From 7514aee2a005953d475c4aa1c49a88372170e48d Mon Sep 17 00:00:00 2001
From: Baohe Zhang <baohe.zhang@verizonmedia.com>
Date: Tue, 25 Aug 2020 10:27:24 -0500
Subject: [PATCH] Update hive example to avoid conflict (#38)

---
 src/main/resources/oozie/spark_hive/workflow.xml      |  1 +
 .../com/yahoo/spark/starter/SparkHiveExample.scala    | 11 ++++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/src/main/resources/oozie/spark_hive/workflow.xml b/src/main/resources/oozie/spark_hive/workflow.xml
index bcf6670f7249e..abac36fcd34e3 100644
--- a/src/main/resources/oozie/spark_hive/workflow.xml
+++ b/src/main/resources/oozie/spark_hive/workflow.xml
@@ -36,6 +36,7 @@
             <spark-opts>--num-executors 3 --executor-memory 2g --executor-cores 1 --queue default --conf spark.yarn.security.tokens.hive.enabled=false</spark-opts>
             <arg>hdfs:///user/${wf:conf('user.name')}/${wfRoot}/output/hive_location</arg>
             <arg>hdfs:///user/${wf:conf('user.name')}/${wfRoot}/output/kv1.txt</arg>
+            <arg>${sparkTag}_hive_test</arg>
         </spark>
         <ok to="end" />
         <error to="fail" />
diff --git a/src/main/scala/com/yahoo/spark/starter/SparkHiveExample.scala b/src/main/scala/com/yahoo/spark/starter/SparkHiveExample.scala
index 459222e855ddc..1894eef9c3dc4 100644
--- a/src/main/scala/com/yahoo/spark/starter/SparkHiveExample.scala
+++ b/src/main/scala/com/yahoo/spark/starter/SparkHiveExample.scala
@@ -9,13 +9,14 @@ case class Record(key: Int, value: String)
 object SparkHiveExample {
   def main(args: Array[String]) {
 
-    if (args.length < 2) {
-      System.err.println("Usage: SparkHiveExample <databaseDir> <inputFile>")
+    if (args.length < 3) {
+      System.err.println("Usage: SparkHiveExample <databaseDir> <inputFile> <database>")
       System.exit(1)
     }
 
     val databaseDir = args(0)
     val inputFile = args(1)
+    val database = args(2)
 
     val spark = SparkSession
       .builder()
@@ -27,9 +28,9 @@ object SparkHiveExample {
     import spark.sql
 
     // Create a database under hdfs home directory for testing purpose
-    sql(s"CREATE DATABASE IF NOT EXISTS spark_hive_test LOCATION '$databaseDir'")
+    sql(s"CREATE DATABASE IF NOT EXISTS $database LOCATION '$databaseDir'")
 
-    sql("USE spark_hive_test")
+    sql(s"USE $database")
 
     // Create the table and load data from a text file on hdfs
     sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
@@ -113,7 +114,7 @@ object SparkHiveExample {
     // ...
 
     // Drop the database
-    sql("DROP DATABASE IF EXISTS spark_hive_test CASCADE")
+    sql(s"DROP DATABASE IF EXISTS $database CASCADE")
 
     spark.stop()
   }