1
0
Fork 0

added workflow upload on zenodo

This commit is contained in:
sandro 2020-10-20 16:09:07 +02:00
parent fed711da80
commit d58d02d448
4 changed files with 206 additions and 0 deletions

View File

@ -0,0 +1,111 @@
package eu.dnetlib.dhp.export.zenodo;
import java.io.*;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveOutputStream;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class MakeTar implements Serializable {
private static final Logger log = LoggerFactory.getLogger(MakeTar.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
MakeTar.class
.getResourceAsStream(
"/eu/dnetlib/dhp/export/input_maketar_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
final String outputPath = parser.get("targetPath");
log.info("hdfsPath: {}", outputPath);
final String hdfsNameNode = parser.get("nameNode");
log.info("nameNode: {}", hdfsNameNode);
final String inputPath = parser.get("sourcePath");
log.info("input path : {}", inputPath);
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
FileSystem fileSystem = FileSystem.get(conf);
makeTArArchive(fileSystem, inputPath, outputPath);
}
public static void makeTArArchive(FileSystem fileSystem, String inputPath, String outputPath) throws IOException {
RemoteIterator<LocatedFileStatus> dir_iterator = fileSystem.listLocatedStatus(new Path(inputPath));
while (dir_iterator.hasNext()) {
LocatedFileStatus fileStatus = dir_iterator.next();
Path p = fileStatus.getPath();
String p_string = p.toString();
String entity = p_string.substring(p_string.lastIndexOf("/") + 1);
write(fileSystem, p_string, outputPath + "/" + entity + ".tar", entity);
}
}
private static void write(FileSystem fileSystem, String inputPath, String outputPath, String dir_name)
throws IOException {
Path hdfsWritePath = new Path(outputPath);
FSDataOutputStream fsDataOutputStream = null;
if (fileSystem.exists(hdfsWritePath)) {
fileSystem.delete(hdfsWritePath, true);
}
fsDataOutputStream = fileSystem.create(hdfsWritePath);
TarArchiveOutputStream ar = new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
.listFiles(
new Path(inputPath), true);
while (fileStatusListIterator.hasNext()) {
LocatedFileStatus fileStatus = fileStatusListIterator.next();
Path p = fileStatus.getPath();
String p_string = p.toString();
if (!p_string.endsWith("_SUCCESS")) {
String name = p_string.substring(p_string.lastIndexOf("/") + 1);
TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name + ".json.gz");
entry.setSize(fileStatus.getLen());
ar.putArchiveEntry(entry);
InputStream is = fileSystem.open(fileStatus.getPath());
BufferedInputStream bis = new BufferedInputStream(is);
int count;
byte data[] = new byte[1024];
while ((count = bis.read(data, 0, data.length)) != -1) {
ar.write(data, 0, count);
}
bis.close();
ar.closeArchiveEntry();
}
}
ar.close();
}
}

View File

@ -0,0 +1,20 @@
[
{
"paramName": "n",
"paramLongName": "nameNode",
"paramDescription": "the Name Node",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the source path",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target path",
"paramRequired": true
}
]

View File

@ -0,0 +1,42 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.wf.rerun.failnodes</name>
<value>false</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
</property>
<property>
<name>spark2EventLogDir</name>
<value>/user/spark/spark2ApplicationHistory</value>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>"com.cloudera.spark.lineage.NavigatorAppListener"</value>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>"com.cloudera.spark.lineage.NavigatorQueryListener"</value>
</property>
</configuration>

View File

@ -0,0 +1,33 @@
<workflow-app name="Send Dump to Zenodo" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>targetPath</name>
<description>the target path</description>
</property>
</parameters>
<start to="MakeTar"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="MakeTar">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.dhp.export.zenodo.MakeTar</main-class>
<arg>-t</arg><arg>${targetPath}</arg>
<arg>-n</arg><arg>${nameNode}</arg>
<arg>-s</arg><arg>${sourcePath}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>