本文整理汇总了Scala中org.apache.hadoop.mapreduce.lib.output.FileOutputFormat类的典型用法代码示例。如果您正苦于以下问题：Scala FileOutputFormat类的具体用法？Scala FileOutputFormat怎么用？Scala FileOutputFormat使用的例子？那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了FileOutputFormat类的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: FrequencyMapReducer
//设置package包名称以及导入依赖的类
package com.argcv.cse8803.mapreducebasic
import com.argcv.valhalla.console.ColorForConsole._
import com.argcv.valhalla.utils.Awakable
import org.apache.hadoop.fs.Path
import org.apache.hadoop.io.{IntWritable, Text}
import org.apache.hadoop.mapreduce.Job
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat
object FrequencyMapReducer extends Awakable {
def main(args: Array[String]): Unit = {
// create a hadoop job and set main class
val job = Job.getInstance()
job.setJarByClass(FrequencyMapReducer.getClass)
job.setJobName("Frequency")
// set the input & output path
FileInputFormat.addInputPath(job, new Path(args.head))
FileOutputFormat.setOutputPath(job, new Path(s"${args(1)}-${System.currentTimeMillis()}"))
// set mapper & reducer
job.setMapperClass(FrequencyMapper.instance)
job.setReducerClass(FrequencyReducer.instance)
// specify the type of the output
job.setOutputKeyClass(new Text().getClass)
job.setOutputValueClass(new IntWritable().getClass)
// run
logger.info(s"job finished, status [${if (job.waitForCompletion(true)) "OK".withColor(GREEN) else "FAILED".withColor(RED)}]")
}
} 示例2: FrequencyMapReducer
//设置package包名称以及导入依赖的类
package com.argcv.iphigenia.example.hdfs.mr
import com.argcv.valhalla.console.ColorForConsole._
import com.argcv.valhalla.utils.Awakable
import org.apache.hadoop.fs.Path
import org.apache.hadoop.io.{ IntWritable, Text }
import org.apache.hadoop.mapreduce.Job
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat
object FrequencyMapReducer extends Awakable {
def main(args: Array[String]): Unit = {
// create a hadoop job and set main class
val job = Job.getInstance()
job.setJarByClass(FrequencyMapReducer.getClass)
job.setJobName("Frequency")
// set the input & output path
FileInputFormat.addInputPath(job, new Path(args.head))
FileOutputFormat.setOutputPath(job, new Path(s"${args(1)}-${System.currentTimeMillis()}"))
// set mapper & reducer
job.setMapperClass(FrequencyMapper.instance)
job.setReducerClass(FrequencyReducer.instance)
// specify the type of the output
job.setOutputKeyClass(new Text().getClass)
job.setOutputValueClass(new IntWritable().getClass)
// run
logger.info(s"job finished, status [${if (job.waitForCompletion(true)) "OK".withColor(GREEN) else "FAILED".withColor(RED)}]")
}
} 示例3: SuccinctAnnotationOutputFormat
//设置package包名称以及导入依赖的类
package edu.berkeley.cs.succinct.annot.serde
import java.io.File
import org.apache.hadoop.io.NullWritable
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat
import org.apache.hadoop.mapreduce.{RecordWriter, TaskAttemptContext}
class SuccinctAnnotationOutputFormat
extends FileOutputFormat[NullWritable, (Int, Iterator[(String, String, String)])] {
override def getRecordWriter(job: TaskAttemptContext):
RecordWriter[NullWritable, (Int, Iterator[(String, String, String)])] = {
val conf = job.getConfiguration
val ignoreParseErrors = conf.get("succinct.annotations.ignoreParseErrors", "true").toBoolean
val serializeInMemory = conf.get("succinct.annotations.serializeInMemory", "true").toBoolean
val dirs = conf.get("spark.local.dir", System.getProperty("java.io.tmpdir")).split(",")
println("ignoreParseErrors = " + ignoreParseErrors + " serializeInMemory = " + serializeInMemory
+ "Spark local dir = " + dirs(0) + " persistInMemory = false")
val path = FileOutputFormat.getOutputPath(job)
new SuccinctAnnotationRecordWriter(path, ignoreParseErrors, conf, (serializeInMemory, new File(dirs(0))))
}
}