D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

Bug fixes

This commit is contained in:
dimitrispie 2023-04-23 18:29:00 +03:00
parent 53ce023035
commit fdb5d2b39f
9 changed files with 0 additions and 584 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
dhp-workflows/dhp-monitor-update/pom.xml
View File

@ -1,32 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.2.4-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-monitor-update</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>pl.project13.maven</groupId>
<artifactId>git-commit-id-plugin</artifactId>
<version>2.1.11</version>
<configuration>
<failOnNoGitDirectory>false</failOnNoGitDirectory>
</configuration>
</plugin>
</plugins>
</build>
</project>

34
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/config-default.xml
View File

@ -1,34 +0,0 @@
<configuration>
<property>
<name>jobTracker</name>
<value>${jobTracker}</value>
</property>
<property>
<name>nameNode</name>
<value>${nameNode}</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hive_jdbc_url</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000/;UseNativeQuery=1;?spark.executor.memory=19166291558;spark.yarn.executor.memoryOverhead=3225;spark.driver.memory=11596411699;spark.yarn.driver.memoryOverhead=1228</value>
</property>
<property>
<name>oozie.wf.workflow.notification.url</name>
<value>{serviceUrl}/v1/oozieNotification/jobUpdate?jobId=$jobId%26status=$status</value>
</property>
<property>
<name>stats_tool_api_url</name>
<value>${stats_tool_api_url}</value>
</property>
</configuration>

56
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/copyDataToImpalaCluster.sh
View File

@ -1,56 +0,0 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
#export HADOOP_USER_NAME="dimitris.pierrakos"
export HADOOP_USER_NAME=$2
function copydb() {
db=$1
# copy the databases from ocean to impala
echo "copying $db"
hadoop distcp -Dmapreduce.map.memory.mb=6144 -pb hdfs://nameservice1/user/hive/warehouse/${db}.db hdfs://impala-cluster-mn1.openaire.eu:8020/tmp
# change ownership to impala
hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -chmod -R 777 /tmp/${db}.db
# create the databases
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop database if exists ${db} cascade";
impala-shell -i impala-cluster-dn1.openaire.eu -q "create database ${db}";
impala-shell -q "INVALIDATE METADATA"
echo "creating schema for ${db}"
for i in `impala-shell -d ${db} --delimited -q "show tables"`;
do
impala-shell -d ${db} --delimited -q "show create table $i";
done | sed 's/"$/;/' | sed 's/^"//' | sed 's/[[:space:]]\date[[:space:]]/`date`/g' | impala-shell -i impala-cluster-dn1.openaire.eu -c -f -
# run the same command twice because we may have failures in the first run (due to views pointing to the same db)
for i in `impala-shell -d ${db} --delimited -q "show tables"`;
do
impala-shell -d ${db} --delimited -q "show create table $i";
done | sed 's/"$/;/' | sed 's/^"//' | sed 's/[[:space:]]\date[[:space:]]/`date`/g' | impala-shell -i impala-cluster-dn1.openaire.eu -c -f -
# load the data from /tmp in the respective tables
echo "copying data in tables and computing stats"
for i in `impala-shell -i impala-cluster-dn1.openaire.eu -d ${db} --delimited -q "show tables"`;
do
impala-shell -i impala-cluster-dn1.openaire.eu -d ${db} -q "load data inpath '/tmp/${db}.db/$i' into table $i";
impala-shell -i impala-cluster-dn1.openaire.eu -d ${db} -q "compute stats $i";
done
# deleting the remaining directory from hdfs
hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -rm -R /tmp/${db}.db
}
MONITOR_DB=$1
HADOOP_USER_NAME=$2
copydb $MONITOR_DB

22
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/finalizeImpalaCluster.sh
View File

@ -1,22 +0,0 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
function createShadowDB() {
SOURCE=$1
SHADOW=$2
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop database ${SHADOW} CASCADE";
impala-shell -i impala-cluster-dn1.openaire.eu -q "create database if not exists ${SHADOW}";
# impala-shell -i impala-cluster-dn1.openaire.eu -d ${SHADOW} -q "show tables" | sed "s/^/drop view if exists ${SHADOW}./" | sed "s/$/;/" | impala-shell -i impala-cluster-dn1.openaire.eu -f -
impala-shell -i impala-cluster-dn1.openaire.eu -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -i impala-cluster-dn1.openaire.eu -f -
}
MONITOR_DB=$3
MONITOR_DB_SHADOW=$4
createShadowDB $MONITOR_DB $MONITOR_DB_SHADOW

19
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/monitor-post.sh
View File

@ -1,19 +0,0 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
export SOURCE=$1
export SHADOW=$2
export HIVE_OPTS="-hiveconf mapred.job.queue.name=analytics -hiveconf hive.spark.client.connect.timeout=120000ms -hiveconf hive.spark.client.server.connect.timeout=300000ms -hiveconf spark.executor.memory=19166291558 -hiveconf spark.yarn.executor.memoryOverhead=3225 -hiveconf spark.driver.memory=11596411699 -hiveconf spark.yarn.driver.memoryOverhead=1228"
export HADOOP_USER_NAME="oozie"
echo "Updating shadow database"
hive -e "drop database if exists ${SHADOW} cascade"
hive -e "create database if not exists ${SHADOW}"
hive $HIVE_OPTS --database ${SOURCE} -e "show tables" | grep -v WARN | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" > foo
hive -f foo
echo "Updated shadow database"

22
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/monitor.sh
View File

@ -1,22 +0,0 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
export SOURCE=$1
export TARGET=$2
export SCRIPT_PATH=$3
export HIVE_OPTS="-hiveconf mapred.job.queue.name=analytics -hiveconf hive.spark.client.connect.timeout=120000ms -hiveconf hive.spark.client.server.connect.timeout=300000ms -hiveconf spark.executor.memory=19166291558 -hiveconf spark.yarn.executor.memoryOverhead=3225 -hiveconf spark.driver.memory=11596411699 -hiveconf spark.yarn.driver.memoryOverhead=1228"
export HADOOP_USER_NAME="oozie"
echo "Getting file from " $SCRIPT_PATH
hdfs dfs -copyToLocal $SCRIPT_PATH
echo "Creating monitor database"
cat createMonitorDB.sql | sed "s/TARGET/${TARGET}/g" | sed "s/SOURCE/${SOURCE}/g" > foo
hive $HIVE_OPTS -f foo
echo "Hive shell finished"

266
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/scripts/createMonitorDB.sql
View File

@ -1,266 +0,0 @@
DROP TABLE IF EXISTS TARGET.result_new;
create table TARGET.result_new stored as parquet as
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 (
'openorgs____::38d7097854736583dde879d12dacafca' -- Brown University
) )) foo;
ANALYZE TABLE TARGET.result_new COMPUTE STATISTICS;
INSERT INTO TARGET.result select * from TARGET.result_new;
INSERT INTO TARGET.result_citations select * from TARGET.result_citations orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_citations COMPUTE STATISTICS;
INSERT INTO TARGET.result_references_oc select * from TARGET.result_references_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_references_oc COMPUTE STATISTICS;
INSERT INTO TARGET.result_citations_oc select * from TARGET.result_citations_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_citations_oc COMPUTE STATISTICS;
INSERT INTO TARGET.result_classifications select * from TARGET.result_classifications orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_classifications COMPUTE STATISTICS;
INSERT INTO TARGET.result_apc select * from TARGET.result_apc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_apc COMPUTE STATISTICS;
INSERT INTO TARGET.result_concepts select * from TARGET.result_concepts orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_concepts COMPUTE STATISTICS;
INSERT INTO TARGET.result_datasources select * from TARGET.result_datasources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_datasources COMPUTE STATISTICS;
INSERT INTO TARGET.result_fundercount select * from TARGET.result_fundercount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_fundercount COMPUTE STATISTICS;
INSERT INTO TARGET.result_gold select * from TARGET.result_gold orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_gold COMPUTE STATISTICS;
INSERT INTO TARGET.result_greenoa select * from TARGET.result_greenoa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_greenoa COMPUTE STATISTICS;
INSERT INTO TARGET.result_languages select * from TARGET.result_languages orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_languages COMPUTE STATISTICS;
INSERT INTO TARGET.result_licenses select * from TARGET.result_licenses orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_licenses COMPUTE STATISTICS;
INSERT INTO TARGET.result_oids select * from TARGET.result_oids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_oids COMPUTE STATISTICS;
INSERT INTO TARGET.result_organization select * from TARGET.result_organization orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_organization COMPUTE STATISTICS;
INSERT INTO TARGET.result_peerreviewed select * from TARGET.result_peerreviewed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_peerreviewed COMPUTE STATISTICS;
INSERT INTO TARGET.result_pids select * from TARGET.result_pids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_pids COMPUTE STATISTICS;
INSERT INTO TARGET.result_projectcount select * from TARGET.result_projectcount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_projectcount COMPUTE STATISTICS;
INSERT INTO TARGET.result_projects select * from TARGET.result_projects orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_projects COMPUTE STATISTICS;
INSERT INTO TARGET.result_refereed select * from TARGET.result_refereed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_refereed COMPUTE STATISTICS;
INSERT INTO TARGET.result_sources select * from TARGET.result_sources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_sources COMPUTE STATISTICS;
INSERT INTO TARGET.result_topics select * from TARGET.result_topics orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_topics COMPUTE STATISTICS;
INSERT INTO TARGET.result_fos select * from TARGET.result_fos orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.result_fos COMPUTE STATISTICS;
INSERT INTO TARGET.result select * from TARGET.result_new;
COMPUTE STATS TARGET.result;
INSERT INTO TARGET.result_citations select * from TARGET.result_citations orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_citations;
INSERT INTO TARGET.result_references_oc select * from TARGET.result_references_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_references_oc;
INSERT INTO TARGET.result_citations_oc select * from TARGET.result_citations_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_citations_oc;
INSERT INTO TARGET.result_classifications select * from TARGET.result_classifications orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_classifications;
INSERT INTO TARGET.result_apc select * from TARGET.result_apc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_apc;
INSERT INTO TARGET.result_concepts select * from TARGET.result_concepts orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_concepts;
INSERT INTO TARGET.result_datasources select * from TARGET.result_datasources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_datasources;
INSERT INTO TARGET.result_fundercount select * from TARGET.result_fundercount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_fundercount;
INSERT INTO TARGET.result_gold select * from TARGET.result_gold orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_gold;
INSERT INTO TARGET.result_greenoa select * from TARGET.result_greenoa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_greenoa;
INSERT INTO TARGET.result_languages select * from TARGET.result_languages orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_languages;
INSERT INTO TARGET.result_licenses select * from TARGET.result_licenses orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_licenses;
INSERT INTO TARGET.result_oids select * from TARGET.result_oids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_oids;
INSERT INTO TARGET.result_organization select * from TARGET.result_organization orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_organization;
INSERT INTO TARGET.result_peerreviewed select * from TARGET.result_peerreviewed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_peerreviewed;
INSERT INTO TARGET.result_pids select * from TARGET.result_pids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_pids;
INSERT INTO TARGET.result_projectcount select * from TARGET.result_projectcount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_projectcount;
INSERT INTO TARGET.result_projects select * from TARGET.result_projects orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_projects;
INSERT INTO TARGET.result_refereed select * from TARGET.result_refereed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_refereed;
INSERT INTO TARGET.result_sources select * from TARGET.result_sources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_sources;
INSERT INTO TARGET.result_topics select * from TARGET.result_topics orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_topics;
INSERT INTO TARGET.result_fos select * from TARGET.result_fos orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
create view TARGET.foo1 as select * from TARGET.result_result rr where rr.source in (select id from TARGET.result_new);
create view TARGET.foo2 as select * from TARGET.result_result rr where rr.target in (select id from TARGET.result_new);
INSERT INTO TARGET.result_result select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou;
drop view TARGET.foo1;
drop view TARGET.foo2;
ANALYZE TABLE TARGET.result_result COMPUTE STATISTICS;
-- indicators
-- Sprint 1 ----
INSERT INTO TARGET.indi_pub_green_oa select * from TARGET.indi_pub_green_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_green_oa COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_grey_lit select * from TARGET.indi_pub_grey_lit orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_grey_lit COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_doi_from_crossref select * from TARGET.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_doi_from_crossref COMPUTE STATISTICS;
-- Sprint 2 ----
INSERT INTO TARGET.indi_result_has_cc_licence select * from TARGET.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_result_has_cc_licence COMPUTE STATISTICS;
INSERT INTO TARGET.indi_result_has_cc_licence_url select * from TARGET.indi_result_has_cc_licence_url orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_result_has_cc_licence_url COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_has_abstract select * from TARGET.indi_pub_has_abstract orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_has_abstract COMPUTE STATISTICS;
INSERT INTO TARGET.indi_result_with_orcid select * from TARGET.indi_result_with_orcid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_result_with_orcid COMPUTE STATISTICS;
---- Sprint 3 ----
INSERT INTO TARGET.indi_funded_result_with_fundref select * from TARGET.indi_funded_result_with_fundref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_funded_result_with_fundref COMPUTE STATISTICS;
---- Sprint 4 ----
INSERT INTO TARGET.indi_pub_diamond select * from TARGET.indi_pub_diamond orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_diamond COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_in_transformative select * from TARGET.indi_pub_in_transformative orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_in_transformative COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_closed_other_open select * from TARGET.indi_pub_closed_other_open orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_closed_other_open COMPUTE STATISTICS;
---- Sprint 5 ----
INSERT INTO TARGET.indi_result_no_of_copies select * from TARGET.indi_result_no_of_copies orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_result_no_of_copies COMPUTE STATISTICS;
---- Sprint 6 ----
INSERT INTO TARGET.indi_pub_hybrid_oa_with_cc select * from TARGET.indi_pub_hybrid_oa_with_cc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_hybrid_oa_with_cc COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_downloads select * from TARGET.indi_pub_downloads orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
ANALYZE TABLE TARGET.indi_pub_downloads COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_downloads_datasource select * from TARGET.indi_pub_downloads_datasource orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
ANALYZE TABLE TARGET.indi_pub_downloads_datasource COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_downloads_year select * from TARGET.indi_pub_downloads_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
ANALYZE TABLE TARGET.indi_pub_downloads_year COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_downloads_datasource_year select * from TARGET.indi_pub_downloads_datasource_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
ANALYZE TABLE TARGET.indi_pub_downloads_datasource_year COMPUTE STATISTICS;
---- Sprint 7 ----
INSERT INTO TARGET.indi_pub_gold_oa select * from TARGET.indi_pub_gold_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_gold_oa COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_hybrid select * from TARGET.indi_pub_hybrid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_hybrid COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_has_preprint select * from TARGET.indi_pub_has_preprint orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_has_preprint COMPUTE STATISTICS;
INSERT INTO TARGET.indi_pub_in_subscribed select * from TARGET.indi_pub_in_subscribed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_pub_in_subscribed COMPUTE STATISTICS;
INSERT INTO TARGET.indi_result_with_pid select * from TARGET.indi_result_with_pid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
ANALYZE TABLE TARGET.indi_result_with_pid COMPUTE STATISTICS;
=======
COMPUTE STATS TARGET.indi_pub_green_oa;
INSERT INTO TARGET.indi_pub_grey_lit select * from TARGET.indi_pub_grey_lit orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_grey_lit;
INSERT INTO TARGET.indi_pub_doi_from_crossref select * from TARGET.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_doi_from_crossref;
-- Sprint 2 ----
INSERT INTO TARGET.indi_result_has_cc_licence select * from TARGET.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_has_cc_licence;
INSERT INTO TARGET.indi_result_has_cc_licence_url select * from TARGET.indi_result_has_cc_licence_url orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_has_cc_licence_url;
INSERT INTO TARGET.indi_pub_has_abstract select * from TARGET.indi_pub_has_abstract orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_has_abstract;
INSERT INTO TARGET.indi_result_with_orcid select * from TARGET.indi_result_with_orcid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_with_orcid;
---- Sprint 3 ----
INSERT INTO TARGET.indi_funded_result_with_fundref select * from TARGET.indi_funded_result_with_fundref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_funded_result_with_fundref;
---- Sprint 4 ----
INSERT INTO TARGET.indi_pub_diamond select * from TARGET.indi_pub_diamond orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_diamond;
INSERT INTO TARGET.indi_pub_in_transformative select * from TARGET.indi_pub_in_transformative orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_in_transformative;
INSERT INTO TARGET.indi_pub_closed_other_open select * from TARGET.indi_pub_closed_other_open orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_closed_other_open;
---- Sprint 5 ----
INSERT INTO TARGET.indi_result_no_of_copies select * from TARGET.indi_result_no_of_copies orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_no_of_copies;
---- Sprint 6 ----
INSERT INTO TARGET.indi_pub_hybrid_oa_with_cc select * from TARGET.indi_pub_hybrid_oa_with_cc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_hybrid_oa_with_cc;
INSERT INTO TARGET.indi_pub_downloads select * from TARGET.indi_pub_downloads orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads;
INSERT INTO TARGET.indi_pub_downloads_datasource select * from TARGET.indi_pub_downloads_datasource orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_datasource;
INSERT INTO TARGET.indi_pub_downloads_year select * from TARGET.indi_pub_downloads_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_year;
INSERT INTO TARGET.indi_pub_downloads_datasource_year select * from TARGET.indi_pub_downloads_datasource_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_datasource_year;
---- Sprint 7 ----
INSERT INTO TARGET.indi_pub_gold_oa select * from TARGET.indi_pub_gold_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_gold_oa;
INSERT INTO TARGET.indi_pub_hybrid select * from TARGET.indi_pub_hybrid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_hybrid;
INSERT INTO TARGET.indi_pub_has_preprint select * from TARGET.indi_pub_has_preprint orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_has_preprint;
INSERT INTO TARGET.indi_pub_in_subscribed select * from TARGET.indi_pub_in_subscribed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_in_subscribed;
INSERT INTO TARGET.indi_result_with_pid select * from TARGET.indi_result_with_pid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_with_pid;
--create table TARGET.indi_datasets_gold_oa stored as parquet as select * from SOURCE.indi_datasets_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_datasets_gold_oa;
--create table TARGET.indi_software_gold_oa stored as parquet as select * from SOURCE.indi_software_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_software_gold_oa;
DROP TABLE TARGET.result_new;

4
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/updateCache.sh
View File

@ -1,4 +0,0 @@
#!/usr/bin/env bash
curl --request GET $1/cache/updateCache
sleep 6h

129
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/workflow.xml
View File

@ -1,129 +0,0 @@
<workflow-app name="Monitor DB" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>stats_db_name</name>
<description>the target stats database name</description>
</property>
<property>
<name>stats_db_shadow_name</name>
<description>the name of the shadow schema</description>
</property>
<property>
<name>monitor_db_name</name>
<description>the target monitor db name</description>
</property>
<property>
<name>monitor_db_shadow_name</name>
<description>the name of the shadow monitor db</description>
</property>
<property>
<name>stats_tool_api_url</name>
<description>The url of the API of the stats tool. Is used to trigger the cache update.</description>
</property>
<property>
<name>hive_metastore_uris</name>
<description>hive server metastore URIs</description>
</property>
<property>
<name>hive_jdbc_url</name>
<description>hive server jdbc url</description>
</property>
<property>
<name>hive_timeout</name>
<description>the time period, in seconds, after which Hive fails a transaction if a Hive client has not sent a hearbeat. The default value is 300 seconds.</description>
</property>
<property>
<name>context_api_url</name>
<description>the base url of the context api (https://services.openaire.eu/openaire)</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
<property>
<name>hive.txn.timeout</name>
<value>${hive_timeout}</value>
</property>
</configuration>
</global>
<start to="Step1-createMonitorDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="Step1-createMonitorDB">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>monitor.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${monitor_db_name}</argument>
<argument>${wf:appPath()}/scripts/createMonitorDB.sql</argument>
<file>monitor.sh</file>
</shell>
<ok to="Step2-createMonitorDB-post"/>
<error to="Kill"/>
</action>
<action name="Step2-createMonitorDB-post">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>monitor-post.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${monitor_db_name}</argument>
<argument>${monitor_db_shadow_name}</argument>
<file>monitor-post.sh</file>
</shell>
<ok to="Step3-copyDataToImpalaCluster"/>
<error to="Kill"/>
</action>
<action name="Step3-copyDataToImpalaCluster">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>copyDataToImpalaCluster.sh</exec>
<argument>${monitor_db_name}</argument>
<argument>${hadoop_user_name}</argument>
<file>copyDataToImpalaCluster.sh</file>
</shell>
<ok to="Step4-finalizeImpalaCluster"/>
<error to="Kill"/>
</action>
<action name="Step4-finalizeImpalaCluster">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>finalizeImpalaCluster.sh</exec>
<argument>${monitor_db_name}</argument>
<argument>${monitor_db_shadow_name}</argument>
<file>finalizeImpalaCluster.sh</file>
</shell>
<ok to="Step5-updateCache"/>
<error to="Kill"/>
</action>
<action name="Step5-updateCache">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>updateCache.sh</exec>
<argument>${stats_tool_api_url}</argument>
<file>updateCache.sh</file>
</shell>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>