习题 19:从文件创建 RDD 并过滤
题目:读取文件,过滤出包含
spark(不区分大小写)的行,统计行数。
import org.apache.spark.{SparkConf, SparkContext}
object TestFilter {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("testfilter").setMaster("local[*]")
val sc = new SparkContext(conf)
val rdd = sc.textFile("input/word.txt")
val cnt = rdd.filter(line => line.toLowerCase().contains("spark")).count()
println(cnt)
}
}