[大数据]Spark 读取HDFS的Zip文件

import java.util.zip.ZipInputStream;
import java.io.BufferedReader;
import java.io.InputStreamReader;   

val path = "xxxx.zip"

def loadZip(path:String)={
    val minPartitions =10
    sc.binaryFiles(path, minPartitions)
    	.flatMap { case (name: String, content: PortableDataStream)=>
        val zis = new ZipInputStream(content.open)
        Stream.continually(zis.getNextEntry)
        	.takeWhile(_ != null)
        	.flatMap { _ =>
                  val br = new BufferedReader(new InputStreamReader(zis))
                  Stream.continually(br.readLine()).takeWhile(_ != null)
              }}
}
 
val rdd = loadZip(path)