Problem

We will use the FileSystem and Path classes from the org.apache.hadoop.fs library to achieve it.

Spark 2.0 or higher

package com.bigdataetl

import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.sql.SparkSession

object Test extends App {

  val spark = SparkSession.builder
    // I set master to local[*], because I run it on my local computer.
    // I production mode master will be set from spark-submit command.
    .master("local[*]")
    .appName("BigDataETL - Check if file exists")
    .getOrCreate()

  // Create FileSystem object from Hadoop Configuration
  val fs = FileSystem.get(spark.sparkContext.hadoopConfiguration)

  // This methods returns Boolean (true - if file exists, false - if file doesn't exist
  val fileExists = fs.exists(new Path("<parh_to_file>"))

  if (fileExists) println("File exists!")
  else println("File doesn't exist!")

}

 Since Spark 1.6 to 2.0

package com.bigdataetl

import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.{SparkConf, SparkContext}

object Test extends App {

  val sparkConf = new SparkConf().setAppName(s"BigDataETL - Check if file exists")
  val sc = new SparkContext(sparkConf)

  // Create FileSystem object from Hadoop Configuration
  val fs = FileSystem.get(sc.hadoopConfiguration)

  // This methods returns Boolean (true - if file exists, false - if file doesn't exist
  val fileExists = fs.exists(new Path("<parh_to_file>"))

  if (fileExists) println("File exists!")
  else println("File doesn't exist!")

}

If you enjoyed this post please add the comment below or share this post on your Facebook, Twitter, LinkedIn or another social media webpage.
Thanks in advanced!