D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

master #59

Closed
claudio.atzori wants to merge 3221 commits from master into stable_ids
pull from: master
merge into: D-Net:stable_ids
Conversation 0 Commits 3221 Files Changed 2141 +2 -1
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 858931ccb6 - Show all commits

3
dhp-workflows/dhp-swh/src/main/java/eu/dnetlib/dhp/swh/PrepareSWHActionsets.java
View File

@ -11,6 +11,7 @@ import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
@ -81,7 +82,7 @@ public class PrepareSWHActionsets {
JavaPairRDD<Text, Text> softwareRDD = prepareActionsets(spark, inputPath, softwareInputPath);
softwareRDD
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
});
}