[OC] compress the output actionset
This commit is contained in:
parent
774e874d18
commit
46034630cf
|
@ -10,6 +10,7 @@ import java.util.*;
|
|||
import org.apache.commons.cli.ParseException;
|
||||
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;
|
||||
|
@ -27,7 +28,6 @@ import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
|||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
|
@ -100,7 +100,7 @@ public class CreateActionSetSparkJob implements Serializable {
|
|||
|
||||
getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, COCI)
|
||||
.union(getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, POCI))
|
||||
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
|
||||
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
}
|
||||
|
||||
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath,
|
||||
|
|
Loading…
Reference in New Issue