enrico.ottonello
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Bug fixes

This commit is contained in:
dimitrispie 2023-04-23 18:22:26 +03:00
parent 4fa750b719
commit 53ce023035
3 changed files with 0 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/monitor.sh
View File

@ -17,7 +17,6 @@ echo "Getting file from " $SCRIPT_PATH
hdfs dfs -copyToLocal $SCRIPT_PATH hdfs dfs -copyToLocal $SCRIPT_PATH
echo "Creating monitor database" echo "Creating monitor database"
#cat step20-createMonitorDB.sql | sed s/SOURCE/$1/g | sed s/TARGET/$2/g1 > foo
cat createMonitorDB.sql | sed "s/TARGET/${TARGET}/g" | sed "s/SOURCE/${SOURCE}/g" > foo cat createMonitorDB.sql | sed "s/TARGET/${TARGET}/g" | sed "s/SOURCE/${SOURCE}/g" > foo
hive $HIVE_OPTS -f foo hive $HIVE_OPTS -f foo
echo "Hive shell finished" echo "Hive shell finished"

1
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/scripts/createMonitorDB.sql
View File

@ -3,7 +3,6 @@ DROP TABLE IF EXISTS TARGET.result_new;
create table TARGET.result_new stored as parquet as create table TARGET.result_new stored as parquet as
select distinct * from ( select distinct * from (
select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in ( select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in (
-- 'openorgs____::b8b8ca674452579f3f593d9f5e557483', -- University College Cork
'openorgs____::38d7097854736583dde879d12dacafca' -- Brown University 'openorgs____::38d7097854736583dde879d12dacafca' -- Brown University
) )) foo; ) )) foo;

2
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/workflow.xml
View File

@ -93,8 +93,6 @@
<job-tracker>${jobTracker}</job-tracker> <job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node> <name-node>${nameNode}</name-node>
<exec>copyDataToImpalaCluster.sh</exec> <exec>copyDataToImpalaCluster.sh</exec>
<!-- <env-var>HADOOP_USER_NAME=${wf:user()}</env-var>-->
<!-- <argument>${external_stats_db_name}</argument>-->
<argument>${monitor_db_name}</argument> <argument>${monitor_db_name}</argument>
<argument>${hadoop_user_name}</argument> <argument>${hadoop_user_name}</argument>
<file>copyDataToImpalaCluster.sh</file> <file>copyDataToImpalaCluster.sh</file>