spark KafkaBatchWrite 源码

2022-10-20
浏览 (319)

spark KafkaBatchWrite 代码

文件路径：/connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaBatchWrite.scala

/*
 * 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 org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.connector.write.{BatchWrite, DataWriter, DataWriterFactory, PhysicalWriteInfo, WriterCommitMessage}
import org.apache.spark.sql.kafka010.KafkaWriter.validateQuery
import org.apache.spark.sql.types.StructType

/**
 * A [[BatchWrite]] for Kafka writing. Responsible for generating the writer factory.
 *
 * @param topic The topic this writer is responsible for. If None, topic will be inferred from
 *              a `topic` field in the incoming data.
 * @param producerParams Parameters for Kafka producers in each task.
 * @param schema The schema of the input data.
 */
private[kafka010] class KafkaBatchWrite(
    topic: Option[String],
    producerParams: ju.Map[String, Object],
    schema: StructType)
  extends BatchWrite {

  validateQuery(schema.toAttributes, producerParams, topic)

  override def createBatchWriterFactory(info: PhysicalWriteInfo): KafkaBatchWriterFactory =
    KafkaBatchWriterFactory(topic, producerParams, schema)

  override def commit(messages: Array[WriterCommitMessage]): Unit = {}
  override def abort(messages: Array[WriterCommitMessage]): Unit = {}
}

/**
 * A [[DataWriterFactory]] for Kafka writing. Will be serialized and sent to executors to
 * generate the per-task data writers.
 * @param topic The topic that should be written to. If None, topic will be inferred from
 *              a `topic` field in the incoming data.
 * @param producerParams Parameters for Kafka producers in each task.
 * @param schema The schema of the input data.
 */
private case class KafkaBatchWriterFactory(
    topic: Option[String],
    producerParams: ju.Map[String, Object],
    schema: StructType)
  extends DataWriterFactory {

  override def createWriter(partitionId: Int, taskId: Long): DataWriter[InternalRow] = {
    new KafkaDataWriter(topic, producerParams, schema.toAttributes)
  }
}

相关信息

spark 源码目录

相关文章

spark ConsumerStrategy 源码

spark JsonUtils 源码

spark KafkaBatch 源码

spark KafkaBatchPartitionReader 源码

spark KafkaContinuousStream 源码

spark KafkaDataWriter 源码

spark KafkaMicroBatchStream 源码

spark KafkaOffsetRangeCalculator 源码

spark KafkaOffsetRangeLimit 源码

spark KafkaOffsetReader 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://www.seaxiang.com/blog/96b37a694d944db1bf9aa72fc48d388c

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙初识ArkTS语言
6、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
7、 flink kafka connector scan.startup.mode 的几个选项
8、 golang
9、 openharmony
10、 Vue中input框自动聚焦

Loading...