Apache spark 如何在spark rdd中读取zip文件中的分隔文件
我有一个HDFS位置,该位置中有一个zip文件 HDFS位置/开发/暂存/b8baf3f4-abce-11eb-8592-0242ac110032/records.zipApache spark 如何在spark rdd中读取zip文件中的分隔文件,apache-spark,Apache Spark,我有一个HDFS位置,该位置中有一个zip文件 HDFS位置/开发/暂存/b8baf3f4-abce-11eb-8592-0242ac110032/records.zip scala> val loc = "/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/" loc: String = "/development/staging/b8baf3f4-abce-11eb-8592-0242ac
scala> val loc = "/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/"
loc: String = "/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/"
scala> val rdd = sc.textFile(loc)
rdd: org.apache.spark.rdd.RDD[String] = /development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/ MapPartitionsRDD[1] at textFile at <console>:26
scala> rdd.take(2)
res0: Array[String] = Array(PK????????]R�R��*�????�??? ???2972120.dat�S�r�0?
��*�0����?t?�]T�Ж??����
`�6ط�kU;P�M�� rSO�;G��p��?��?�Z1^3@�^�� ��F��ٕb�?~,ٖ
�u6�D��'�@�??��L*�Gp?�kcL�7!r�p1�1e�� a*.{?
�.;��������s�(�)�, ?�=�9U<"*!?5��?;�?�?�مd{h}
��gG���� �?�Z)
scala>val loc=“/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/”
loc:String=“/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/”
scala>val rdd=sc.textFile(loc)
rdd:org.apache.spark.rdd.rdd[String]=/development/staging/b8baf3f4-abce-11eb-8592-0242ac110032/MapPartitionsRDD[1],文本文件:26
scala>rdd.take(2)
res0:Array[String]=数组(PK?????)RżRżRżR˝RRR˝RRo?
ď
`本方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方方!
第七届奥运会开幕式是什么?第七届奥运会开幕式是什么?
你正在寻找这样的东西:
import java.io.{ IOException, FileOutputStream, FileInputStream, File }
import java.util.zip.{ ZipEntry, ZipInputStream }
import org.apache.spark.sql.SQLContext
import org.apache.spark.SparkContext
//Unzip the file and copy the internal contents outside in new location
object Unzip extends App {
val INPUT_ZIP_FILE: String = "src/resources/my-zip.zip";
val OUTPUT_FOLDER: String = "src/resources/my-zip";
def unZipIt(zipFile: String, outputFolder: String): Unit = {
val buffer = new Array[Byte](1024)
try {
//output directory
val folder = new File(OUTPUT_FOLDER);
if (!folder.exists()) {
folder.mkdir();
}
//zip file content
val zis: ZipInputStream = new ZipInputStream(new FileInputStream(zipFile));
//get the zipped file list entry
var ze: ZipEntry = zis.getNextEntry();
while (ze != null) {
val fileName = ze.getName();
val newFile = new File(outputFolder + File.separator + fileName);
System.out.println("file unzip : " + newFile.getAbsoluteFile());
//create folders
new File(newFile.getParent()).mkdirs();
val fos = new FileOutputStream(newFile);
var len: Int = zis.read(buffer);
while (len > 0) {
fos.write(buffer, 0, len)
len = zis.read(buffer)
}
fos.close()
ze = zis.getNextEntry()
}
zis.closeEntry()
zis.close()
} catch {
case e: IOException => println("exception caught: " + e.getMessage)
}
}
Unzip.unZipIt(INPUT_ZIP_FILE, OUTPUT_FOLDER)
val sac = new SparkContext("local[*]", " first Program");
val sqlc = new SQLContext(sac);
val rdd = sac.textFile("src/resources/my-zip/sample.txt")
rdd.take(1).foreach(println)
/*val rddFromFile = sqlc.sparkContext.textFile("src/resources/my-zip/sample.txt")
println(rddFromFile.getClass)
println("##Get data Using collect")
rddFromFile.collect().foreach(f=>{
println(f)
})*/
}
不确定这是否达到了您想要的效果,但可能会有所帮助!这是否回答了您的问题?正在寻找scala代码中的解决方案