本文整理汇总了Scala中org.apache.hadoop.io.compress.GzipCodec类的典型用法代码示例。如果您正苦于以下问题:Scala GzipCodec类的具体用法?Scala GzipCodec怎么用?Scala GzipCodec使用的例子?那么恭喜您, 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GzipCodec类的2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,您的评价将有助于我们的系统推荐出更棒的Scala代码示例。
示例1: BaseOutputFormat
//设置package包名称以及导入依赖的类
package kr.acon.lib.io
import java.io.DataOutputStream
import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.hadoop.mapred.FileOutputFormat
import org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.mapred.RecordWriter
import org.apache.hadoop.util.Progressable
import org.apache.hadoop.util.ReflectionUtils
import it.unimi.dsi.fastutil.longs.LongOpenHashBigSet
abstract class BaseOutputFormat extends FileOutputFormat[Long, LongOpenHashBigSet] {
@inline def getRecordWriter(out: DataOutputStream): RecordWriter[Long, LongOpenHashBigSet]
@inline override def getRecordWriter(ignored: FileSystem,
job: JobConf,
name: String,
progress: Progressable) = {
val isCompressed = FileOutputFormat.getCompressOutput(job)
if (!isCompressed) {
val file = FileOutputFormat.getTaskOutputPath(job, name)
val fs = file.getFileSystem(job)
val fileOut = fs.create(file, progress)
getRecordWriter(fileOut)
} else {
val codecClass = FileOutputFormat.getOutputCompressorClass(job, classOf[GzipCodec])
val codec = ReflectionUtils.newInstance(codecClass, job)
val file = FileOutputFormat.getTaskOutputPath(job, name + codec.getDefaultExtension())
val fs = file.getFileSystem(job)
val fileOut = fs.create(file, progress)
val fileOutWithCodec = new DataOutputStream(codec.createOutputStream(fileOut))
getRecordWriter(fileOutWithCodec)
}
}
}
开发者ID:chan150,项目名称:TrillionG,代码行数:39,代码来源:BaseOutputFormat.scala
示例2: Of
//设置package包名称以及导入依赖的类
package com.larry.da.jobs.userdigest
import java.text.SimpleDateFormat
import java.util.Date
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.SparkContext
agsid").map(UserMapping(_)).map(u => ((u.cid, u.idType), u)).reduceByKey((a, b) => a.merge(b), 150).map(_._2)
agsidToday.map(p => {p.uid = uidDic.value.getOrElse(p.uid, p.uid);p}).saveAsTextFile(s"${Config.historyIdMapAgsidPath}/$day", classOf[GzipCodec])
// agsidToday.map(p => {p.uid = uidDic.value.getOrElse(p.uid, p.uid);p}).saveAsTextFile(s"aguid/idmapHistory/agsid/$day", classOf[GzipCodec])
}
//------channelid-----------
aguid4Channel(historyDay, day);
//------agsid-----------
aguid4Agsid(day)
}
def aguidChange(day:String) = {
val rddList = "07,15,23".split(",").map(hour=>sc.textFile(s"/user/dauser/aguid/hbase/${day}-$hour/verticesDel").map(_ + "\t" + hour)).map(rdd=>{
rdd.map(x=>{
val Array(u1,u2,hour) = x.split("\t")
(u1,(u2,hour))
})
})
val log = sc.union( rddList )
val data = log.reduceByKey((a,b)=>if(a._2 > b._2) a else b,20)
data.map(x=>{
val (u1,(u2,hour)) = x
(u1,u2)
})
}
}
开发者ID:larry88,项目名称:spark_da,代码行数:39,代码来源:ChannelIdMerge.scala
注:本文中的org.apache.hadoop.io.compress.GzipCodec类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论