przemyslaw.jacewicz
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

code formatting

This commit is contained in:
Claudio Atzori 2020-07-16 19:06:56 +02:00
parent db8b90a156
commit 1781609508
1 changed files with 94 additions and 90 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphSparkJob.java
View File

@ -1,11 +1,11 @@
package eu.dnetlib.dhp.oa.graph.merge;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
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.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
@ -16,13 +16,16 @@ import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import scala.Tuple2;
import java.util.Objects;
import java.util.Optional;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
/**
* Combines the content from two aggregator graph tables of the same type, entities (or relationships) with the same ids
* are picked preferring those from the BETA aggregator rather then from PROD. The identity of a relationship is defined
@ -88,7 +91,8 @@ public class MergeGraphSparkJob {
Dataset<Tuple2<String, B>> beta = readTableFromPath(spark, betaInputPath, b_clazz);
Dataset<Tuple2<String, P>> prod = readTableFromPath(spark, prodInputPath, p_clazz);
prod.joinWith(beta, prod.col("_1").equalTo(beta.col("_1")), "full_outer")
prod
.joinWith(beta, prod.col("_1").equalTo(beta.col("_1")), "full_outer")
.map((MapFunction<Tuple2<Tuple2<String, P>, Tuple2<String, B>>, P>) value -> {
Optional<P> p = Optional.ofNullable(value._1()).map(Tuple2::_2);
Optional<B> b = Optional.ofNullable(value._2()).map(Tuple2::_2);