D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

no use of IsLookUp. The query is done once and its result stored on HDFS. The path to the result is given instead of the isLookUpUrl

This commit is contained in:
Miriam Baglioni 2020-08-07 17:34:40 +02:00
parent ae1b7fbfdb
commit d52b0e1797
1 changed files with 2 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/community/SparkSplitForCommunity.java
View File

@ -1,29 +1,12 @@
package eu.dnetlib.dhp.oa.graph.dump.community; package eu.dnetlib.dhp.oa.graph.dump.community;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.Optional; import java.util.Optional;
import java.util.Set;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import com.google.gson.Gson;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.QueryInformationSystem;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
public class SparkSplitForCommunity implements Serializable { public class SparkSplitForCommunity implements Serializable {
@ -51,23 +34,11 @@ public class SparkSplitForCommunity implements Serializable {
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath); log.info("outputPath: {}", outputPath);
final String isLookUpUrl = parser.get("isLookUpUrl"); final String communityMapPath = parser.get("communityMapPath");
log.info("isLookUpUrl: {}", isLookUpUrl);
CommunitySplit split = new CommunitySplit(); CommunitySplit split = new CommunitySplit();
split.run(isSparkSessionManaged, inputPath, outputPath, communityMapPath);
CommunityMap communityMap;
QueryInformationSystem queryInformationSystem = new QueryInformationSystem();
queryInformationSystem.setIsLookUp(getIsLookUpService(isLookUpUrl));
communityMap = queryInformationSystem.getCommunityMap();
split.run(isSparkSessionManaged, inputPath, outputPath, communityMap);
}
public static ISLookUpService getIsLookUpService(String isLookUpUrl) {
return ISLookupClientFactory.getLookUpService(isLookUpUrl);
} }
} }