added possibility to copy the graph from hive
This commit is contained in:
parent
9dea4f30ca
commit
32d64dd7a1
|
@ -0,0 +1,92 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.oa.graph.dump;
|
||||||
|
|
||||||
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.util.ArrayList;
|
||||||
|
import java.util.List;
|
||||||
|
import java.util.Optional;
|
||||||
|
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.function.FilterFunction;
|
||||||
|
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||||
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
import org.apache.spark.sql.*;
|
||||||
|
import org.slf4j.Logger;
|
||||||
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
import scala.Tuple2;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 22/09/23
|
||||||
|
*/
|
||||||
|
public class SparkCopyGraph implements Serializable {
|
||||||
|
|
||||||
|
private static final Logger log = LoggerFactory.getLogger(SparkCopyGraph.class);
|
||||||
|
|
||||||
|
public static void main(String[] args) throws Exception {
|
||||||
|
|
||||||
|
String jsonConfiguration = IOUtils
|
||||||
|
.toString(
|
||||||
|
SparkCopyGraph.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/oa/graph/dump/copygraph_parameters.json"));
|
||||||
|
|
||||||
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||||
|
|
||||||
|
parser.parseArgument(args);
|
||||||
|
|
||||||
|
Boolean isSparkSessionManaged = Optional
|
||||||
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
|
||||||
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
|
final String hivePath = parser.get("hivePath");
|
||||||
|
log.info("hivePath: {}", hivePath);
|
||||||
|
|
||||||
|
final String outputPath = parser.get("outputPath");
|
||||||
|
log.info("outputPath: {}", outputPath);
|
||||||
|
|
||||||
|
SparkConf conf = new SparkConf();
|
||||||
|
|
||||||
|
runWithSparkSession(
|
||||||
|
conf,
|
||||||
|
isSparkSessionManaged,
|
||||||
|
spark ->
|
||||||
|
|
||||||
|
execCopy(
|
||||||
|
spark,
|
||||||
|
hivePath,
|
||||||
|
outputPath));
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void execCopy(SparkSession spark, String hivePath, String outputPath) {
|
||||||
|
|
||||||
|
ModelSupport.oafTypes.entrySet().parallelStream().forEach(entry -> {
|
||||||
|
String entityType = entry.getKey();
|
||||||
|
Class<?> clazz = entry.getValue();
|
||||||
|
// if (!entityType.equalsIgnoreCase("relation")) {
|
||||||
|
spark
|
||||||
|
.read()
|
||||||
|
.schema(Encoders.bean(clazz).schema())
|
||||||
|
.parquet(hivePath + "/" + entityType)
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Overwrite)
|
||||||
|
.option("compression", "gzip")
|
||||||
|
.json(outputPath + "/" + entityType);
|
||||||
|
|
||||||
|
});
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,30 @@
|
||||||
|
<configuration>
|
||||||
|
<property>
|
||||||
|
<name>jobTracker</name>
|
||||||
|
<value>yarnRM</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>nameNode</name>
|
||||||
|
<value>hdfs://nameservice1</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.use.system.libpath</name>
|
||||||
|
<value>true</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveMetastoreUris</name>
|
||||||
|
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveJdbcUrl</name>
|
||||||
|
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveDbName</name>
|
||||||
|
<value>openaire</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||||
|
<value>true</value>
|
||||||
|
</property>
|
||||||
|
</configuration>
|
|
@ -0,0 +1,110 @@
|
||||||
|
<workflow-app name="copy_graph_from_hive" xmlns="uri:oozie:workflow:0.5">
|
||||||
|
<parameters>
|
||||||
|
|
||||||
|
<property>
|
||||||
|
<name>outputPath</name>
|
||||||
|
<description>the output path</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hivePath</name>
|
||||||
|
<description>the country for which to produce the dump</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveDbName</name>
|
||||||
|
<description>the target hive database name</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveJdbcUrl</name>
|
||||||
|
<description>hive server jdbc url</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>hiveMetastoreUris</name>
|
||||||
|
<description>hive server metastore URIs</description>
|
||||||
|
</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>
|
||||||
|
</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>${oozieActionShareLibForSpark2}</value>
|
||||||
|
</property>
|
||||||
|
|
||||||
|
</configuration>
|
||||||
|
</global>
|
||||||
|
|
||||||
|
<start to="copy_graph" />
|
||||||
|
<!-- <start to="make_archive" />-->
|
||||||
|
<kill name="Kill">
|
||||||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||||
|
</kill>
|
||||||
|
<action name="copy_graph">
|
||||||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||||
|
<master>yarn</master>
|
||||||
|
<mode>cluster</mode>
|
||||||
|
<name>Copy graph</name>
|
||||||
|
<class>eu.dnetlib.dhp.oa.graph.dump.SparkCopyGraph</class>
|
||||||
|
<jar>dump-${projectVersion}.jar</jar>
|
||||||
|
<spark-opts>
|
||||||
|
--executor-memory=${sparkExecutorMemory}
|
||||||
|
--executor-cores=${sparkExecutorCores}
|
||||||
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||||
|
</spark-opts>
|
||||||
|
<arg>--hivePath</arg><arg>${hivePath}</arg>
|
||||||
|
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||||
|
</spark>
|
||||||
|
<ok to="End"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<end name="End" />
|
||||||
|
</workflow-app>
|
|
@ -0,0 +1,21 @@
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"paramName": "out",
|
||||||
|
"paramLongName": "outputPath",
|
||||||
|
"paramDescription": "the path used to store temporary output files",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"hp",
|
||||||
|
"paramLongName":"hivePath",
|
||||||
|
"paramDescription": "the name of the result table we are currently working on",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"issm",
|
||||||
|
"paramLongName":"isSparkSessionManaged",
|
||||||
|
"paramDescription": "the name of the result table we are currently working on",
|
||||||
|
"paramRequired": false
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
|
@ -175,6 +175,8 @@
|
||||||
<error to="Kill"/>
|
<error to="Kill"/>
|
||||||
</action>
|
</action>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
<decision name="choose_dump">
|
<decision name="choose_dump">
|
||||||
<switch>
|
<switch>
|
||||||
<case to="dump_funder">${wf:conf('dumpType') eq "funder"}</case>
|
<case to="dump_funder">${wf:conf('dumpType') eq "funder"}</case>
|
||||||
|
|
Loading…
Reference in New Issue