forked from D-Net/dnet-hadoop
due to change in the input file the filtering step is no more needed
This commit is contained in:
parent
54f6e2f693
commit
e07c3ba089
|
@ -143,7 +143,6 @@ public class PrepareProgramme {
|
||||||
|
|
||||||
JavaRDD<CSVProgramme> h2020Programmes = programme
|
JavaRDD<CSVProgramme> h2020Programmes = programme
|
||||||
.toJavaRDD()
|
.toJavaRDD()
|
||||||
.filter(p -> p.getFrameworkProgramme().trim().equalsIgnoreCase("H2020"))
|
|
||||||
.mapToPair(csvProgramme -> new Tuple2<>(csvProgramme.getCode(), csvProgramme))
|
.mapToPair(csvProgramme -> new Tuple2<>(csvProgramme.getCode(), csvProgramme))
|
||||||
.reduceByKey((a, b) -> {
|
.reduceByKey((a, b) -> {
|
||||||
if (!a.getLanguage().equals("en")) {
|
if (!a.getLanguage().equals("en")) {
|
||||||
|
|
Loading…
Reference in New Issue