drop the hive DB before populating it from scratch

This commit is contained in:
Claudio Atzori 2020-02-27 10:10:55 +01:00
parent 6a73fd5da5
commit 60bc2b1a20
4 changed files with 13 additions and 0 deletions

View File

@ -27,6 +27,7 @@ public class SparkGraphImporterJob {
final String inputPath = parser.get("sourcePath");
final String hiveDbName = parser.get("hive_db_name");
spark.sql(String.format("DROP DATABASE IF EXISTS %s CASCADE", hiveDbName));
spark.sql(String.format("CREATE DATABASE IF NOT EXISTS %s", hiveDbName));
// Read the input file and convert it into RDD of serializable object

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.graph;
public class SortableRelationKey {
}

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.graph.utils;
public class RelationPartitioner {
}

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.graph;
public class GraphJoinerTest {
}