现在远程虚机创建1.txt输入如下内容
Hello Spark
Hello Java
[server@hadoop102 ~]$ cat 1.txt
Hello Spark
Hello Java
[server@hadoop102 ~]$ hadoop fs -put 1.txt /tmp
2025-12-28 10:17:55,964 INFO sasl.SaslDataTransferClient: SASL encryption trust check: localHostTrusted = false, remoteHostTrusted = false
[server@hadoop102 ~]$ hadoop fs -ls /tmp/
Found 5 items
-rw-r--r-- 3 server supergroup 23 2025-12-28 10:17 /tmp/1.txt
-rw-r--r-- 3 server supergroup 43579 2025-12-28 10:16 /tmp/a.txt
drwxrwxrwt - server supergroup 0 2021-08-03 17:19 /tmp/hadoop-yarn
drwxrwxrwt - server supergroup 0 2025-12-20 22:44 /tmp/hive
drwxrwxrwt - server server 0 2021-08-03 17:22 /tmp/logs
package com.spoon.bigdata.core.rdd.builder
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.rdd.RDD
object RDD_File {
def main(args: Array[String]): Unit = {
//准备环境
val sparkConf=new SparkConf().setMaster("local[*]").setAppName("RDD")
val sc=new SparkContext(sparkConf)
//val rdd: RDD[String] =sc.textFile("datas/1.txt")
val rdd: RDD[String] =sc.textFile("hdfs://hadoop102:8020/tmp/1.txt")
rdd.collect().foreach(println)
//关闭环境
sc.stop()
}
}
pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>spark-demo</artifactId>
<groupId>com.spoon.bigdata</groupId>
<version>1.0-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>spark-core</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.12</artifactId>
<version>3.0.0</version>
</dependency>
</dependencies>
<repositories>
<repository>
<id>pentaho-releases</id>
<url>https://nexus.pentaho.org/content/groups/omni/</url>
</repository>
<repository>
<id>pentaho</id>
<url>https://repo.pentaho.org/content/groups/omni/</url>
</repository>
</repositories>
</project>










网友评论