alessia.bardi
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

adding default parameters in code

This commit is contained in:
Miriam Baglioni 2020-02-17 16:30:52 +01:00
parent a5517eee35
commit 3a9d723655
2 changed files with 7 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
dhp-workflows/dhp-propagation/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java
View File

@ -42,30 +42,11 @@ public class SparkCountryPropagationJob {
directory.mkdirs();
}
List<String> whitelist = new ArrayList<>();
List<String> allowedtypes = new ArrayList<>();
//TODO: add as Job Parameters
List<String> whitelist = Arrays.asList("10|opendoar____::300891a62162b960cf02ce3827bb363c");
List<String> allowedtypes = Arrays.asList("pubsrepository::institutional");
// JavaPairRDD<String, TypedRow> results = getResults(sc, inputPath);
// sc.sequenceFile(inputPath + "/dataset", Text.class, Text.class)
// .map(item -> new ObjectMapper().readValue(item._2().toString(), Dataset.class))
// .map(oaf -> new TypedRow().setType("dataset").setDeleted(oaf.getDataInfo().getDeletedbyinference()).setOaf(oaf.toString()).setSourceId(oaf.getId()))
// .mapToPair(toPair())
// .union(sc.sequenceFile(inputPath + "/otherresearchproduct", Text.class, Text.class)
// .map(item -> new ObjectMapper().readValue(item._2().toString(), OtherResearchProduct.class))
// .map(oaf -> new TypedRow().setType("otherresearchproduct").setDeleted(oaf.getDataInfo().getDeletedbyinference()).setOaf(oaf.toString()).setSourceId(oaf.getId()))
// .mapToPair(toPair()))
// .union(sc.sequenceFile(inputPath + "/software", Text.class, Text.class)
// .map(item -> new ObjectMapper().readValue(item._2().toString(), Software.class))
// .map(oaf -> new TypedRow().setType("software").setDeleted(oaf.getDataInfo().getDeletedbyinference()).setOaf(oaf.toString()).setSourceId(oaf.getId()))
// .mapToPair(toPair()))
// .union(sc.sequenceFile(inputPath + "/publication", Text.class, Text.class)
// .map(item -> new ObjectMapper().readValue(item._2().toString(), Publication.class))
// .map(oaf -> new TypedRow().setType("publication").setDeleted(oaf.getDataInfo().getDeletedbyinference()).setOaf(oaf.toString()).setSourceId(oaf.getId()))
// .mapToPair(toPair()));
//
//
JavaPairRDD<String, TypedRow> organizations = sc.sequenceFile(inputPath + "/organization", Text.class, Text.class)
.map(item -> new ObjectMapper().readValue(item._2().toString(), Organization.class))
.filter(org -> !org.getDataInfo().getDeletedbyinference())

4
dhp-workflows/dhp-propagation/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java Normal file
View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.resulttoorganizationfrominstrepo;
public class SparkResultToOrganizationFromIstRepoJob {
}