job execution now based on file last_update.txt on hdfs
parent
b2de598c1a
commit
465ce39f75
@ -0,0 +1,38 @@
|
||||
|
||||
package eu.dnetlib.doiboost.orcid.util;
|
||||
|
||||
import java.io.BufferedWriter;
|
||||
import java.io.IOException;
|
||||
import java.io.OutputStreamWriter;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FSDataInputStream;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
|
||||
public class HDFSUtil {
|
||||
|
||||
public static String readFromTextFile(String path) throws IOException {
|
||||
Configuration conf = new Configuration();
|
||||
FileSystem fileSystem = FileSystem.get(conf);
|
||||
FSDataInputStream inputStream = new FSDataInputStream(fileSystem.open(new Path(path)));
|
||||
return IOUtils.toString(inputStream, StandardCharsets.UTF_8.name());
|
||||
}
|
||||
|
||||
public static void writeToTextFile(String pathValue, String text) throws IOException {
|
||||
Configuration conf = new Configuration();
|
||||
FileSystem fileSystem = FileSystem.get(conf);
|
||||
Path path = new Path(pathValue);
|
||||
if (fileSystem.exists(path)) {
|
||||
fileSystem.delete(path, true);
|
||||
}
|
||||
FSDataOutputStream os = fileSystem.create(path);
|
||||
BufferedWriter br = new BufferedWriter(new OutputStreamWriter(os, "UTF-8"));
|
||||
br.write(text);
|
||||
br.close();
|
||||
fileSystem.close();
|
||||
}
|
||||
}
|
||||
@ -1,163 +0,0 @@
|
||||
<workflow-app name="update_orcid_datasets" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>spark2MaxExecutors</name>
|
||||
<value>50</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkDriverMemory</name>
|
||||
<description>memory for driver process</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<description>memory for individual executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<description>number of cores used by single executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozieActionShareLibForSpark2</name>
|
||||
<description>oozie action sharelib for spark 2.*</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2ExtraListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||||
<description>spark 2.* extra listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2SqlQueryExecutionListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||||
<description>spark 2.* sql query execution listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2YarnHistoryServerAddress</name>
|
||||
<description>spark 2.* yarn history server address</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2EventLogDir</name>
|
||||
<description>spark 2.* event log dir location</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>workingPath</name>
|
||||
<description>the working dir base path</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<global>
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="promoteOrcidAuthorsDataset"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="ResetWorkingPath">
|
||||
<fs>
|
||||
<delete path='${workingPath}/orcid_dataset/new_authors'/>
|
||||
<delete path='${workingPath}/orcid_dataset/new_works'/>
|
||||
</fs>
|
||||
<ok to="UpdateOrcidAuthors"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="UpdateOrcidAuthors">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn-cluster</master>
|
||||
<mode>cluster</mode>
|
||||
<name>UpdateOrcidAuthors</name>
|
||||
<class>eu.dnetlib.doiboost.orcid.SparkUpdateOrcidAuthors</class>
|
||||
<jar>dhp-doiboost-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--conf spark.dynamicAllocation.enabled=true
|
||||
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
</spark-opts>
|
||||
<arg>-w</arg><arg>${workingPath}/</arg>
|
||||
<arg>-n</arg><arg>${nameNode}</arg>
|
||||
<arg>-f</arg><arg>-</arg>
|
||||
<arg>-o</arg><arg>-</arg>
|
||||
<arg>-t</arg><arg>-</arg>
|
||||
</spark>
|
||||
<ok to="UpdateOrcidWorks"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="UpdateOrcidWorks">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn-cluster</master>
|
||||
<mode>cluster</mode>
|
||||
<name>UpdateOrcidWorks</name>
|
||||
<class>eu.dnetlib.doiboost.orcid.SparkUpdateOrcidWorks</class>
|
||||
<jar>dhp-doiboost-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--conf spark.dynamicAllocation.enabled=true
|
||||
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
</spark-opts>
|
||||
<arg>-w</arg><arg>${workingPath}/</arg>
|
||||
<arg>-n</arg><arg>${nameNode}</arg>
|
||||
<arg>-f</arg><arg>-</arg>
|
||||
<arg>-o</arg><arg>-</arg>
|
||||
<arg>-t</arg><arg>-</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="promoteOrcidAuthorsDataset">
|
||||
<distcp xmlns="uri:oozie:distcp-action:0.2">
|
||||
<prepare>
|
||||
<delete path="${workingPath}/orcid_dataset/authors"/>
|
||||
<mkdir path="${workingPath}/orcid_dataset/authors"/>
|
||||
</prepare>
|
||||
<arg>${workingPath}/orcid_dataset/new_authors/*</arg>
|
||||
<arg>${workingPath}/orcid_dataset/authors</arg>
|
||||
</distcp>
|
||||
<ok to="promoteOrcidWorksDataset"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="promoteOrcidWorksDataset">
|
||||
<distcp xmlns="uri:oozie:distcp-action:0.2">
|
||||
<prepare>
|
||||
<delete path="${workingPath}/orcid_dataset/works"/>
|
||||
<mkdir path="${workingPath}/orcid_dataset/works"/>
|
||||
</prepare>
|
||||
<arg>${workingPath}/orcid_dataset/new_works/*</arg>
|
||||
<arg>${workingPath}/orcid_dataset/works</arg>
|
||||
</distcp>
|
||||
<ok to="CleanWorkingPath"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="CleanWorkingPath">
|
||||
<fs>
|
||||
<delete path='${workingPath}/orcid_dataset/new_authors'/>
|
||||
<delete path='${workingPath}/orcid_dataset/new_works'/>
|
||||
</fs>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
||||
Loading…
Reference in New Issue