antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

produces AtomicActions instead of Projects

This commit is contained in:
Miriam Baglioni 2020-05-22 15:26:57 +02:00
parent eae12a6586
commit 473c6d3a23
1 changed files with 35 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/SparkAtomicActionJob.java
View File

@ -9,12 +9,17 @@ import java.util.HashMap;
import java.util.Optional;
import java.util.function.Consumer;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.rdd.SequenceFileRDDFunctions;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
@ -28,16 +33,11 @@ import eu.dnetlib.dhp.actionmanager.project.csvutils.CSVProgramme;
import eu.dnetlib.dhp.actionmanager.project.csvutils.CSVProject;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Programme;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.utils.DHPUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.SequenceFile;
import org.apache.spark.rdd.SequenceFileRDDFunctions;
import org.apache.hadoop.io.Text;
import scala.Function1;
import scala.Tuple2;
import scala.runtime.BoxedUnit;
@ -75,8 +75,6 @@ public class SparkAtomicActionJob {
final String programmePath = parser.get("programmePath");
log.info("programmePath {}: ", programmePath);
final String nameNode = parser.get("hdfsNameNode");
SparkConf conf = new SparkConf();
runWithSparkSession(
@ -88,8 +86,7 @@ public class SparkAtomicActionJob {
spark,
projectPath,
programmePath,
outputPath,
nameNode);
outputPath);
});
}
@ -99,8 +96,7 @@ public class SparkAtomicActionJob {
private static void getAtomicActions(SparkSession spark, String projectPatH,
String programmePath,
String outputPath,
String nameNode) throws Exception{
String outputPath) {
Dataset<CSVProject> project = readPath(spark, projectPatH, CSVProject.class);
Dataset<CSVProgramme> programme = readPath(spark, programmePath, CSVProgramme.class);
@ -121,15 +117,18 @@ public class SparkAtomicActionJob {
pm.setCode(csvProject.getProgramme());
pm.setDescription(csvProgramme.get().getShortTitle());
p.setProgramme(Arrays.asList(pm));
return new AtomicAction<>(Project.class, p);
return p;
}
return null;
}, Encoders.bean(AtomicAction.class))
.filter(aa -> !(aa == null))
}, Encoders.bean(Project.class))
.filter(p -> !(p == null))
.toJavaRDD()
.mapToPair(aa->new Tuple2<>(aa.getClazz().getCanonicalName(), OBJECT_MAPPER.writeValueAsString(aa)))
.saveAsHadoopFile(outputPath, Text.class, Text.class, null);
.map(p -> new AtomicAction(Project.class, p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
}