dimitris.pierrakos
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

fixed a problem with empty mdstore list (2)

This commit is contained in:
Michele Artini 2021-06-14 12:04:47 +02:00
parent 83132ee99a
commit ada063ce70
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateHdfsMdstoresApplication.java
View File

@ -14,8 +14,6 @@ import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
@ -105,7 +103,10 @@ public class MigrateHdfsMdstoresApplication extends AbstractMigrationApplication
// .coalesce(1)
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
} else {
FileSystem.get(sc.hadoopConfiguration()).createNewFile(new Path(outputPath));
spark.emptyDataFrame()
.toJavaRDD()
.mapToPair(xml -> new Tuple2<>(new Text(), new Text()))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
}
}