1
0
Fork 0

[Bypass Action Set] minor fix

This commit is contained in:
Miriam Baglioni 2021-11-12 10:18:01 +01:00
parent 935062edec
commit 716021546e
6 changed files with 28 additions and 30 deletions

View File

@ -45,7 +45,7 @@ public class PrepareBipFinder implements Serializable {
.toString( .toString(
PrepareBipFinder.class PrepareBipFinder.class
.getResourceAsStream( .getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip_prepare_parameters.json")); "/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -35,7 +35,7 @@ public class PrepareFOSSparkJob implements Serializable {
.toString( .toString(
PrepareFOSSparkJob.class PrepareFOSSparkJob.class
.getResourceAsStream( .getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/distribute_fos_parameters.json")); "/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -1,21 +0,0 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName":"out",
"paramLongName":"outputPath",
"paramDescription": "the output path",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
}
]

View File

@ -1,3 +1,4 @@
<workflow-app name="UnresolvedEntities" xmlns="uri:oozie:workflow:0.5"> <workflow-app name="UnresolvedEntities" xmlns="uri:oozie:workflow:0.5">
<parameters> <parameters>
<property> <property>
@ -49,6 +50,25 @@
</property> </property>
</parameters> </parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="prepareInfo"/> <start to="prepareInfo"/>
<kill name="Kill"> <kill name="Kill">
@ -79,7 +99,7 @@
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${bipScorePath}</arg> <arg>--sourcePath</arg><arg>${bipScorePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared/bip</arg> <arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
</spark> </spark>
<ok to="join"/> <ok to="join"/>
<error to="Kill"/> <error to="Kill"/>
@ -102,7 +122,7 @@
<master>yarn</master> <master>yarn</master>
<mode>cluster</mode> <mode>cluster</mode>
<name>Produces the unresolved from FOS!</name> <name>Produces the unresolved from FOS!</name>
<class>eu.dnetlib.dhp.actionmanager.bipfinder.SparkAtomicActionScoreJob</class> <class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareFOSSparkJob</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar> <jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
@ -115,8 +135,7 @@
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/input/fos</arg> <arg>--sourcePath</arg><arg>${workingDir}/input/fos</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared/fos</arg>
</spark> </spark>
<ok to="join"/> <ok to="join"/>
@ -132,7 +151,7 @@
<master>yarn</master> <master>yarn</master>
<mode>cluster</mode> <mode>cluster</mode>
<name>Saves the result produced for bip and fos by grouping results with the same id</name> <name>Saves the result produced for bip and fos by grouping results with the same id</name>
<class>eu.dnetlib.dhp.actionmanager.bipfinder.CollectAndSave</class> <class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.SparkSaveUnresolved</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar> <jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
@ -144,7 +163,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${workingDir}/prepared</arg> <arg>--sourcePath</arg><arg>${workingDir}/prepared</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg> <arg>--outputPath</arg><arg>${outputPath}</arg>
</spark> </spark>
<ok to="End"/> <ok to="End"/>

View File

@ -143,7 +143,7 @@ public class PrepareTest {
} }
@Test @Test
void getFOSFileTest() throws CollectorException, IOException, ClassNotFoundException { void getFOSFileTest() throws IOException, ClassNotFoundException {
final String sourcePath = getClass() final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/h2020_fos_sbs.csv") .getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/h2020_fos_sbs.csv")