removed the part after part-x- in the file name generated by spark. It was too long and created problems while creating the tar entries

This commit is contained in:
Miriam Baglioni 2021-04-13 16:30:59 +02:00
parent 04a0d1ba6e
commit 6179deb836
4 changed files with 40 additions and 0 deletions

View File

@ -90,6 +90,13 @@ public class MakeTarArchive implements Serializable {
String p_string = p.toString();
if (!p_string.endsWith("_SUCCESS")) {
String name = p_string.substring(p_string.lastIndexOf("/") + 1);
if (name.startsWith("part-") & name.length() > 10) {
String tmp = name.substring(0, 10);
if (name.contains(".")) {
tmp += name.substring(name.indexOf("."));
}
name = tmp;
}
TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name);
entry.setSize(fileStatus.getLen());
current_size += fileStatus.getLen();

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.oa.graph.dump.community;
public class RemoveCommunities {
}

View File

@ -0,0 +1,25 @@
[
{
"paramName":"is",
"paramLongName":"isLookUpUrl",
"paramDescription": "URL of the isLookUp Service",
"paramRequired": true
},
{
"paramName":"nn",
"paramLongName":"nameNode",
"paramDescription": "the name node",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
}
]

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp.oa.graph.dump.community;
public class RemoveCommunityTest {
}