spark KafkaSourceOffset 源码

2022-10-20
浏览 (284)

spark KafkaSourceOffset 代码

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

import org.apache.spark.sql.connector.read.streaming
import org.apache.spark.sql.connector.read.streaming.PartitionOffset
import org.apache.spark.sql.execution.streaming.{Offset, SerializedOffset}

/**
 * An [[Offset]] for the [[KafkaSource]]. This one tracks all partitions of subscribed topics and
 * their offsets.
 */
private[kafka010]
case class KafkaSourceOffset(partitionToOffsets: Map[TopicPartition, Long]) extends Offset {

  override val json = JsonUtils.partitionOffsets(partitionToOffsets)
}

private[kafka010]
case class KafkaSourcePartitionOffset(topicPartition: TopicPartition, partitionOffset: Long)
  extends PartitionOffset

/** Companion object of the [[KafkaSourceOffset]] */
private[kafka010] object KafkaSourceOffset {

  def getPartitionOffsets(offset: Offset): Map[TopicPartition, Long] = {
    offset match {
      case o: KafkaSourceOffset => o.partitionToOffsets
      case so: SerializedOffset => KafkaSourceOffset(so).partitionToOffsets
      case _ =>
        throw new IllegalArgumentException(
          s"Invalid conversion from offset of ${offset.getClass} to KafkaSourceOffset")
    }
  }

  /**
   * Returns [[KafkaSourceOffset]] from a variable sequence of (topic, partitionId, offset)
   * tuples.
   */
  def apply(offsetTuples: (String, Int, Long)*): KafkaSourceOffset = {
    KafkaSourceOffset(offsetTuples.map { case(t, p, o) => (new TopicPartition(t, p), o) }.toMap)
  }

  /**
   * Returns [[KafkaSourceOffset]] from a JSON [[SerializedOffset]]
   */
  def apply(offset: SerializedOffset): KafkaSourceOffset =
    KafkaSourceOffset(JsonUtils.partitionOffsets(offset.json))

  /**
   * Returns [[KafkaSourceOffset]] from a streaming.Offset
   */
  def apply(offset: streaming.Offset): KafkaSourceOffset = {
    offset match {
      case k: KafkaSourceOffset => k
      case so: SerializedOffset => apply(so)
      case _ =>
        throw new IllegalArgumentException(
          s"Invalid conversion from offset of ${offset.getClass} to KafkaSourceOffset")
    }
  }
}

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 KafkaBatchWrite 源码

spark KafkaContinuousStream 源码

spark KafkaDataWriter 源码

spark KafkaMicroBatchStream 源码

spark KafkaOffsetRangeCalculator 源码

spark KafkaOffsetRangeLimit 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/761c9bcdc76f43c2bc54df43b01ac0e6

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...