spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tdas <...@git.apache.org>
Subject [GitHub] spark pull request #20096: [SPARK-22908] Add kafka source and sink for conti...
Date Thu, 04 Jan 2018 23:58:35 GMT
Github user tdas commented on a diff in the pull request:

    https://github.com/apache/spark/pull/20096#discussion_r159728249
  
    --- Diff: external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSinkV2.scala
---
    @@ -0,0 +1,142 @@
    +/*
    + * 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 org.apache.kafka.clients.producer.{Callback, ProducerRecord, RecordMetadata}
    +
    +import org.apache.spark.internal.Logging
    +import org.apache.spark.sql.{Row, SparkSession}
    +import org.apache.spark.sql.catalyst.InternalRow
    +import org.apache.spark.sql.catalyst.expressions.{Attribute, Cast, Literal, UnsafeProjection}
    +import org.apache.spark.sql.kafka010.KafkaSourceProvider.{kafkaParamsForProducer, TOPIC_OPTION_KEY}
    +import org.apache.spark.sql.sources.v2.streaming.writer.ContinuousWriter
    +import org.apache.spark.sql.sources.v2.writer._
    +import org.apache.spark.sql.streaming.OutputMode
    +import org.apache.spark.sql.types.{BinaryType, StringType, StructType}
    +
    +class ContinuousKafkaWriter(
    +    topic: Option[String], producerParams: Map[String, String], schema: StructType)
    +  extends ContinuousWriter with SupportsWriteInternalRow {
    +
    +  override def createInternalRowWriterFactory(): KafkaWriterFactory =
    +    KafkaWriterFactory(topic, producerParams, schema)
    +
    +  override def commit(epochId: Long, messages: Array[WriterCommitMessage]): Unit = {}
    +  override def abort(messages: Array[WriterCommitMessage]): Unit = {}
    +}
    +
    +case class KafkaWriterFactory(
    +    topic: Option[String], producerParams: Map[String, String], schema: StructType)
    +  extends DataWriterFactory[InternalRow] {
    +
    +  override def createDataWriter(partitionId: Int, attemptNumber: Int): DataWriter[InternalRow]
= {
    +    new KafkaDataWriter(topic, producerParams, schema.toAttributes)
    +  }
    +}
    +
    +case class KafkaWriterCommitMessage() extends WriterCommitMessage {}
    --- End diff --
    
    If there is no param, then this can be a `case object`. And I dont think `{}` is needed.
 


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message