipWithIndex.map { case (o, i) => new
KafkaSourceRDDPartition(i, o) }.toArray
+ }
+
+ override def count(): Long = offsetRanges.map(_.size).sum
+
--- End diff --
> Why missing countApprox?
Added
---
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
