in src/main/scala/com/aliyun/emr/example/spark/SparkOssDemo.scala [29:57]
def main(args: Array[String]): Unit = {
if (args.length < 2) {
System.err.println(
"""Usage: bin/spark-submit --class com.aliyun.emr.example.spark.SparkOssDemo examples-1.0-SNAPSHOT-shaded.jar
|
|Arguments:
|
| accessKeyId OSS accessKeyId
| accessKeySecret OSS accessKeySecret
| endpoint OSS endpoint
| inputPath Input OSS object path, like oss://bucket/input/a.txt
| outputPath Output OSS object path, like oss://bucket/output/
| numPartitions the number of RDD partitions.
|
""".stripMargin)
System.exit(1)
}
accessKeyId = args(0)
accessKeySecret = args(1)
endpoint = args(2)
val inputPath = args(3)
val outputPath = args(4)
val numPartitions = args(5).toInt
val ossData = getSparkContext.hadoopFile(inputPath, classOf[TextInputFormat], classOf[LongWritable], classOf[Text], numPartitions)
ossData.foreach(line => println(s"print: ${line}"))
ossData.saveAsTextFile(outputPath)
}