forked from D-Net/dnet-hadoop
Historical Snapshots Workflow
Create historical snapshots db with parameters: hist_db_name=openaire_beta_historical_snapshots_xxx hist_db_name_prev=openaire_beta_historical_snapshots_xxx (previous run of wf) stats_db_name=openaire_beta_stats_xxx stats_irish_db_name=openaire_beta_stats_monitor_ie_xxx monitor_db_name=openaire_beta_stats_monitor_xxx monitor_db_prod_name=openaire_beta_stats_monitor monitor_irish_db_name=openaire_beta_stats_monitor_ie_xxx monitor_irish_db_prod_name=openaire_beta_stats_monitor_ie hist_db_prod_name=openaire_beta_historical_snapshots hist_db_shadow_name=openaire_beta_historical_snapshots_shadow hist_date=122023 hive_timeout=150000 hadoop_user_name=xxx resumeFrom=CreateDB
This commit is contained in:
dimitrispie
parent
ffdd03d2f4
commit
75bfde043c
|
|
@ -0,0 +1,32 @@
|
||||||
|
<?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-stats-hist-snaps</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>
|
||||||
|
|
@ -0,0 +1,30 @@
|
||||||
|
<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=22166291558;spark.yarn.executor.memoryOverhead=3225;spark.driver.memory=15596411699;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>
|
||||||
|
</configuration>
|
||||||
|
|
@ -0,0 +1,71 @@
|
||||||
|
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=$2
|
||||||
|
|
||||||
|
function copydb() {
|
||||||
|
|
||||||
|
|
||||||
|
db=$1
|
||||||
|
FILE=("hive_wf_tmp_"$RANDOM)
|
||||||
|
hdfs dfs -mkdir hdfs://impala-cluster-mn1.openaire.eu:8020/tmp/$FILE/
|
||||||
|
|
||||||
|
# change ownership to impala
|
||||||
|
# hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -chmod -R 777 /tmp/$FILE/${db}.db
|
||||||
|
hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -chmod -R 777 /tmp/$FILE/
|
||||||
|
|
||||||
|
|
||||||
|
# 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/$FILE/
|
||||||
|
|
||||||
|
hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -chmod -R 777 /tmp/$FILE/${db}.db
|
||||||
|
|
||||||
|
# drop tables from db
|
||||||
|
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 "drop table $i;"`;
|
||||||
|
done
|
||||||
|
|
||||||
|
# drop views from db
|
||||||
|
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 "drop view $i;"`;
|
||||||
|
done
|
||||||
|
|
||||||
|
# delete the database
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop database if exists ${db} cascade";
|
||||||
|
|
||||||
|
# create the databases
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create database ${db}";
|
||||||
|
|
||||||
|
impala-shell -q "INVALIDATE METADATA"
|
||||||
|
echo "creating schema for ${db}"
|
||||||
|
for (( k = 0; k < 5; k ++ )); do
|
||||||
|
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 --user $HADOOP_USER_NAME -i impala-cluster-dn1.openaire.eu -c -f -
|
||||||
|
done
|
||||||
|
|
||||||
|
# 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 ${db} -q "load data inpath '/tmp/$FILE/${db}.db/$i' into table $i";
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -d ${db} -q "compute stats $i";
|
||||||
|
done
|
||||||
|
|
||||||
|
# deleting the remaining directory from hdfs
|
||||||
|
hdfs dfs -conf /etc/impala_cluster/hdfs-site.xml -rm -R /tmp/$FILE/${db}.db
|
||||||
|
}
|
||||||
|
|
||||||
|
MONITOR_DB=$1
|
||||||
|
#HADOOP_USER_NAME=$2
|
||||||
|
copydb $MONITOR_DB
|
||||||
|
|
||||||
|
|
@ -0,0 +1,43 @@
|
||||||
|
export PYTHON_EGG_CACHE=/home/$(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
|
||||||
|
|
||||||
|
SOURCE=$1
|
||||||
|
PRODUCTION=$2
|
||||||
|
SHADOW=$3
|
||||||
|
MONITOR=$4
|
||||||
|
MONITOR_PROD=$5
|
||||||
|
MONITOR_IRISH_PROD=$6
|
||||||
|
MONITOR_IRISH=$7
|
||||||
|
|
||||||
|
|
||||||
|
echo ${SOURCE}
|
||||||
|
echo ${PRODUCTION}
|
||||||
|
|
||||||
|
#echo "Updating ${PRODUCTION} monitor database old cluster"
|
||||||
|
#impala-shell -q "create database if not exists ${PRODUCTION}"
|
||||||
|
#impala-shell -d ${PRODUCTION} -q "show tables" --delimited | sed "s/^/drop view if exists ${PRODUCTION}./" | sed "s/$/;/" | impala-shell -c -f -
|
||||||
|
#impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${PRODUCTION}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -c -f -
|
||||||
|
|
||||||
|
echo "Updating ${PRODUCTION} historical snapshots database"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create database if not exists ${PRODUCTION}"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -d ${PRODUCTION} -q "show tables" --delimited | sed "s/^/drop view if exists ${PRODUCTION}./" | sed "s/$/;/" | impala-shell -i impala-cluster-dn1.openaire.eu -c -f -
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${PRODUCTION}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -i impala-cluster-dn1.openaire.eu -c -f -
|
||||||
|
echo "Production monitor db ready!"
|
||||||
|
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop view ${MONITOR_PROD}.historical_snapshots"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop view ${MONITOR_PROD}.historical_snapshots_fos"
|
||||||
|
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create view ${MONITOR_PROD}.historical_snapshots as select * from ${SOURCE}.historical_snapshots"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create view ${MONITOR_PROD}.historical_snapshots_fos as select * from ${SOURCE}.historical_snapshots_fos"
|
||||||
|
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop view ${MONITOR_IRISH_PROD}.historical_snapshots_irish"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "drop view ${MONITOR_IRISH_PROD}.historical_snapshots_irish_fos"
|
||||||
|
|
||||||
|
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create view ${MONITOR_IRISH_PROD}.historical_snapshots_irish as select * from ${SOURCE}.historical_snapshots_irish"
|
||||||
|
impala-shell -i impala-cluster-dn1.openaire.eu -q "create view ${MONITOR_IRISH_PROD}.historical_snapshots_irish_fos as select * from ${SOURCE}.historical_snapshots_irish"
|
||||||
|
|
@ -0,0 +1,27 @@
|
||||||
|
export PYTHON_EGG_CACHE=/home/$(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 SHADOW=$3
|
||||||
|
export SCRIPT_PATH=$4
|
||||||
|
|
||||||
|
|
||||||
|
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 " $4
|
||||||
|
hdfs dfs -copyToLocal $4
|
||||||
|
|
||||||
|
#update Monitor DB IRISH
|
||||||
|
#cat CreateDB.sql | sed "s/SOURCE/$1/g" | sed "s/TARGET/$2/g1" | sed "s/GRAPHDB/$3/g1" > foo
|
||||||
|
cat buildIrishMonitorDB.sql | sed "s/SOURCE/$1/g" | sed "s/TARGET/$2/g1" > foo
|
||||||
|
hive $HIVE_OPTS -f foo
|
||||||
|
|
||||||
|
echo "Hive shell finished"
|
||||||
|
|
||||||
|
|
@ -0,0 +1,82 @@
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_fos_tmp
|
||||||
|
SELECT * FROM ${hist_db_name_prev}.historical_snapshots_fos;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_fos_tmp
|
||||||
|
select
|
||||||
|
cast(${hist_date} as STRING),
|
||||||
|
count(distinct r.id),
|
||||||
|
r.type,
|
||||||
|
rf.lvl1,
|
||||||
|
rf.lvl2,
|
||||||
|
pf.publicly_funded,
|
||||||
|
r.access_mode,
|
||||||
|
r.gold,
|
||||||
|
r.green,
|
||||||
|
coalesce(gl.green_with_license,0),
|
||||||
|
h.is_hybrid,
|
||||||
|
b.is_bronze_oa,
|
||||||
|
d.in_diamond_journal,
|
||||||
|
t.is_transformative,
|
||||||
|
pr.refereed
|
||||||
|
from ${stats_db_name}.result r
|
||||||
|
left outer join ${stats_db_name}.result_fos rf on rf.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_publicly_funded pf on pf.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_green_with_license gl on gl.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_bronze_oa b on b.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_diamond d on d.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_in_transformative t on t.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_hybrid h on h.id=r.id
|
||||||
|
left outer join ${stats_db_name}.result_refereed pr on pr.id=r.id
|
||||||
|
group by r.green, r.gold, r.access_mode, r.type, rf.lvl1,rf.lvl2, pf.publicly_funded,r.green, gl.green_with_license,b.is_bronze_oa,d.in_diamond_journal,t.is_transformative,h.is_hybrid,pr.refereed;
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_fos purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_fos STORED AS PARQUET AS
|
||||||
|
SELECT * FROM ${hist_db_name}.historical_snapshots_fos_tmp;
|
||||||
|
|
||||||
|
drop table if exists ${monitor_db_name}.historical_snapshots_fos purge;
|
||||||
|
|
||||||
|
create table ${monitor_db_name}.historical_snapshots_fos stored as parquet
|
||||||
|
as select * from ${hist_db_name}.historical_snapshots_fos;
|
||||||
|
|
||||||
|
drop table ${hist_db_name}.historical_snapshots_fos_tmp purge;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_tmp as
|
||||||
|
SELECT * FROM ${hist_db_name_prev}.historical_snapshots;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_tmp
|
||||||
|
select
|
||||||
|
cast(${hist_date} as STRING),
|
||||||
|
count(distinct r.id),
|
||||||
|
r.type,
|
||||||
|
pf.publicly_funded,
|
||||||
|
r.access_mode,
|
||||||
|
r.gold,
|
||||||
|
r.green,
|
||||||
|
coalesce(gl.green_with_license,0),
|
||||||
|
h.is_hybrid,
|
||||||
|
b.is_bronze_oa,
|
||||||
|
d.in_diamond_journal,
|
||||||
|
t.is_transformative,
|
||||||
|
pr.refereed
|
||||||
|
from ${stats_db_name}.result r
|
||||||
|
left outer join ${stats_db_name}.indi_pub_publicly_funded pf on pf.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_green_with_license gl on gl.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_bronze_oa b on b.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_diamond d on d.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_in_transformative t on t.id=r.id
|
||||||
|
left outer join ${stats_db_name}.indi_pub_hybrid h on h.id=r.id
|
||||||
|
left outer join ${stats_db_name}.result_refereed pr on pr.id=r.id
|
||||||
|
group by r.green, r.gold, r.access_mode, r.type, pf.publicly_funded,r.green, gl.green_with_license,b.is_bronze_oa,d.in_diamond_journal,t.is_transformative,h.is_hybrid,pr.refereed;
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots STORED AS PARQUET AS
|
||||||
|
SELECT * FROM ${hist_db_name}.historical_snapshots_tmp;
|
||||||
|
|
||||||
|
drop table if exists ${monitor_db_name}.historical_snapshots purge;
|
||||||
|
|
||||||
|
create table ${monitor_db_name}.historical_snapshots stored as parquet
|
||||||
|
as select * from ${hist_db_name}.historical_snapshots;
|
||||||
|
|
||||||
|
drop table ${hist_db_name}.historical_snapshots_tmp purge;
|
||||||
|
|
@ -0,0 +1,91 @@
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_fos_irish_tmp
|
||||||
|
SELECT * FROM ${hist_db_name_prev}.historical_snapshots_irish_fos;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_fos_irish_tmp
|
||||||
|
select
|
||||||
|
cast(${hist_date} as STRING),
|
||||||
|
count(distinct r.id),
|
||||||
|
r.type,
|
||||||
|
rf.lvl1,
|
||||||
|
rf.lvl2,
|
||||||
|
pf.publicly_funded,
|
||||||
|
r.access_mode,
|
||||||
|
r.gold,
|
||||||
|
r.green,
|
||||||
|
coalesce(gl.green_with_license,0),
|
||||||
|
h.is_hybrid,
|
||||||
|
b.is_bronze_oa,
|
||||||
|
d.in_diamond_journal,
|
||||||
|
t.is_transformative,
|
||||||
|
pr.refereed
|
||||||
|
from ${stats_irish_db_name}.result r
|
||||||
|
left outer join ${stats_irish_db_name}.result_fos rf on rf.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_publicly_funded pf on pf.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_green_with_license gl on gl.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_bronze_oa b on b.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_diamond d on d.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_in_transformative t on t.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_hybrid h on h.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.result_refereed pr on pr.id=r.id
|
||||||
|
group by r.green, r.gold, r.access_mode, r.type, rf.lvl1,rf.lvl2, pf.publicly_funded,r.green, gl.green_with_license,b.is_bronze_oa,d.in_diamond_journal,t.is_transformative,h.is_hybrid,pr.refereed;
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_irish_fos purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_irish_fos STORED AS PARQUET AS
|
||||||
|
SELECT * FROM ${hist_db_name}.historical_snapshots_fos_irish_tmp;
|
||||||
|
|
||||||
|
drop table if exists ${monitor_irish_db_name}.historical_snapshots_irish_fos purge;
|
||||||
|
|
||||||
|
create table ${monitor_irish_db_name}.historical_snapshots_irish_fos stored as parquet
|
||||||
|
as select * from ${hist_db_name}.historical_snapshots_irish_fos;
|
||||||
|
|
||||||
|
drop table ${hist_db_name}.historical_snapshots_fos_irish_tmp purge;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_irish_tmp
|
||||||
|
SELECT * FROM ${hist_db_name_prev}.historical_snapshots_irish;
|
||||||
|
|
||||||
|
INSERT INTO ${hist_db_name}.historical_snapshots_irish_tmp
|
||||||
|
select
|
||||||
|
cast(${hist_date} as STRING),
|
||||||
|
count(distinct r.id),
|
||||||
|
r.type,
|
||||||
|
pf.publicly_funded,
|
||||||
|
r.access_mode,
|
||||||
|
r.gold,
|
||||||
|
r.green,
|
||||||
|
coalesce(gl.green_with_license,0),
|
||||||
|
h.is_hybrid,
|
||||||
|
b.is_bronze_oa,
|
||||||
|
d.in_diamond_journal,
|
||||||
|
t.is_transformative,
|
||||||
|
pr.refereed
|
||||||
|
from ${stats_irish_db_name}.result r
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_publicly_funded pf on pf.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_green_with_license gl on gl.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_bronze_oa b on b.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_diamond d on d.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_in_transformative t on t.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.indi_pub_hybrid h on h.id=r.id
|
||||||
|
left outer join ${stats_irish_db_name}.result_refereed pr on pr.id=r.id
|
||||||
|
group by r.green, r.gold, r.access_mode, r.type, pf.publicly_funded,r.green, gl.green_with_license,b.is_bronze_oa,d.in_diamond_journal,t.is_transformative,h.is_hybrid,pr.refereed;
|
||||||
|
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_irish purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_irish STORED AS PARQUET AS
|
||||||
|
SELECT * FROM ${hist_db_name}.historical_snapshots_irish_tmp;
|
||||||
|
|
||||||
|
drop table if exists ${monitor_irish_db_name}.historical_snapshots_irish purge;
|
||||||
|
|
||||||
|
create table ${monitor_irish_db_name}.historical_snapshots_irish stored as parquet
|
||||||
|
as select * from ${hist_db_name}.historical_snapshots_irish;
|
||||||
|
|
||||||
|
drop table ${hist_db_name}.historical_snapshots_irish_tmp purge;
|
||||||
|
|
||||||
|
|
||||||
|
drop table if exists ${monitor_irish_db_name}.historical_snapshots_irish_fos purge;
|
||||||
|
|
||||||
|
create table ${monitor_irish_db_name}.historical_snapshots_irish_fos stored as parquet
|
||||||
|
as select * from ${hist_db_name}.historical_snapshots_irish_fos;
|
||||||
|
|
||||||
|
drop table ${hist_db_name}.historical_snapshots_fos_irish_tmp purge;
|
||||||
|
|
@ -0,0 +1,92 @@
|
||||||
|
--------------------------------------------------------------
|
||||||
|
--------------------------------------------------------------
|
||||||
|
-- Historical Snapshots database creation
|
||||||
|
--------------------------------------------------------------
|
||||||
|
--------------------------------------------------------------
|
||||||
|
|
||||||
|
DROP database IF EXISTS ${hist_db_name} CASCADE;
|
||||||
|
CREATE database ${hist_db_name};
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_fos_tmp purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_fos_tmp
|
||||||
|
(
|
||||||
|
hist_date STRING,
|
||||||
|
total INT,
|
||||||
|
type STRING,
|
||||||
|
lvl1 STRING,
|
||||||
|
lvl2 STRING,
|
||||||
|
publicly_funded INT,
|
||||||
|
accessrights STRING,
|
||||||
|
gold INT,
|
||||||
|
green INT,
|
||||||
|
green_with_license INT,
|
||||||
|
hybrid INT,
|
||||||
|
bronze INT,
|
||||||
|
diamond INT,
|
||||||
|
transformative INT,
|
||||||
|
peer_reviewed STRING
|
||||||
|
)
|
||||||
|
CLUSTERED BY (hist_date) INTO 100 buckets stored as orc tblproperties ('transactional' = 'true');
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_fos_irish_tmp purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_fos_irish_tmp
|
||||||
|
(
|
||||||
|
hist_date STRING,
|
||||||
|
total INT,
|
||||||
|
type STRING,
|
||||||
|
lvl1 STRING,
|
||||||
|
lvl2 STRING,
|
||||||
|
publicly_funded INT,
|
||||||
|
accessrights STRING,
|
||||||
|
gold INT,
|
||||||
|
green INT,
|
||||||
|
green_with_license INT,
|
||||||
|
hybrid INT,
|
||||||
|
bronze INT,
|
||||||
|
diamond INT,
|
||||||
|
transformative INT,
|
||||||
|
peer_reviewed STRING
|
||||||
|
)
|
||||||
|
CLUSTERED BY (hist_date) INTO 100 buckets stored as orc tblproperties ('transactional' = 'true');
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_tmp purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_tmp
|
||||||
|
(
|
||||||
|
hist_date STRING,
|
||||||
|
total INT,
|
||||||
|
type STRING,
|
||||||
|
publicly_funded INT,
|
||||||
|
accessrights STRING,
|
||||||
|
gold INT,
|
||||||
|
green INT,
|
||||||
|
green_with_license INT,
|
||||||
|
hybrid INT,
|
||||||
|
bronze INT,
|
||||||
|
diamond INT,
|
||||||
|
transformative INT,
|
||||||
|
peer_reviewed STRING
|
||||||
|
)
|
||||||
|
CLUSTERED BY (hist_date) INTO 100 buckets stored as orc tblproperties ('transactional' = 'true');
|
||||||
|
|
||||||
|
drop table if exists ${hist_db_name}.historical_snapshots_irish_tmp purge;
|
||||||
|
|
||||||
|
CREATE TABLE ${hist_db_name}.historical_snapshots_irish_tmp
|
||||||
|
(
|
||||||
|
hist_date STRING,
|
||||||
|
total INT,
|
||||||
|
type STRING,
|
||||||
|
publicly_funded INT,
|
||||||
|
accessrights STRING,
|
||||||
|
gold INT,
|
||||||
|
green INT,
|
||||||
|
green_with_license INT,
|
||||||
|
hybrid INT,
|
||||||
|
bronze INT,
|
||||||
|
diamond INT,
|
||||||
|
transformative INT,
|
||||||
|
peer_reviewed STRING
|
||||||
|
)
|
||||||
|
CLUSTERED BY (hist_date) INTO 100 buckets stored as orc tblproperties ('transactional' = 'true');
|
||||||
|
|
@ -0,0 +1,159 @@
|
||||||
|
<workflow-app name="Stats Hist Snapshots" xmlns="uri:oozie:workflow:0.5">
|
||||||
|
<parameters>
|
||||||
|
<property>
|
||||||
|
<name>hist_db_name</name>
|
||||||
|
<description>the target hist database name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hist_db_name_prev</name>
|
||||||
|
<description>the hist database name of previous_month</description>
|
||||||
|
</property>
|
||||||
|
|
||||||
|
<property>
|
||||||
|
<name>stats_db_name</name>
|
||||||
|
<description>the stats db name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>stats_irish_db_name</name>
|
||||||
|
<description>the stats irish db name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>monitor_db_name</name>
|
||||||
|
<description>the monitor db name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>monitor_irish_db_name</name>
|
||||||
|
<description>the irish monitor db name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hist_db_prod_name</name>
|
||||||
|
<description>the production db</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hist_db_shadow_name</name>
|
||||||
|
<description>the production shadow db</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hist_date</name>
|
||||||
|
<description>the snaps date</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>hadoop_user_name</name>
|
||||||
|
<description>user name of the wf owner</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>${hive_timeout}</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>mapred.job.queue.name</name>
|
||||||
|
<value>analytics</value>
|
||||||
|
</property>
|
||||||
|
</configuration>
|
||||||
|
</global>
|
||||||
|
|
||||||
|
<start to="resume_from"/>
|
||||||
|
<decision name="resume_from">
|
||||||
|
<switch>
|
||||||
|
<case to="CreateDB">${wf:conf('resumeFrom') eq 'CreateDB'}</case>
|
||||||
|
<case to="BuildHistSnaps">${wf:conf('resumeFrom') eq 'BuildHistSnaps'}</case>
|
||||||
|
<case to="BuildHistSnapsIrish">${wf:conf('resumeFrom') eq 'BuildHistSnapsIrish'}</case>
|
||||||
|
<case to="Step2-copyDataToImpalaCluster">${wf:conf('resumeFrom') eq 'Step2-copyDataToImpalaCluster'}</case>
|
||||||
|
<case to="Step3-finalizeImpalaCluster">${wf:conf('resumeFrom') eq 'Step3-finalizeImpalaCluster'}</case>
|
||||||
|
<default to="BuildHistSnaps"/>
|
||||||
|
</switch>
|
||||||
|
</decision>
|
||||||
|
|
||||||
|
<kill name="Kill">
|
||||||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||||
|
</kill>
|
||||||
|
|
||||||
|
<action name="CreateDB">
|
||||||
|
<hive2 xmlns="uri:oozie:hive2-action:0.1">
|
||||||
|
<jdbc-url>${hive_jdbc_url}</jdbc-url>
|
||||||
|
<script>scripts/CreateDB.sql</script>
|
||||||
|
<param>hist_db_name=${hist_db_name}</param>
|
||||||
|
</hive2>
|
||||||
|
<ok to="BuildHistSnaps"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<action name="BuildHistSnaps">
|
||||||
|
<hive2 xmlns="uri:oozie:hive2-action:0.1">
|
||||||
|
<jdbc-url>${hive_jdbc_url}</jdbc-url>
|
||||||
|
<script>scripts/BuildHistSnapsAll.sql</script>
|
||||||
|
<param>hist_db_name=${hist_db_name}</param>
|
||||||
|
<param>hist_db_name_prev=${hist_db_name_prev}</param>
|
||||||
|
<param>stats_db_name=${stats_db_name}</param>
|
||||||
|
<param>monitor_db_name=${monitor_db_name}</param>
|
||||||
|
<param>hist_date=${hist_date}</param>
|
||||||
|
</hive2>
|
||||||
|
<ok to="BuildHistSnapsIrish"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<action name="BuildHistSnapsIrish">
|
||||||
|
<hive2 xmlns="uri:oozie:hive2-action:0.1">
|
||||||
|
<jdbc-url>${hive_jdbc_url}</jdbc-url>
|
||||||
|
<script>scripts/BuildHistSnapsIrish.sql</script>
|
||||||
|
<param>hist_db_name=${hist_db_name}</param>
|
||||||
|
<param>hist_db_name_prev=${hist_db_name_prev}</param>
|
||||||
|
<param>stats_irish_db_name=${stats_irish_db_name}</param>
|
||||||
|
<param>monitor_irish_db_name=${monitor_irish_db_name}</param>
|
||||||
|
<param>hist_date=${hist_date}</param>
|
||||||
|
</hive2>
|
||||||
|
<ok to="Step2-copyDataToImpalaCluster"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
<action name="Step2-copyDataToImpalaCluster">
|
||||||
|
<shell xmlns="uri:oozie:shell-action:0.1">
|
||||||
|
<job-tracker>${jobTracker}</job-tracker>
|
||||||
|
<name-node>${nameNode}</name-node>
|
||||||
|
<exec>copyDataToImpalaCluster.sh</exec>
|
||||||
|
<argument>${hist_db_name}</argument>
|
||||||
|
<argument>${hadoop_user_name}</argument>
|
||||||
|
<file>copyDataToImpalaCluster.sh</file>
|
||||||
|
</shell>
|
||||||
|
<ok to="Step3-finalizeImpalaCluster"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
<action name="Step3-finalizeImpalaCluster">
|
||||||
|
<shell xmlns="uri:oozie:shell-action:0.1">
|
||||||
|
<job-tracker>${jobTracker}</job-tracker>
|
||||||
|
<name-node>${nameNode}</name-node>
|
||||||
|
<exec>finalizeImpalaCluster.sh</exec>
|
||||||
|
<argument>${hist_db_name}</argument>
|
||||||
|
<argument>${hist_db_prod_name}</argument>
|
||||||
|
<argument>${monitor_db_name}</argument>
|
||||||
|
<argument>${monitor_db_name}</argument>
|
||||||
|
<argument>${monitor_irish_db_name}</argument>
|
||||||
|
<file>finalizeImpalaCluster.sh</file>
|
||||||
|
</shell>
|
||||||
|
<ok to="End"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<end name="End"/>
|
||||||
|
</workflow-app>
|
||||||
Loading…
Reference in New Issue