dimitris.pierrakos
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

code formatting

This commit is contained in:
Claudio Atzori 2022-01-19 12:30:52 +01:00
parent 44a937f4ed
commit 62f135262e
3 changed files with 37 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/DispatchEntitiesSparkJob.java
View File

@ -1,11 +1,11 @@
package eu.dnetlib.dhp.oa.merge;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.Objects;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
@ -17,10 +17,12 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.Objects;
import java.util.Optional;
import com.fasterxml.jackson.databind.ObjectMapper;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
public class DispatchEntitiesSparkJob {

42
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
View File

@ -1,17 +1,15 @@
package eu.dnetlib.dhp.oa.merge;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.jayway.jsonpath.Configuration;
import com.jayway.jsonpath.DocumentContext;
import com.jayway.jsonpath.JsonPath;
import com.jayway.jsonpath.Option;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
import java.io.IOException;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
@ -22,17 +20,21 @@ import org.apache.spark.sql.*;
import org.apache.spark.sql.expressions.Aggregator;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.jayway.jsonpath.Configuration;
import com.jayway.jsonpath.DocumentContext;
import com.jayway.jsonpath.JsonPath;
import com.jayway.jsonpath.Option;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
import java.io.IOException;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
/**
* Groups the graph content by entity identifier to ensure ID uniqueness
*/

3
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
View File

@ -68,7 +68,8 @@ public class OafMapperUtils {
}
private static boolean isFromDeletedAuthority(Result r) {
return r.getInstance()
return r
.getInstance()
.stream()
.map(i -> i.getCollectedfrom().getKey())
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId));