sabeel
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

added java doc

This commit is contained in:
Miriam Baglioni 2020-12-01 18:36:29 +01:00
parent 3d62d99d5d
commit 888175baf7
6 changed files with 24 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/BipDeserialize.java
View File

@ -6,6 +6,11 @@ import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
/**
* Class that maps the model of the bipFinder! input data.
* Only needed for deserialization purposes
*/
public class BipDeserialize extends HashMap<String, List<Score>> implements Serializable {
public BipDeserialize() {

8
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/BipScore.java
View File

@ -4,9 +4,13 @@ package eu.dnetlib.dhp.actionmanager.bipfinder;
import java.io.Serializable;
import java.util.List;
/**
* Rewriting of the bipFinder input data by extracting the identifier of the result (doi)
*/
public class BipScore implements Serializable {
private String id;
private List<Score> scoreList;
private String id; //doi
private List<Score> scoreList; //unit as given in the inputfile
public String getId() {
return id;

8
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/CollectAndSave.java
View File

@ -10,11 +10,7 @@ import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -25,6 +21,10 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Result;
/**
* Just collects all the atomic actions produced for the different results and saves them in
* outputpath for the ActionSet
*/
public class CollectAndSave implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CollectAndSave.class);

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/PreparedResult.java
View File

@ -3,6 +3,9 @@ package eu.dnetlib.dhp.actionmanager.bipfinder;
import java.io.Serializable;
/**
* Subset of the information of the generic results that are needed to create the atomic action
*/
public class PreparedResult implements Serializable {
private String id; // openaire id
private String value; // doi

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/Score.java
View File

@ -4,6 +4,9 @@ package eu.dnetlib.dhp.actionmanager.bipfinder;
import java.io.Serializable;
import java.util.List;
/**
* represents the score in the input file
*/
public class Score implements Serializable {
private String id;

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/SparkAtomicActionScoreJob.java
View File

@ -8,20 +8,16 @@ import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.hdfs.qjournal.protocol.QJournalProtocolProtos;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -35,6 +31,9 @@ import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import scala.Tuple2;
/**
* created the Atomic Action for each tipe of results
*/
public class SparkAtomicActionScoreJob implements Serializable {
private static String DOI = "doi";