spark KafkaSourceInitialOffsetWriter 源码

2022-10-20
浏览 (308)

spark KafkaSourceInitialOffsetWriter 代码

文件路径：/connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceInitialOffsetWriter.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.io._
import java.nio.charset.StandardCharsets

import org.apache.commons.io.IOUtils

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.streaming.{HDFSMetadataLog, SerializedOffset}

/** A version of [[HDFSMetadataLog]] specialized for saving the initial offsets. */
private[kafka010] class KafkaSourceInitialOffsetWriter(
    sparkSession: SparkSession,
    metadataPath: String)
  extends HDFSMetadataLog[KafkaSourceOffset](sparkSession, metadataPath) {

  val VERSION = 1

  override def serialize(metadata: KafkaSourceOffset, out: OutputStream): Unit = {
    out.write(0) // A zero byte is written to support Spark 2.1.0 (SPARK-19517)
    val writer = new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8))
    writer.write(s"v$VERSION\n")
    writer.write(metadata.json)
    writer.flush
  }

  override def deserialize(in: InputStream): KafkaSourceOffset = {
    in.read() // A zero byte is read to support Spark 2.1.0 (SPARK-19517)
    val content = IOUtils.toString(new InputStreamReader(in, StandardCharsets.UTF_8))
    // HDFSMetadataLog guarantees that it never creates a partial file.
    require(content.nonEmpty)
    if (content(0) == 'v') {
      val indexOfNewLine = content.indexOf("\n")
      if (indexOfNewLine > 0) {
        validateVersion(content.substring(0, indexOfNewLine), VERSION)
        KafkaSourceOffset(SerializedOffset(content.substring(indexOfNewLine + 1)))
      } else {
        throw new IllegalStateException(
          "Log file was malformed: failed to detect the log file version line.")
      }
    } else {
      // The log was generated by Spark 2.1.0
      KafkaSourceOffset(SerializedOffset(content))
    }
  }
}

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/7cb86b50f6b247b0800e8edc177143df

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...