sabeel
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

fixed a problem with empty mdstore list

This commit is contained in:
Michele Artini 2021-06-14 11:57:00 +02:00
parent cf360d7c97
commit 83132ee99a
1 changed files with 16 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateHdfsMdstoresApplication.java
View File

@ -14,6 +14,8 @@ 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;
@ -52,8 +54,7 @@ public class MigrateHdfsMdstoresApplication extends AbstractMigrationApplication
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
MigrateHdfsMdstoresApplication.class
.toString(MigrateHdfsMdstoresApplication.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/migrate_hdfs_mstores_parameters.json")));
parser.parseArgument(args);
@ -94,6 +95,7 @@ public class MigrateHdfsMdstoresApplication extends AbstractMigrationApplication
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
.toArray(size -> new String[size]);
if (validPaths.length > 0) {
spark
.read()
.parquet(validPaths)
@ -102,6 +104,9 @@ public class MigrateHdfsMdstoresApplication extends AbstractMigrationApplication
.mapToPair(xml -> new Tuple2<>(new Text(UUID.randomUUID() + ":" + type), new Text(xml)))
// .coalesce(1)
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
} else {
FileSystem.get(sc.hadoopConfiguration()).createNewFile(new Path(outputPath));
}
}
private static String enrichRecord(final Row r) {