From 9758645fd6e51d71c25b42766a582ee909ae3f9a Mon Sep 17 00:00:00 2001
From: priyankab122 <priyanka@scienaptic.com>
Date: Sat, 15 Aug 2020 01:15:17 +0530
Subject: [PATCH] removed file protocol from the filepath

---
 src/main/java/com/scienaptic/Application.java | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/main/java/com/scienaptic/Application.java b/src/main/java/com/scienaptic/Application.java
index 6908556..fb930b8 100644
--- a/src/main/java/com/scienaptic/Application.java
+++ b/src/main/java/com/scienaptic/Application.java
@@ -11,15 +11,14 @@ public class Application extends MistFn {
 
     @Override
     public Handle handle() {
-        return withArgs(stringArg("inputPath")).
+        return withArgs(stringArg("inputPath")). //Give complete hdfs path hdfs://<host:port>/filepath for parameter inputPath while running the job
                 withMistExtras().
-                onSparkSession((path, extras, SparkSession) -> {
-                    String filePath =  "file://" + path;
+                onSparkSession((filePath, extras, SparkSession) -> {
                     Dataset<Row> df = SparkSession.read()
                             .format("csv")
                             .option("header",true)
                             .load(filePath);
-                    String fileName = filePath.substring(0,path.lastIndexOf('.'));
+                    String fileName = filePath.substring(0,filePath.lastIndexOf('.'));
                     String outputPath = fileName + ".parquet";
                     df.write().mode("overwrite").parquet(outputPath);
                     return  outputPath;