假期四

Posted 2021-03-12 jbwen

vim ./sparkapp/src/main/scala/SimpleApp.scala #在 ./sparkapp/src/main/scala 下建立一个名为 SimpleApp.scala 的文件，并添加如下代码

/* SimpleApp.scala */
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf

object SimpleApp {
def main(args: Array[String]) {
val logFile = "file:///usr/local/spark/README.md" // Should be some file on your system
val conf = new SparkConf().setAppName("Simple Application")
val sc = new SparkContext(conf)
val logData = sc.textFile(logFile, 2).cache()
val numAs = logData.filter(line => line.contains("a")).count()
val numBs = logData.filter(line => line.contains("b")).count()
println("Lines with a: %s, Lines with b: %s".format(numAs, numBs))
}
}